dify资产

{
  "code": 0,
  "data": {
    "plugins": [
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Ollama"
        },
        "category": "model",
        "created_at": "2024-12-04T09:46:32Z",
        "endpoint": {},
        "icon": "langgenius/packages/ollama/_assets/icon_s_en.svg",
        "index_id": "langgenius___ollama",
        "install_count": 129728,
        "introduction": "## Overview\n\nOllama is a cross-platform inference framework client (MacOS, Windows, Linux) designed for seamless deployment of large language models (LLMs) such as Llama 2, Mistral, Llava, and more. With its one-click setup, Ollama enables local execution of LLMs, providing enhanced data privacy and security by keeping your data on your own machine.\n\nDify supports integrating LLM and Text Embedding capabilities of large language models deployed with Ollama.\n\n## Configure\n\n#### 1. Download Ollama\nVisit [Ollama download page](https://ollama.com/download) to download the Ollama client for your system.\n\n#### 2. Run Ollama and Chat with Llava\n\n````\nollama run llama3.2\n````\n\nAfter successful launch, Ollama starts an API service on local port 11434, which can be accessed at `http://localhost:11434`.\n\nFor other models, visit [Ollama Models](https://ollama.com/library) for more details.\n\n#### 3. Install Ollama Plugin\nGo to the Dify marketplace and search the Ollama to download it.\n\n![](./_assets/ollama-01.png)\n\n#### 4. Integrate Ollama in Dify\n\nIn `Settings > Model Providers > Ollama`, fill in:\n\n![](./_assets/ollama-02.png)\n\n- Model Name：`llama3.2`\n- Base URL: `http://<your-ollama-endpoint-domain>:11434`\n- Enter the base URL where the Ollama service is accessible.\n- If Dify is deployed using Docker, consider using the local network IP address, e.g., `http://192.168.1.100:11434` or `http://host.docker.internal:11434` to access the service.\n- For local source code deployment, use `http://localhost:11434`.\n- Model Type: `Chat`\n- Model Context Length: `4096`\n- The maximum context length of the model. If unsure, use the default value of 4096.\n- Maximum Token Limit: `4096`\n- The maximum number of tokens returned by the model. If there are no specific requirements for the model, this can be consistent with the model context length.\n- Support for Vision: `Yes`\n- Check this option if the model supports image understanding (multimodal), like `llava`.\n\nClick \"Save\" to use the model in the application after verifying that there are no errors.\n\nThe integration method for Embedding models is similar to LLM, just change the model type to Text Embedding.\n\nFor more detail, please check [Dify's official document](https://docs.dify.ai/development/models-integration/ollama).\n",
        "label": {
          "en_US": "Ollama"
        },
        "latest_package_identifier": "langgenius/ollama:0.0.5@cc38c90a58d4b4e43c9a821d352829b2c2a8d6d742de9fec9e61e6b34865b496",
        "latest_version": "0.0.5",
        "model": {
          "background": "#F9FAFB",
          "configurate_methods": [
            "customizable-model"
          ],
          "description": {
            "en_US": "Ollama"
          },
          "help": {
            "title": {
              "en_US": "How to integrate with Ollama",
              "zh_Hans": "如何集成 Ollama"
            },
            "url": {
              "en_US": "https://docs.dify.ai/tutorials/model-configuration/ollama"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.svg"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "Ollama"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "Base URL",
                  "zh_Hans": "基础 URL"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Base url of Ollama server, e.g. http://192.168.1.100:11434",
                  "zh_Hans": "Ollama server 的基础 URL，例如 http://192.168.1.100:11434"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "base_url"
              },
              {
                "default": "chat",
                "label": {
                  "en_US": "Completion mode",
                  "zh_Hans": "模型类型"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Completion",
                      "zh_Hans": "补全"
                    },
                    "show_on": [],
                    "value": "completion"
                  },
                  {
                    "label": {
                      "en_US": "Chat",
                      "zh_Hans": "对话"
                    },
                    "show_on": [],
                    "value": "chat"
                  }
                ],
                "placeholder": {
                  "en_US": "Select completion mode",
                  "zh_Hans": "选择对话类型"
                },
                "required": true,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "select",
                "variable": "mode"
              },
              {
                "default": "4096",
                "label": {
                  "en_US": "Model context size",
                  "zh_Hans": "模型上下文长度"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Model context size",
                  "zh_Hans": "在此输入您的模型上下文长度"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "context_size"
              },
              {
                "default": "4096",
                "label": {
                  "en_US": "Upper bound for max tokens",
                  "zh_Hans": "最大 token 上限"
                },
                "max_length": 0,
                "options": [],
                "placeholder": null,
                "required": true,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "text-input",
                "variable": "max_tokens"
              },
              {
                "default": "false",
                "label": {
                  "en_US": "Vision support",
                  "zh_Hans": "是否支持 Vision"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Yes",
                      "zh_Hans": "是"
                    },
                    "show_on": [],
                    "value": "true"
                  },
                  {
                    "label": {
                      "en_US": "No",
                      "zh_Hans": "否"
                    },
                    "show_on": [],
                    "value": "false"
                  }
                ],
                "placeholder": null,
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "radio",
                "variable": "vision_support"
              },
              {
                "default": "false",
                "label": {
                  "en_US": "Function call support",
                  "zh_Hans": "是否支持函数调用"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Yes",
                      "zh_Hans": "是"
                    },
                    "show_on": [],
                    "value": "true"
                  },
                  {
                    "label": {
                      "en_US": "No",
                      "zh_Hans": "否"
                    },
                    "show_on": [],
                    "value": "false"
                  }
                ],
                "placeholder": null,
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "radio",
                "variable": "function_call_support"
              }
            ],
            "model": {
              "label": {
                "en_US": "Model Name",
                "zh_Hans": "模型名称"
              },
              "placeholder": {
                "en_US": "Enter your model name",
                "zh_Hans": "输入模型名称"
              }
            }
          },
          "models": [],
          "provider": "ollama",
          "provider_credential_schema": null,
          "supported_model_types": [
            "llm",
            "text-embedding"
          ]
        },
        "name": "ollama",
        "org": "langgenius",
        "plugin_id": "langgenius/ollama",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/ollama.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-10T06:30:33Z",
        "version_updated_at": "2025-04-10T06:30:33Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Models provided by OpenAI, such as GPT-3.5-Turbo and GPT-4.",
          "zh_Hans": "OpenAI 提供的模型，例如 GPT-3.5-Turbo 和 GPT-4。"
        },
        "category": "model",
        "created_at": "2024-11-22T08:07:23Z",
        "endpoint": {},
        "icon": "langgenius/packages/openai/_assets/icon_s_en.svg",
        "index_id": "langgenius___openai",
        "install_count": 99832,
        "introduction": "## Overview\nOpenAI offers a comprehensive set of models for various tasks, including text generation, image generation, vision, audio generation, text-to-speech (TTS), speech-to-text (STT), embeddings, moderation, and reasoning.\nThis plugin allows developers to integrate LLMs such as GPT-3.5, GPT-4, and the o1 family (including custom fine-tuned versions) via the API, with support for function calling.\n\n## Configure\nAfter installing the plugin, configure your OpenAI settings in the Model Provider section. This includes your API key (find it [here](https://platform.openai.com/account/api-keys)) and optional Organization ID and API Base. Save to use OpenAI.\n\n<img src=\"./_assets/openai-01.png\" width=\"400\" />\n",
        "label": {
          "en_US": "OpenAI"
        },
        "latest_package_identifier": "langgenius/openai:0.0.19@6b2b2e115b1b9d34a63eb26fadcc33d74330fd2ec06071bb30b8a24b1fab107a",
        "latest_version": "0.0.19",
        "model": {
          "background": "#E5E7EB",
          "configurate_methods": [
            "predefined-model",
            "customizable-model"
          ],
          "description": {
            "en_US": "Models provided by OpenAI, such as GPT-3.5-Turbo and GPT-4.",
            "zh_Hans": "OpenAI 提供的模型，例如 GPT-3.5-Turbo 和 GPT-4。"
          },
          "help": {
            "title": {
              "en_US": "Get your API Key from OpenAI",
              "zh_Hans": "从 OpenAI 获取 API Key"
            },
            "url": {
              "en_US": "https://platform.openai.com/account/api-keys"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.svg"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "OpenAI"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "openai_api_key"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Organization",
                  "zh_Hans": "组织 ID"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Organization ID",
                  "zh_Hans": "在此输入您的组织 ID"
                },
                "required": false,
                "show_on": [],
                "type": "text-input",
                "variable": "openai_organization"
              },
              {
                "default": null,
                "label": {
                  "en_US": "API Base",
                  "zh_Hans": "API Base"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Base",
                  "zh_Hans": "在此输入您的 API Base"
                },
                "required": false,
                "show_on": [],
                "type": "text-input",
                "variable": "openai_api_base"
              }
            ],
            "model": {
              "label": {
                "en_US": "Model Name",
                "zh_Hans": "模型名称"
              },
              "placeholder": {
                "en_US": "Enter your model name",
                "zh_Hans": "输入模型名称"
              }
            }
          },
          "models": [
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "chatgpt-4o-latest",
                "zh_Hans": "chatgpt-4o-latest"
              },
              "model": "chatgpt-4o-latest",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 16384,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "2.5",
                "output": "10",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-3.5-turbo-0125",
                "zh_Hans": "gpt-3.5-turbo-0125"
              },
              "model": "gpt-3.5-turbo-0125",
              "model_properties": {
                "context_size": 16385,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0005",
                "output": "0.0015",
                "unit": "0.001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-3.5-turbo-0613",
                "zh_Hans": "gpt-3.5-turbo-0613"
              },
              "model": "gpt-3.5-turbo-0613",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0015",
                "output": "0.002",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-3.5-turbo-1106",
                "zh_Hans": "gpt-3.5-turbo-1106"
              },
              "model": "gpt-3.5-turbo-1106",
              "model_properties": {
                "context_size": 16385,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.001",
                "output": "0.002",
                "unit": "0.001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-3.5-turbo-16k-0613",
                "zh_Hans": "gpt-3.5-turbo-16k-0613"
              },
              "model": "gpt-3.5-turbo-16k-0613",
              "model_properties": {
                "context_size": 16385,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 16385,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.003",
                "output": "0.004",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-3.5-turbo-16k",
                "zh_Hans": "gpt-3.5-turbo-16k"
              },
              "model": "gpt-3.5-turbo-16k",
              "model_properties": {
                "context_size": 16385,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 16385,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.003",
                "output": "0.004",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-3.5-turbo-instruct",
                "zh_Hans": "gpt-3.5-turbo-instruct"
              },
              "model": "gpt-3.5-turbo-instruct",
              "model_properties": {
                "context_size": 4096,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0015",
                "output": "0.002",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-3.5-turbo",
                "zh_Hans": "gpt-3.5-turbo"
              },
              "model": "gpt-3.5-turbo",
              "model_properties": {
                "context_size": 16385,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0005",
                "output": "0.0015",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-4-0125-preview",
                "zh_Hans": "gpt-4-0125-preview"
              },
              "model": "gpt-4-0125-preview",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "If specified, model will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.",
                    "zh_Hans": "如果指定，模型将尽最大努力进行确定性采样，使得重复的具有相同种子和参数的请求应该返回相同的结果。不能保证确定性，您应该参考 system_fingerprint 响应参数来监视变化。"
                  },
                  "label": {
                    "en_US": "Seed",
                    "zh_Hans": "种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.01",
                "output": "0.03",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-4-1106-preview",
                "zh_Hans": "gpt-4-1106-preview"
              },
              "model": "gpt-4-1106-preview",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "If specified, model will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.",
                    "zh_Hans": "如果指定，模型将尽最大努力进行确定性采样，使得重复的具有相同种子和参数的请求应该返回相同的结果。不能保证确定性，您应该参考 system_fingerprint 响应参数来监视变化。"
                  },
                  "label": {
                    "en_US": "Seed",
                    "zh_Hans": "种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.01",
                "output": "0.03",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-4-32k",
                "zh_Hans": "gpt-4-32k"
              },
              "model": "gpt-4-32k",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 32768,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "If specified, model will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.",
                    "zh_Hans": "如果指定，模型将尽最大努力进行确定性采样，使得重复的具有相同种子和参数的请求应该返回相同的结果。不能保证确定性，您应该参考 system_fingerprint 响应参数来监视变化。"
                  },
                  "label": {
                    "en_US": "Seed",
                    "zh_Hans": "种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.06",
                "output": "0.12",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-4-turbo-2024-04-09",
                "zh_Hans": "gpt-4-turbo-2024-04-09"
              },
              "model": "gpt-4-turbo-2024-04-09",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "If specified, model will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.",
                    "zh_Hans": "如果指定，模型将尽最大努力进行确定性采样，使得重复的具有相同种子和参数的请求应该返回相同的结果。不能保证确定性，您应该参考 system_fingerprint 响应参数来监视变化。"
                  },
                  "label": {
                    "en_US": "Seed",
                    "zh_Hans": "种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.01",
                "output": "0.03",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-4-turbo-preview",
                "zh_Hans": "gpt-4-turbo-preview"
              },
              "model": "gpt-4-turbo-preview",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "If specified, model will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.",
                    "zh_Hans": "如果指定，模型将尽最大努力进行确定性采样，使得重复的具有相同种子和参数的请求应该返回相同的结果。不能保证确定性，您应该参考 system_fingerprint 响应参数来监视变化。"
                  },
                  "label": {
                    "en_US": "Seed",
                    "zh_Hans": "种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.01",
                "output": "0.03",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-4-turbo",
                "zh_Hans": "gpt-4-turbo"
              },
              "model": "gpt-4-turbo",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "If specified, model will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.",
                    "zh_Hans": "如果指定，模型将尽最大努力进行确定性采样，使得重复的具有相同种子和参数的请求应该返回相同的结果。不能保证确定性，您应该参考 system_fingerprint 响应参数来监视变化。"
                  },
                  "label": {
                    "en_US": "Seed",
                    "zh_Hans": "种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.01",
                "output": "0.03",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-4-vision-preview",
                "zh_Hans": "gpt-4-vision-preview"
              },
              "model": "gpt-4-vision-preview",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "If specified, model will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.",
                    "zh_Hans": "如果指定，模型将尽最大努力进行确定性采样，使得重复的具有相同种子和参数的请求应该返回相同的结果。不能保证确定性，您应该参考 system_fingerprint 响应参数来监视变化。"
                  },
                  "label": {
                    "en_US": "Seed",
                    "zh_Hans": "种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.01",
                "output": "0.03",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-4.1-2025-04-14",
                "zh_Hans": "gpt-4.1-2025-04-14"
              },
              "model": "gpt-4.1-2025-04-14",
              "model_properties": {
                "context_size": 1047576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 32768,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object",
                    "json_schema"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "2",
                "output": "8",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-4.1-mini-2025-04-14",
                "zh_Hans": "gpt-4.1-mini-2025-04-14"
              },
              "model": "gpt-4.1-mini-2025-04-14",
              "model_properties": {
                "context_size": 1047576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 32768,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object",
                    "json_schema"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.4",
                "output": "1.6",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-4.1-mini",
                "zh_Hans": "gpt-4.1-mini"
              },
              "model": "gpt-4.1-mini",
              "model_properties": {
                "context_size": 1047576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 32768,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object",
                    "json_schema"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.4",
                "output": "1.6",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-4.1-nano-2025-04-14",
                "zh_Hans": "gpt-4.1-nano-2025-04-14"
              },
              "model": "gpt-4.1-nano-2025-04-14",
              "model_properties": {
                "context_size": 1047576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 32768,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object",
                    "json_schema"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.1",
                "output": "0.4",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-4.1-nano",
                "zh_Hans": "gpt-4.1-nano"
              },
              "model": "gpt-4.1-nano",
              "model_properties": {
                "context_size": 1047576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 32768,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object",
                    "json_schema"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.1",
                "output": "0.4",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-4.1",
                "zh_Hans": "gpt-4.1"
              },
              "model": "gpt-4.1",
              "model_properties": {
                "context_size": 1047576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 32768,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object",
                    "json_schema"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "2",
                "output": "8",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-4",
                "zh_Hans": "gpt-4"
              },
              "model": "gpt-4",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "If specified, model will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.",
                    "zh_Hans": "如果指定，模型将尽最大努力进行确定性采样，使得重复的具有相同种子和参数的请求应该返回相同的结果。不能保证确定性，您应该参考 system_fingerprint 响应参数来监视变化。"
                  },
                  "label": {
                    "en_US": "Seed",
                    "zh_Hans": "种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.03",
                "output": "0.06",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-4o-2024-05-13",
                "zh_Hans": "gpt-4o-2024-05-13"
              },
              "model": "gpt-4o-2024-05-13",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "5",
                "output": "15",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-4o-2024-08-06",
                "zh_Hans": "gpt-4o-2024-08-06"
              },
              "model": "gpt-4o-2024-08-06",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 16384,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object",
                    "json_schema"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "2.5",
                "output": "10",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-4o-2024-11-20",
                "zh_Hans": "gpt-4o-2024-11-20"
              },
              "model": "gpt-4o-2024-11-20",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 16384,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object",
                    "json_schema"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "2.5",
                "output": "10",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-4o-audio-preview",
                "zh_Hans": "gpt-4o-audio-preview"
              },
              "model": "gpt-4o-audio-preview",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "5",
                "output": "15",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-4o-mini-2024-07-18",
                "zh_Hans": "gpt-4o-mini-2024-07-18"
              },
              "model": "gpt-4o-mini-2024-07-18",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 16384,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object",
                    "json_schema"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.15",
                "output": "0.6",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-4o-mini",
                "zh_Hans": "gpt-4o-mini"
              },
              "model": "gpt-4o-mini",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 16384,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object",
                    "json_schema"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.15",
                "output": "0.6",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-4o",
                "zh_Hans": "gpt-4o"
              },
              "model": "gpt-4o",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object",
                    "json_schema"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "5",
                "output": "15",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "o1-mini-2024-09-12",
                "zh_Hans": "o1-mini-2024-09-12"
              },
              "model": "o1-mini-2024-09-12",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 65536,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 65536,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "response_format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "3",
                "output": "12",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "o1-mini",
                "zh_Hans": "o1-mini"
              },
              "model": "o1-mini",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 65536,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 65536,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "response_format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "3",
                "output": "12",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "o1-preview-2024-09-12",
                "zh_Hans": "o1-preview-2024-09-12"
              },
              "model": "o1-preview-2024-09-12",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 32768,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 32768,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "response_format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "15",
                "output": "60",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "o1-preview",
                "zh_Hans": "o1-preview"
              },
              "model": "o1-preview",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 32768,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 32768,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "response_format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "15",
                "output": "60",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "o1",
                "zh_Hans": "o1"
              },
              "model": "o1",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 50000,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 50000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "constrains effort on reasoning for reasoning models",
                    "zh_Hans": "限制推理模型的推理工作"
                  },
                  "label": {
                    "en_US": "reasoning_effort",
                    "zh_Hans": "推理工作"
                  },
                  "max": null,
                  "min": null,
                  "name": "reasoning_effort",
                  "options": [
                    "low",
                    "medium",
                    "high"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "response_format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object",
                    "json_schema"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "15",
                "output": "60",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "o3-mini-2025-01-31",
                "zh_Hans": "o3-mini-2025-01-31"
              },
              "model": "o3-mini-2025-01-31",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 100000,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 100000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "constrains effort on reasoning for reasoning models",
                    "zh_Hans": "限制推理模型的推理工作"
                  },
                  "label": {
                    "en_US": "reasoning_effort",
                    "zh_Hans": "推理工作"
                  },
                  "max": null,
                  "min": null,
                  "name": "reasoning_effort",
                  "options": [
                    "low",
                    "medium",
                    "high"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "response_format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object",
                    "json_schema"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "1.1",
                "output": "4.4",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "o3-mini",
                "zh_Hans": "o3-mini"
              },
              "model": "o3-mini",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 100000,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 100000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "constrains effort on reasoning for reasoning models",
                    "zh_Hans": "限制推理模型的推理工作"
                  },
                  "label": {
                    "en_US": "reasoning_effort",
                    "zh_Hans": "推理工作"
                  },
                  "max": null,
                  "min": null,
                  "name": "reasoning_effort",
                  "options": [
                    "low",
                    "medium",
                    "high"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "response_format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object",
                    "json_schema"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "1.1",
                "output": "4.4",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": true,
              "features": [],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "text-davinci-003",
                "zh_Hans": "text-davinci-003"
              },
              "model": "text-davinci-003",
              "model_properties": {
                "context_size": 4096,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.001",
                "output": "0.002",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "text-moderation-stable"
              },
              "model": "text-moderation-stable",
              "model_properties": {
                "max_characters_per_chunk": 2000,
                "max_chunks": 32
              },
              "model_type": "moderation",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "whisper-1"
              },
              "model": "whisper-1",
              "model_properties": {
                "file_upload_limit": 25,
                "supported_file_extensions": "flac,mp3,mp4,mpeg,mpga,m4a,ogg,wav,webm"
              },
              "model_type": "speech2text",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "text-embedding-3-large"
              },
              "model": "text-embedding-3-large",
              "model_properties": {
                "context_size": 8191,
                "max_chunks": 32
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.00013",
                "output": null,
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "text-embedding-3-small"
              },
              "model": "text-embedding-3-small",
              "model_properties": {
                "context_size": 8191,
                "max_chunks": 32
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.00002",
                "output": null,
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "text-embedding-ada-002"
              },
              "model": "text-embedding-ada-002",
              "model_properties": {
                "context_size": 8097,
                "max_chunks": 32
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.0001",
                "output": null,
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-4o-mini-tts"
              },
              "model": "gpt-4o-mini-tts",
              "model_properties": {
                "audio_type": "mp3",
                "default_voice": "alloy",
                "max_workers": 5,
                "voices": [
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "alloy",
                    "name": "Alloy"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "ash",
                    "name": "Ash"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "ballad",
                    "name": "Ballad"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "coral",
                    "name": "Coral"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "echo",
                    "name": "Echo"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "fable",
                    "name": "Fable"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "onyx",
                    "name": "Onyx"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "nova",
                    "name": "Nova"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "sage",
                    "name": "Sage"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "shimmer",
                    "name": "Shimmer"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "verse",
                    "name": "Verse"
                  }
                ],
                "word_limit": 3500
              },
              "model_type": "tts",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.012",
                "output": "0",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "tts-1-hd"
              },
              "model": "tts-1-hd",
              "model_properties": {
                "audio_type": "mp3",
                "default_voice": "alloy",
                "max_workers": 5,
                "voices": [
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "alloy",
                    "name": "Alloy"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "ash",
                    "name": "Ash"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "ballad",
                    "name": "Ballad"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "coral",
                    "name": "Coral"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "echo",
                    "name": "Echo"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "fable",
                    "name": "Fable"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "onyx",
                    "name": "Onyx"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "nova",
                    "name": "Nova"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "sage",
                    "name": "Sage"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "shimmer",
                    "name": "Shimmer"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "verse",
                    "name": "Verse"
                  }
                ],
                "word_limit": 3500
              },
              "model_type": "tts",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.03",
                "output": "0",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "tts-1"
              },
              "model": "tts-1",
              "model_properties": {
                "audio_type": "mp3",
                "default_voice": "alloy",
                "max_workers": 5,
                "voices": [
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "alloy",
                    "name": "Alloy"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "ash",
                    "name": "Ash"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "ballad",
                    "name": "Ballad"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "coral",
                    "name": "Coral"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "echo",
                    "name": "Echo"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "fable",
                    "name": "Fable"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "onyx",
                    "name": "Onyx"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "nova",
                    "name": "Nova"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "sage",
                    "name": "Sage"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "shimmer",
                    "name": "Shimmer"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "verse",
                    "name": "Verse"
                  }
                ],
                "word_limit": 3500
              },
              "model_type": "tts",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.015",
                "output": "0",
                "unit": "0.001"
              }
            }
          ],
          "position": {
            "llm": [
              "o1",
              "o1-2024-12-17",
              "o1-mini",
              "o1-mini-2024-09-12",
              "o3-mini",
              "o3-mini-2025-01-31",
              "gpt-4",
              "gpt-4o",
              "gpt-4o-2024-05-13",
              "gpt-4o-2024-08-06",
              "gpt-4o-2024-11-20",
              "gpt-4.1",
              "gpt-4.1-2025-04-14",
              "gpt-4.1-mini",
              "gpt-4.1-mini-2025-04-14",
              "gpt-4.1-nano",
              "gpt-4.1-nano-2025-04-14",
              "gpt-4-turbo",
              "gpt-4-turbo-2024-04-09",
              "gpt-4-turbo-preview",
              "gpt-4-32k",
              "gpt-4-1106-preview",
              "gpt-4-0125-preview",
              "gpt-4-vision-preview",
              "gpt-3.5-turbo",
              "gpt-3.5-turbo-16k",
              "gpt-3.5-turbo-16k-0613",
              "gpt-3.5-turbo-0125",
              "gpt-3.5-turbo-1106",
              "gpt-3.5-turbo-0613",
              "gpt-3.5-turbo-instruct",
              "text-davinci-003"
            ]
          },
          "provider": "openai",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "openai_api_key"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Organization",
                  "zh_Hans": "组织 ID"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Organization ID",
                  "zh_Hans": "在此输入您的组织 ID"
                },
                "required": false,
                "show_on": [],
                "type": "text-input",
                "variable": "openai_organization"
              },
              {
                "default": null,
                "label": {
                  "en_US": "API Base",
                  "zh_Hans": "API Base"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Base, e.g. https://api.openai.com",
                  "zh_Hans": "在此输入您的 API Base, 如：https://api.openai.com"
                },
                "required": false,
                "show_on": [],
                "type": "text-input",
                "variable": "openai_api_base"
              }
            ]
          },
          "supported_model_types": [
            "llm",
            "text-embedding",
            "speech2text",
            "moderation",
            "tts"
          ]
        },
        "name": "openai",
        "org": "langgenius",
        "plugin_id": "langgenius/openai",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/openai.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "utilities"
          }
        ],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-16T06:18:40Z",
        "version_updated_at": "2025-04-16T06:18:40Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Models provided by deepseek, such as deepseek-chat、deepseek-coder.",
          "zh_Hans": "深度求索提供的模型，例如 deepseek-chat、deepseek-coder 。"
        },
        "category": "model",
        "created_at": "2024-11-29T11:49:55Z",
        "endpoint": {},
        "icon": "langgenius/packages/deepseek/_assets/icon_s_en.svg",
        "index_id": "langgenius___deepseek",
        "install_count": 79186,
        "introduction": "# Overview\nDeepSeek provides advanced AI capabilities for chats and completions. This plugin enables developers to integrate DeepSeek's models, including text generation (deepseek-chat and deepseek-code) via the API.\n\n# Configure\nAfter installation, you need to get API keys from [Deepseek](https://platform.deepseek.com/api_keys) and setup in Settings -> Model Provider.\n\n![](_assets/deepseek.PNG)",
        "label": {
          "en_US": "DeepSeek",
          "zh_Hans": "深度求索"
        },
        "latest_package_identifier": "langgenius/deepseek:0.0.5@fd6efd37c2a931911de8ab9ca3ba2da303bef146d45ee87ad896b04b36d09403",
        "latest_version": "0.0.5",
        "model": {
          "background": "#c0cdff",
          "configurate_methods": [
            "predefined-model"
          ],
          "description": {
            "en_US": "Models provided by deepseek, such as deepseek-reasoner、deepseek-chat、deepseek-coder.",
            "zh_Hans": "深度求索提供的模型，例如 deepseek-reasoner、deepseek-chat、deepseek-coder 。"
          },
          "help": {
            "title": {
              "en_US": "Get your API Key from deepseek",
              "zh_Hans": "从深度求索获取 API Key"
            },
            "url": {
              "en_US": "https://platform.deepseek.com/api_keys"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.svg"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "deepseek",
            "zh_Hans": "深度求索"
          },
          "model_credential_schema": null,
          "models": [
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "multi-tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "deepseek-chat",
                "zh_Hans": "deepseek-chat"
              },
              "model": "deepseek-chat",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Control the diversity and randomness of generated results. The smaller the value, the more rigorous it is; the larger the value, the more divergent it is.",
                    "zh_Hans": "控制生成结果的多样性和随机性。数值越小，越严谨；数值越大，越发散。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Control the randomness of generated results. The smaller the value, the weaker the randomness; the larger the value, the stronger the randomness. Generally speaking, you can adjust one of the two parameters top_p and temperature.",
                    "zh_Hans": "控制生成结果的随机性。数值越小，随机性越弱；数值越大，随机性越强。一般而言，top_p 和 temperature 两个参数选择一个进行调整即可。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0.01,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Whether to return the log probability of the output token. If true, returns the log probability of each output token in the content of message .",
                    "zh_Hans": "是否返回所输出 token 的对数概率。如果为 true，则在 message 的 content 中返回每个输出 token 的对数概率。"
                  },
                  "label": {
                    "en_US": "Logprobs"
                  },
                  "max": null,
                  "min": null,
                  "name": "logprobs",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "An integer N between 0 and 20, specifying that each output position returns the top N tokens with output probability, and returns the logarithmic probability of these tokens. When specifying this parameter, logprobs must be true.",
                    "zh_Hans": "一个介于 0 到 20 之间的整数 N，指定每个输出位置返回输出概率 top N 的 token，且返回这些 token 的对数概率。指定此参数时，logprobs 必须为 true。"
                  },
                  "label": {
                    "en_US": "Top Logprobs"
                  },
                  "max": 20,
                  "min": 0,
                  "name": "top_logprobs",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "A number between -2.0 and 2.0. If the value is positive, new tokens are penalized based on their frequency of occurrence in existing text, reducing the likelihood that the model will repeat the same content.",
                    "zh_Hans": "介于 -2.0 和 2.0 之间的数字。如果该值为正，那么新 token 会根据其在已有文本中的出现频率受到相应的惩罚，降低模型重复相同内容的可能性。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "2",
                "output": "8",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "multi-tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "deepseek-coder",
                "zh_Hans": "deepseek-coder"
              },
              "model": "deepseek-coder",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "deepseek-reasoner",
                "zh_Hans": "deepseek-reasoner"
              },
              "model": "deepseek-reasoner",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "4",
                "output": "16",
                "unit": "0.000001"
              }
            }
          ],
          "position": {
            "llm": [
              "deepseek-chat",
              "deepseek-coder",
              "deepseek-reasoner"
            ]
          },
          "provider": "deepseek",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Custom API endpoint URL",
                  "zh_Hans": "自定义 API endpoint 地址"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Base URL, e.g. https://api.deepseek.com/v1 or https://api.deepseek.com",
                  "zh_Hans": "Base URL, e.g. https://api.deepseek.com/v1 or https://api.deepseek.com"
                },
                "required": false,
                "show_on": [],
                "type": "text-input",
                "variable": "endpoint_url"
              }
            ]
          },
          "supported_model_types": [
            "llm"
          ]
        },
        "name": "deepseek",
        "org": "langgenius",
        "plugin_id": "langgenius/deepseek",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/deepseek.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-02-17T06:57:29Z",
        "version_updated_at": "2025-02-17T06:57:29Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "TONGYI",
          "zh_Hans": "通义千问"
        },
        "category": "model",
        "created_at": "2024-12-05T08:52:27Z",
        "endpoint": {},
        "icon": "langgenius/packages/tongyi/_assets/icon_s_en.png",
        "index_id": "langgenius___tongyi",
        "install_count": 68610,
        "introduction": "# Overview\nTongyi Qwen, developed by Alibaba Cloud, is a sophisticated series of LLMs. It includes multiple variants, such as Qwen for text processing, Qwen-VL for vision-language tasks, and Qwen-Audio for audio understanding. The models are notable for their impressive scale, with the flagship Qwen-72B model featuring 72 billion parameters and trained on over 3 trillion tokens.\n\n# Configure\nAfter installation, you need to get API keys from [Alibaba Cloud](https://bailian.console.aliyun.com/?apiKey=1#/api-key) and setup in Settings -> Model Provider.\n\n![](_assets/tongyi.PNG)\n",
        "label": {
          "en_US": "TONGYI",
          "zh_Hans": "通义千问"
        },
        "latest_package_identifier": "langgenius/tongyi:0.0.18@ca40ec06ff35ca611fa5fdf99a15eeb007a9fe3bd725c9ff6d0436469ab0edc9",
        "latest_version": "0.0.18",
        "model": {
          "background": "#EFF1FE",
          "configurate_methods": [
            "predefined-model",
            "customizable-model"
          ],
          "description": {
            "en_US": "TONGYI",
            "zh_Hans": "通义千问"
          },
          "help": {
            "title": {
              "en_US": "Get your API key from AliCloud",
              "zh_Hans": "从阿里云百炼获取 API Key"
            },
            "url": {
              "en_US": "https://bailian.console.aliyun.com/?apiKey=1#/api-key"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.png",
            "zh_Hans": "icon_l_zh.png"
          },
          "icon_small": {
            "en_US": "icon_s_en.png"
          },
          "label": {
            "en_US": "TONGYI",
            "zh_Hans": "通义千问"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "dashscope_api_key"
              },
              {
                "default": "4096",
                "label": {
                  "en_US": "Model context size",
                  "zh_Hans": "模型上下文长度"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Model context size",
                  "zh_Hans": "在此输入您的模型上下文长度"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "context_size"
              },
              {
                "default": "4096",
                "label": {
                  "en_US": "Upper bound for max tokens",
                  "zh_Hans": "最大 token 上限"
                },
                "max_length": 0,
                "options": [],
                "placeholder": null,
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "text-input",
                "variable": "max_tokens"
              },
              {
                "default": "no_call",
                "label": {
                  "en_US": "Function calling"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Not Support",
                      "zh_Hans": "不支持"
                    },
                    "show_on": [],
                    "value": "no_call"
                  },
                  {
                    "label": {
                      "en_US": "Support",
                      "zh_Hans": "支持"
                    },
                    "show_on": [],
                    "value": "function_call"
                  }
                ],
                "placeholder": null,
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "select",
                "variable": "function_calling_type"
              }
            ],
            "model": {
              "label": {
                "en_US": "Model Name",
                "zh_Hans": "模型名称"
              },
              "placeholder": {
                "en_US": "Enter your model name",
                "zh_Hans": "输入模型名称"
              }
            }
          },
          "models": [
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "DeepSeek-R1-Distill-Qwen-14B",
                "zh_Hans": "DeepSeek-R1-Distill-Qwen-14B"
              },
              "model": "deepseek-r1-distill-qwen-14b",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.001",
                "output": "0.003",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "DeepSeek-R1-Distill-Qwen-32B",
                "zh_Hans": "DeepSeek-R1-Distill-Qwen-32B"
              },
              "model": "deepseek-r1-distill-qwen-32b",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.002",
                "output": "0.006",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "DeepSeek-R1",
                "zh_Hans": "DeepSeek-R1"
              },
              "model": "deepseek-r1",
              "model_properties": {
                "context_size": 64000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.004",
                "output": "0.016",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "DeepSeek-V3",
                "zh_Hans": "DeepSeek-V3"
              },
              "model": "deepseek-v3",
              "model_properties": {
                "context_size": 64000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.002",
                "output": "0.008",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "farui-plus"
              },
              "model": "farui-plus",
              "model_properties": {
                "context_size": 12288,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 2000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.02",
                "output": "0.02",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-coder-turbo-0919"
              },
              "model": "qwen-coder-turbo-0919",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.002",
                "output": "0.006",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-coder-turbo-latest"
              },
              "model": "qwen-coder-turbo-latest",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.002",
                "output": "0.006",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-coder-turbo"
              },
              "model": "qwen-coder-turbo",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.002",
                "output": "0.006",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call",
                "document"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-long"
              },
              "model": "qwen-long",
              "model_properties": {
                "context_size": 10000000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 2000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 6000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.0005",
                "output": "0.002",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-math-plus-0816"
              },
              "model": "qwen-math-plus-0816",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 3072,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 3072,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.004",
                "output": "0.012",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-math-plus-0919"
              },
              "model": "qwen-math-plus-0919",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 3072,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 3072,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.004",
                "output": "0.012",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-math-plus-latest"
              },
              "model": "qwen-math-plus-latest",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 3072,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 3072,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.004",
                "output": "0.012",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-math-plus"
              },
              "model": "qwen-math-plus",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 3072,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 3072,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.004",
                "output": "0.012",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-math-turbo-0919"
              },
              "model": "qwen-math-turbo-0919",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 3072,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 3072,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.002",
                "output": "0.006",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-math-turbo-latest"
              },
              "model": "qwen-math-turbo-latest",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 3072,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 3072,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.002",
                "output": "0.006",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-math-turbo"
              },
              "model": "qwen-math-turbo",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 3072,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 3072,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.002",
                "output": "0.006",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-max-0107"
              },
              "model": "qwen-max-0107",
              "model_properties": {
                "context_size": 8000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 2000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.04",
                "output": "0.12",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-max-0125"
              },
              "model": "qwen-max-0125",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.0024",
                "output": "0.0096",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-max-0403"
              },
              "model": "qwen-max-0403",
              "model_properties": {
                "context_size": 8000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 2000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.04",
                "output": "0.12",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-max-0428"
              },
              "model": "qwen-max-0428",
              "model_properties": {
                "context_size": 8000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 2000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.04",
                "output": "0.12",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-max-0919"
              },
              "model": "qwen-max-0919",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.02",
                "output": "0.06",
                "unit": "0.001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-max-1201"
              },
              "model": "qwen-max-1201",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 2000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.04",
                "output": "0.12",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-max-latest"
              },
              "model": "qwen-max-latest",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.0024",
                "output": "0.0096",
                "unit": "0.001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-max-longcontext"
              },
              "model": "qwen-max-longcontext",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.04",
                "output": "0.12",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-max"
              },
              "model": "qwen-max",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.0024",
                "output": "0.0096",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-plus-0112"
              },
              "model": "qwen-plus-0112",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.0008",
                "output": "0.002",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-plus-0125"
              },
              "model": "qwen-plus-0125",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.0008",
                "output": "0.002",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-plus-0206"
              },
              "model": "qwen-plus-0206",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.004",
                "output": "0.012",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-plus-0624"
              },
              "model": "qwen-plus-0624",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.004",
                "output": "0.012",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-plus-0723"
              },
              "model": "qwen-plus-0723",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.004",
                "output": "0.012",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-plus-0806"
              },
              "model": "qwen-plus-0806",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.004",
                "output": "0.012",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-plus-0919"
              },
              "model": "qwen-plus-0919",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.0008",
                "output": "0.002",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-plus-1125"
              },
              "model": "qwen-plus-1125",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.0008",
                "output": "0.002",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-plus-1127"
              },
              "model": "qwen-plus-1127",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.0008",
                "output": "0.002",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-plus-1220"
              },
              "model": "qwen-plus-1220",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.0008",
                "output": "0.002",
                "unit": "0.001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-plus-chat"
              },
              "model": "qwen-plus-chat",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 2000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.004",
                "output": "0.012",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-plus-latest"
              },
              "model": "qwen-plus-latest",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.0008",
                "output": "0.002",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-plus"
              },
              "model": "qwen-plus",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.0008",
                "output": "0.002",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-turbo-0206"
              },
              "model": "qwen-turbo-0206",
              "model_properties": {
                "context_size": 8000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 2000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.002",
                "output": "0.006",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-turbo-0624"
              },
              "model": "qwen-turbo-0624",
              "model_properties": {
                "context_size": 8000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 2000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.002",
                "output": "0.006",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-turbo-0919"
              },
              "model": "qwen-turbo-0919",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.0003",
                "output": "0.0006",
                "unit": "0.001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-turbo-chat"
              },
              "model": "qwen-turbo-chat",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1500,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 1500,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.002",
                "output": "0.006",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-turbo-latest"
              },
              "model": "qwen-turbo-latest",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.0006",
                "output": "0.0003",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-turbo"
              },
              "model": "qwen-turbo",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 2000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.0006",
                "output": "0.0003",
                "unit": "0.001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "vision",
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-vl-max-0201"
              },
              "model": "qwen-vl-max-0201",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.02",
                "output": "0.02",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "vision",
                "agent-thought",
                "video"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-vl-max-0809"
              },
              "model": "qwen-vl-max-0809",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 2000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.02",
                "output": "0.02",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "vision",
                "agent-thought",
                "video"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-vl-max-2025-01-25"
              },
              "model": "qwen-vl-max-2025-01-25",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.003",
                "output": "0.009",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "vision",
                "agent-thought",
                "video"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-vl-max-latest"
              },
              "model": "qwen-vl-max-latest",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.003",
                "output": "0.009",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "vision",
                "agent-thought",
                "video"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-vl-max"
              },
              "model": "qwen-vl-max",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 2000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.02",
                "output": "0.02",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "vision",
                "agent-thought",
                "video"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-vl-plus-0809"
              },
              "model": "qwen-vl-plus-0809",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 2000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.008",
                "output": "0.008",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "vision",
                "agent-thought",
                "video"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-vl-plus-2025-01-02"
              },
              "model": "qwen-vl-plus-2025-01-02",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.0015",
                "output": "0.0045",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "vision",
                "agent-thought",
                "video"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-vl-plus-2025-01-25"
              },
              "model": "qwen-vl-plus-2025-01-25",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.003",
                "output": "0.009",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "vision",
                "agent-thought",
                "video"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-vl-plus-latest"
              },
              "model": "qwen-vl-plus-latest",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.003",
                "output": "0.009",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "vision",
                "agent-thought",
                "video"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-vl-plus"
              },
              "model": "qwen-vl-plus",
              "model_properties": {
                "context_size": 8000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 2000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.008",
                "output": "0.008",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen2-math-1.5b-instruct"
              },
              "model": "qwen2-math-1.5b-instruct",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 2000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.004",
                "output": "0.012",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen2-math-72b-instruct"
              },
              "model": "qwen2-math-72b-instruct",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 2000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.004",
                "output": "0.012",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen2-math-7b-instruct"
              },
              "model": "qwen2-math-7b-instruct",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 2000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.004",
                "output": "0.012",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen2.5-0.5b-instruct"
              },
              "model": "qwen2.5-0.5b-instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen2.5-1.5b-instruct"
              },
              "model": "qwen2.5-1.5b-instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen2.5-14b-instruct-1m"
              },
              "model": "qwen2.5-14b-instruct-1m",
              "model_properties": {
                "context_size": 1000000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.001",
                "output": "0.003",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen2.5-14b-instruct"
              },
              "model": "qwen2.5-14b-instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.001",
                "output": "0.003",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen2.5-32b-instruct"
              },
              "model": "qwen2.5-32b-instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.002",
                "output": "0.006",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen2.5-3b-instruct"
              },
              "model": "qwen2.5-3b-instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.0003",
                "output": "0.0009",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen2.5-72b-instruct"
              },
              "model": "qwen2.5-72b-instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.004",
                "output": "0.012",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen2.5-7b-instruct-1m"
              },
              "model": "qwen2.5-7b-instruct-1m",
              "model_properties": {
                "context_size": 1000000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.0005",
                "output": "0.001",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen2.5-7b-instruct"
              },
              "model": "qwen2.5-7b-instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.0005",
                "output": "0.001",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen2.5-coder-7b-instruct"
              },
              "model": "qwen2.5-coder-7b-instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.001",
                "output": "0.002",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "vision",
                "agent-thought",
                "video"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen2.5-vl-3b-instruct"
              },
              "model": "qwen2.5-vl-3b-instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.0012",
                "output": "0.0036",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "vision",
                "agent-thought",
                "video"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen2.5-vl-72b-instruct"
              },
              "model": "qwen2.5-vl-72b-instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.016",
                "output": "0.048",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "vision",
                "agent-thought",
                "video"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen2.5-vl-7b-instruct"
              },
              "model": "qwen2.5-vl-7b-instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.002",
                "output": "0.005",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwq-32b",
                "zh_Hans": "通义千问QWQ-32B"
              },
              "model": "qwq-32b",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 2000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.012",
                "output": "0.036",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "vision",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qvq-max-latest",
                "zh_Hans": "通义千问QWQ-Max-Latest"
              },
              "model": "qvq-max-latest",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 2000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.0016",
                "output": "0.004",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "vision",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qvq-max",
                "zh_Hans": "通义千问QWQ-Max"
              },
              "model": "qvq-max",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 2000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.0016",
                "output": "0.004",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwq-plus-0305",
                "zh_Hans": "通义千问QWQ-Plus-0305"
              },
              "model": "qwq-plus-0305",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 2000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.0016",
                "output": "0.004",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwq-plus",
                "zh_Hans": "通义千问QWQ-Plus"
              },
              "model": "qwq-plus",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 2000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.0016",
                "output": "0.004",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gte-rerank-v2"
              },
              "model": "gte-rerank-v2",
              "model_properties": {
                "context_size": 4000
              },
              "model_type": "rerank",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gte-rerank"
              },
              "model": "gte-rerank",
              "model_properties": {
                "context_size": 4000
              },
              "model_type": "rerank",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "paraformer-realtime-v1"
              },
              "model": "paraformer-realtime-v1",
              "model_properties": {
                "file_upload_limit": 100,
                "supported_file_extensions": "aac,amr,avi,flac,flv,m4a,mkv,mov,mp3,mp4,mpeg,ogg,opus,wav,webm,wma,wmv"
              },
              "model_type": "speech2text",
              "parameter_rules": [],
              "pricing": {
                "currency": "RMB",
                "input": "0.00024",
                "output": null,
                "unit": "0.00001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "paraformer-realtime-v2"
              },
              "model": "paraformer-realtime-v2",
              "model_properties": {
                "file_upload_limit": 100,
                "supported_file_extensions": "aac,amr,avi,flac,flv,m4a,mkv,mov,mp3,mp4,mpeg,ogg,opus,wav,webm,wma,wmv"
              },
              "model_type": "speech2text",
              "parameter_rules": [],
              "pricing": {
                "currency": "RMB",
                "input": "0.00024",
                "output": null,
                "unit": "0.00001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "text-embedding-v1"
              },
              "model": "text-embedding-v1",
              "model_properties": {
                "context_size": 2048,
                "max_chunks": 25
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "RMB",
                "input": "0.0007",
                "output": null,
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "text-embedding-v2"
              },
              "model": "text-embedding-v2",
              "model_properties": {
                "context_size": 2048,
                "max_chunks": 25
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "RMB",
                "input": "0.0007",
                "output": null,
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "text-embedding-v3"
              },
              "model": "text-embedding-v3",
              "model_properties": {
                "context_size": 8192,
                "max_chunks": 25
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "RMB",
                "input": "0.0007",
                "output": null,
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "tts-1"
              },
              "model": "tts-1",
              "model_properties": {
                "audio_type": "mp3",
                "default_voice": "sambert-zhiru-v1",
                "max_workers": 5,
                "voices": [
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "sambert-zhinan-v1",
                    "name": "知楠（广告男声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "sambert-zhiqi-v1",
                    "name": "知琪（温柔女声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "sambert-zhichu-v1",
                    "name": "知厨（新闻播报）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "sambert-zhide-v1",
                    "name": "知德（新闻男声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "sambert-zhijia-v1",
                    "name": "知佳（标准女声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "sambert-zhiru-v1",
                    "name": "知茹（新闻女声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "sambert-zhiqian-v1",
                    "name": "知倩（配音解说、新闻播报）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "sambert-zhixiang-v1",
                    "name": "知祥（配音解说）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "sambert-zhiwei-v1",
                    "name": "知薇（萝莉女声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "sambert-zhihao-v1",
                    "name": "知浩（咨询男声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "sambert-zhijing-v1",
                    "name": "知婧（严厉女声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "sambert-zhiming-v1",
                    "name": "知茗（诙谐男声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "sambert-zhimo-v1",
                    "name": "知墨（情感男声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "sambert-zhina-v1",
                    "name": "知娜（浙普女声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "sambert-zhishu-v1",
                    "name": "知树（资讯男声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "sambert-zhistella-v1",
                    "name": "知莎（知性女声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "sambert-zhiting-v1",
                    "name": "知婷（电台女声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "sambert-zhixiao-v1",
                    "name": "知笑（资讯女声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "sambert-zhiya-v1",
                    "name": "知雅（严厉女声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "sambert-zhiye-v1",
                    "name": "知晔（青年男声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "sambert-zhiying-v1",
                    "name": "知颖（软萌童声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "sambert-zhiyuan-v1",
                    "name": "知媛（知心姐姐）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "sambert-zhigui-v1",
                    "name": "知柜（直播女声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "sambert-zhishuo-v1",
                    "name": "知硕（自然男声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "sambert-zhimiao-emo-v1",
                    "name": "知妙（多种情感女声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "sambert-zhimao-v1",
                    "name": "知猫（直播女声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "sambert-zhilun-v1",
                    "name": "知伦（悬疑解说）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "sambert-zhifei-v1",
                    "name": "知飞（激昂解说）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "sambert-zhida-v1",
                    "name": "知达（标准男声）"
                  },
                  {
                    "language": [
                      "es-ES"
                    ],
                    "mode": "sambert-camila-v1",
                    "name": "Camila（西班牙语女声）"
                  },
                  {
                    "language": [
                      "it-IT"
                    ],
                    "mode": "sambert-perla-v1",
                    "name": "Perla（意大利语女声）"
                  },
                  {
                    "language": [
                      "id-ID"
                    ],
                    "mode": "sambert-indah-v1",
                    "name": "Indah（印尼语女声）"
                  },
                  {
                    "language": [
                      "fr-FR"
                    ],
                    "mode": "sambert-clara-v1",
                    "name": "Clara（法语女声）"
                  },
                  {
                    "language": [
                      "de-DE"
                    ],
                    "mode": "sambert-hanna-v1",
                    "name": "Hanna（德语女声）"
                  },
                  {
                    "language": [
                      "en-US"
                    ],
                    "mode": "sambert-beth-v1",
                    "name": "Beth（咨询女声）"
                  },
                  {
                    "language": [
                      "en-US"
                    ],
                    "mode": "sambert-betty-v1",
                    "name": "Betty（客服女声）"
                  },
                  {
                    "language": [
                      "en-US"
                    ],
                    "mode": "sambert-cally-v1",
                    "name": "Cally（自然女声）"
                  },
                  {
                    "language": [
                      "en-US"
                    ],
                    "mode": "sambert-cindy-v1",
                    "name": "Cindy（对话女声）"
                  },
                  {
                    "language": [
                      "en-US"
                    ],
                    "mode": "sambert-eva-v1",
                    "name": "Eva（陪伴女声）"
                  },
                  {
                    "language": [
                      "en-US"
                    ],
                    "mode": "sambert-donna-v1",
                    "name": "Donna（教育女声）"
                  },
                  {
                    "language": [
                      "en-US"
                    ],
                    "mode": "sambert-brian-v1",
                    "name": "Brian（客服男声）"
                  },
                  {
                    "language": [
                      "th-TH"
                    ],
                    "mode": "sambert-waan-v1",
                    "name": "Waan（泰语女声）"
                  }
                ],
                "word_limit": 7000
              },
              "model_type": "tts",
              "parameter_rules": [],
              "pricing": {
                "currency": "RMB",
                "input": "1",
                "output": "0",
                "unit": "0.0001"
              }
            }
          ],
          "position": {
            "llm": [
              "qwq-32b",
              "qwq-plus",
              "qwq-plus-0305",
              "qwq-max",
              "qwq-max-latest",
              "deepseek-r1",
              "deepseek-r1-distill-qwen-14b",
              "deepseek-r1-distill-qwen-32b",
              "deepseek-v3",
              "qwen2.5-vl-72b-instruct",
              "qwen2.5-vl-7b-instruct",
              "qwen2.5-vl-3b-instruct",
              "qwen-vl-max-latest",
              "qwen-vl-max-2025-01-25",
              "qwen-vl-max-0809",
              "qwen-vl-max-0201",
              "qwen-vl-max",
              "qwen-max-latest",
              "qwen-max-0125",
              "qwen-max-1201",
              "qwen-max-0919",
              "qwen-max-0428",
              "qwen-max-0403",
              "qwen-max-0107",
              "qwen-max",
              "qwen-max-longcontext",
              "qwen-plus-latest",
              "qwen-plus-0125",
              "qwen-plus-0112",
              "qwen-plus-1220",
              "qwen-plus-1127",
              "qwen-plus-1125",
              "qwen-plus-0919",
              "qwen-plus-0806",
              "qwen-plus-0723",
              "qwen-plus-0624",
              "qwen-plus-0206",
              "qwen-plus-chat",
              "qwen-plus",
              "qwen-vl-plus-latest",
              "qwen-vl-plus-2025-01-25",
              "qwen-vl-plus-2025-01-02",
              "qwen-vl-plus-0809",
              "qwen-vl-plus",
              "qwen-turbo-latest",
              "qwen-turbo-0919",
              "qwen-turbo-0624",
              "qwen-turbo-0206",
              "qwen-turbo-chat",
              "qwen-turbo",
              "qwen2.5-72b-instruct",
              "qwen2.5-32b-instruct",
              "qwen2.5-14b-instruct-1m",
              "qwen2.5-14b-instruct",
              "qwen2.5-7b-instruct-1m",
              "qwen2.5-7b-instruct",
              "qwen2.5-3b-instruct",
              "qwen2.5-1.5b-instruct",
              "qwen2.5-0.5b-instruct",
              "qwen2.5-coder-7b-instruct",
              "qwen2-math-72b-instruct",
              "qwen2-math-7b-instruct",
              "qwen2-math-1.5b-instruct",
              "qwen-long",
              "qwen-math-plus-latest",
              "qwen-math-plus-0919",
              "qwen-math-plus-0816",
              "qwen-math-plus",
              "qwen-math-turbo-latest",
              "qwen-math-turbo-0919",
              "qwen-math-turbo",
              "qwen-coder-turbo-latest",
              "qwen-coder-turbo-0919",
              "qwen-coder-turbo",
              "farui-plus"
            ],
            "rerank": [
              "gte-rerank",
              "gte-rerank-v2"
            ]
          },
          "provider": "tongyi",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "dashscope_api_key"
              }
            ]
          },
          "supported_model_types": [
            "llm",
            "text-embedding",
            "rerank",
            "speech2text",
            "tts"
          ]
        },
        "name": "tongyi",
        "org": "langgenius",
        "plugin_id": "langgenius/tongyi",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/tongyi.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": false,
              "llm": false,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-16T04:17:53Z",
        "version_updated_at": "2025-04-16T04:17:53Z"
      },
      {
        "agent_strategy": {},
        "badges": [
          "partner"
        ],
        "brief": {
          "en_US": "SiliconFlow provides access to various models (LLMs, text embedding, reranking, STT, TTS), configurable via model name, API key, and other parameters.",
          "zh_Hans": "硅基流动提供对各种模型（LLM、文本嵌入、重排序、STT、TTS）的访问，可通过模型名称、API密钥和其他参数进行配置。"
        },
        "category": "model",
        "created_at": "2024-12-04T04:54:03Z",
        "endpoint": {},
        "icon": "langgenius/packages/siliconflow/_assets/siliconflow_square.svg",
        "index_id": "langgenius___siliconflow",
        "install_count": 63947,
        "introduction": "## Overview\n\nSiliconCloud (MaaS) simplifies AI model deployment with robust performance. This plugin provides access to various models (LLMs, text embedding, reranking, STT, TTS), configurable via model name, API key, and other parameters.\n\n## Configure\n\nInstall the SiliconFlow plugin, then configure it by entering your API Key. Get your API Key from [SiliconFlow](https://cloud.siliconflow.cn/account/ak) and save.\n\n![](./_assets/siliconflow-01.png)\n\n## About SiliconFlow  \n\nSiliconFlow is committed to building a scalable, standardized, and high-performance AI Infra platform. It offers SiliconCloud (the model cloud service platform), SiliconLLM (the LLM inference engine), and OneDiff (the high-performance text-to-image/video acceleration library). These solutions help enterprises and individual users deploy AI models efficiently and cost-effectively.\n\n[Website](https://siliconflow.cn/) | [SiliconCloud Quick Start](https://docs.siliconflow.cn/quickstart) ",
        "label": {
          "en_US": "SiliconFlow",
          "zh_Hans": "硅基流动"
        },
        "latest_package_identifier": "langgenius/siliconflow:0.0.9@d0bed72582f8945dba4bf0fb23e03a449e7319f7cb0056ce02bfc76ca3f08215",
        "latest_version": "0.0.9",
        "model": {
          "background": "#ffecff",
          "configurate_methods": [
            "predefined-model",
            "customizable-model"
          ],
          "description": {
            "en_US": "SiliconFlow provides access to various models (LLMs, text embedding, reranking, STT, TTS), configurable via model name, API key, and other parameters.",
            "zh_Hans": "硅基流动提供对各种模型（LLM、文本嵌入、重排序、STT、TTS）的访问，可通过模型名称、API密钥和其他参数进行配置。"
          },
          "help": {
            "title": {
              "en_US": "Get your API Key from SiliconFlow",
              "zh_Hans": "从 SiliconFlow 获取 API Key"
            },
            "url": {
              "en_US": "https://cloud.siliconflow.cn/account/ak"
            }
          },
          "icon_large": {
            "en_US": "siliconflow.svg"
          },
          "icon_small": {
            "en_US": "siliconflow_square.svg"
          },
          "label": {
            "en_US": "SiliconFlow",
            "zh_Hans": "硅基流动"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              },
              {
                "default": "4096",
                "label": {
                  "en_US": "Model context size",
                  "zh_Hans": "模型上下文长度"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Model context size",
                  "zh_Hans": "在此输入您的模型上下文长度"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "context_size"
              },
              {
                "default": "4096",
                "label": {
                  "en_US": "Upper bound for max tokens",
                  "zh_Hans": "最大 token 上限"
                },
                "max_length": 0,
                "options": [],
                "placeholder": null,
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "text-input",
                "variable": "max_tokens"
              },
              {
                "default": "no_call",
                "label": {
                  "en_US": "Function calling"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Not Support",
                      "zh_Hans": "不支持"
                    },
                    "show_on": [],
                    "value": "no_call"
                  },
                  {
                    "label": {
                      "en_US": "Support",
                      "zh_Hans": "支持"
                    },
                    "show_on": [],
                    "value": "function_call"
                  }
                ],
                "placeholder": null,
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "select",
                "variable": "function_calling_type"
              }
            ],
            "model": {
              "label": {
                "en_US": "Model Name",
                "zh_Hans": "模型名称"
              },
              "placeholder": {
                "en_US": "Enter your model name",
                "zh_Hans": "输入模型名称"
              }
            }
          },
          "models": [
            {
              "deprecated": false,
              "features": [
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "OpenGVLab/InternVL2-26B"
              },
              "model": "OpenGVLab/InternVL2-26B",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 2000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "21",
                "output": "21",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Pro/OpenGVLab/InternVL2-8B"
              },
              "model": "Pro/OpenGVLab/InternVL2-8B",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 2000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "21",
                "output": "21",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "deepseek-ai/DeepSeek-Coder-V2-Instruct"
              },
              "model": "deepseek-ai/DeepSeek-Coder-V2-Instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "1.33",
                "output": "1.33",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
                "zh_Hans": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B"
              },
              "model": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "4.13",
                "output": "4.13",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "deepseek-ai/DeepSeek-R1-Distill-Llama-8B",
                "zh_Hans": "deepseek-ai/DeepSeek-R1-Distill-Llama-8B"
              },
              "model": "deepseek-ai/DeepSeek-R1-Distill-Llama-8B",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
                "zh_Hans": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"
              },
              "model": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B",
                "zh_Hans": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
              },
              "model": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.7",
                "output": "0.7",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
                "zh_Hans": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B"
              },
              "model": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "1.26",
                "output": "1.26",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
                "zh_Hans": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B"
              },
              "model": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Pro/deepseek-ai/DeepSeek-R1",
                "zh_Hans": "Pro/deepseek-ai/DeepSeek-R1"
              },
              "model": "Pro/deepseek-ai/DeepSeek-R1",
              "model_properties": {
                "context_size": 64000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 16384,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 16384,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "4",
                "output": "16",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "deepseek-ai/DeepSeek-R1",
                "zh_Hans": "deepseek-ai/DeepSeek-R1"
              },
              "model": "deepseek-ai/DeepSeek-R1",
              "model_properties": {
                "context_size": 64000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 16384,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 16384,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "4",
                "output": "16",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "deepseek-ai/DeepSeek-V2-Chat"
              },
              "model": "deepseek-ai/DeepSeek-V2-Chat",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "1.33",
                "output": "1.33",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "deepseek-ai/DeepSeek-V2.5"
              },
              "model": "deepseek-ai/DeepSeek-V2.5",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "1.33",
                "output": "1.33",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Pro/deepseek-ai/DeepSeek-V3"
              },
              "model": "Pro/deepseek-ai/DeepSeek-V3",
              "model_properties": {
                "context_size": 64000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "2",
                "output": "8",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "deepseek-ai/DeepSeek-V3"
              },
              "model": "deepseek-ai/DeepSeek-V3",
              "model_properties": {
                "context_size": 64000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "2",
                "output": "8",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "google/gemma-2-27b-it"
              },
              "model": "google/gemma-2-27b-it",
              "model_properties": {
                "context_size": 8196,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "1.26",
                "output": "1.26",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "google/gemma-2-9b-it"
              },
              "model": "google/gemma-2-9b-it",
              "model_properties": {
                "context_size": 8196,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "THUDM/glm-4-9b-chat"
              },
              "model": "THUDM/glm-4-9b-chat",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Tencent/Hunyuan-A52B-Instruct"
              },
              "model": "Tencent/Hunyuan-A52B-Instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 2000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "21",
                "output": "21",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "internlm/internlm2_5-20b-chat"
              },
              "model": "internlm/internlm2_5-20b-chat",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "1",
                "output": "1",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "internlm/internlm2_5-7b-chat"
              },
              "model": "internlm/internlm2_5-7b-chat",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "OpenGVLab/InternVL2-Llama3-76B"
              },
              "model": "OpenGVLab/InternVL2-Llama3-76B",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 2000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "21",
                "output": "21",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "deepseek-ai/Janus-Pro-7B",
                "zh_Hans": "deepseek-ai/Janus-Pro-7B"
              },
              "model": "deepseek-ai/Janus-Pro-7B",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "meta-llama/Llama-3.3-70B-Instruct"
              },
              "model": "meta-llama/Llama-3.3-70B-Instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "4.13",
                "output": "4.13",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "meta-llama/Meta-Llama-3-70B-Instruct"
              },
              "model": "meta-llama/Meta-Llama-3-70B-Instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "4.13",
                "output": "4.13",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "meta-llama/Meta-Llama-3-8B-Instruct"
              },
              "model": "meta-llama/Meta-Llama-3-8B-Instruct",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "meta-llama/Meta-Llama-3.1-405B-Instruct"
              },
              "model": "meta-llama/Meta-Llama-3.1-405B-Instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "21",
                "output": "21",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "meta-llama/Meta-Llama-3.1-70B-Instruct"
              },
              "model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "4.13",
                "output": "4.13",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "meta-llama/Meta-Llama-3.1-8B-Instruct"
              },
              "model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "mistralai/Mistral-7B-Instruct-v0.2"
              },
              "model": "mistralai/Mistral-7B-Instruct-v0.2",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "mistralai/Mixtral-8x7B-Instruct-v0.1"
              },
              "model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "1.26",
                "output": "1.26",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought",
                "tool-call",
                "stream-tool-call",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen/QVQ-72B-Preview"
              },
              "model": "Qwen/QVQ-72B-Preview",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 16384,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "9.9",
                "output": "9.9",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen/QwQ-32B-Preview"
              },
              "model": "Qwen/QwQ-32B-Preview",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "1.26",
                "output": "1.26",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen/QwQ-32B"
              },
              "model": "Qwen/QwQ-32B",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 32768,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "1",
                "output": "4",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen/Qwen2-1.5B-Instruct"
              },
              "model": "Qwen/Qwen2-1.5B-Instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen/Qwen2-57B-A14B-Instruct"
              },
              "model": "Qwen/Qwen2-57B-A14B-Instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "1.26",
                "output": "1.26",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen/Qwen2-72B-Instruct"
              },
              "model": "Qwen/Qwen2-72B-Instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "4.13",
                "output": "4.13",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen/Qwen2-7B-Instruct"
              },
              "model": "Qwen/Qwen2-7B-Instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen/Qwen2-VL-72B-Instruct"
              },
              "model": "Qwen/Qwen2-VL-72B-Instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 2000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "4.13",
                "output": "4.13",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Pro/Qwen/Qwen2-VL-7B-Instruct"
              },
              "model": "Pro/Qwen/Qwen2-VL-7B-Instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 2000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.35",
                "output": "0.35",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen/Qwen2.5-14B-Instruct"
              },
              "model": "Qwen/Qwen2.5-14B-Instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.7",
                "output": "0.7",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen/Qwen2.5-32B-Instruct"
              },
              "model": "Qwen/Qwen2.5-32B-Instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "1.26",
                "output": "1.26",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen/Qwen2.5-72B-Instruct-128K"
              },
              "model": "Qwen/Qwen2.5-72B-Instruct-128K",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "4.13",
                "output": "4.13",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Vendor-A/Qwen/Qwen2.5-72B-Instruct"
              },
              "model": "Vendor-A/Qwen/Qwen2.5-72B-Instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "1",
                "output": "1",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen/Qwen2.5-72B-Instruct"
              },
              "model": "Qwen/Qwen2.5-72B-Instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "4.13",
                "output": "4.13",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen/Qwen2.5-7B-Instruct"
              },
              "model": "Qwen/Qwen2.5-7B-Instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen/Qwen2.5-Coder-32B-Instruct"
              },
              "model": "Qwen/Qwen2.5-Coder-32B-Instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "1.26",
                "output": "1.26",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen/Qwen2.5-Coder-7B-Instruct"
              },
              "model": "Qwen/Qwen2.5-Coder-7B-Instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen/Qwen2.5-Math-72B-Instruct"
              },
              "model": "Qwen/Qwen2.5-Math-72B-Instruct",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 2000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "4.13",
                "output": "4.13",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen/Qwen2.5-VL-32B-Instruct"
              },
              "model": "Qwen/Qwen2.5-VL-32B-Instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 2000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "1.89",
                "output": "1.89",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen/Qwen2.5-VL-72B-Instruct"
              },
              "model": "Qwen/Qwen2.5-VL-72B-Instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 2000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "4.13",
                "output": "4.13",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Pro/Qwen/Qwen2.5-VL-7B-Instruct"
              },
              "model": "Pro/Qwen/Qwen2.5-VL-7B-Instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 2000,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1234,
                  "help": {
                    "en_US": "The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.",
                    "zh_Hans": "生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。"
                  },
                  "label": {
                    "en_US": "Random seed",
                    "zh_Hans": "随机种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty",
                    "zh_Hans": "重复惩罚"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.35",
                "output": "0.35",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "01-ai/Yi-1.5-34B-Chat-16K"
              },
              "model": "01-ai/Yi-1.5-34B-Chat",
              "model_properties": {
                "context_size": 16384,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "1.26",
                "output": "1.26",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "01-ai/Yi-1.5-6B-Chat"
              },
              "model": "01-ai/Yi-1.5-6B-Chat",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "01-ai/Yi-1.5-9B-Chat-16K"
              },
              "model": "01-ai/Yi-1.5-9B-Chat-16K",
              "model_properties": {
                "context_size": 16384,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "netease-youdao/bce-reranker-base_v1"
              },
              "model": "netease-youdao/bce-reranker-base_v1",
              "model_properties": {
                "context_size": 512
              },
              "model_type": "rerank",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "BAAI/bge-reranker-v2-m3"
              },
              "model": "BAAI/bge-reranker-v2-m3",
              "model_properties": {
                "context_size": 8192
              },
              "model_type": "rerank",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "FunAudioLLM/SenseVoiceSmall"
              },
              "model": "FunAudioLLM/SenseVoiceSmall",
              "model_properties": {
                "file_upload_limit": 1,
                "supported_file_extensions": "mp3,wav"
              },
              "model_type": "speech2text",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": true,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "iic/SenseVoiceSmall"
              },
              "model": "iic/SenseVoiceSmall",
              "model_properties": {
                "file_upload_limit": 1,
                "supported_file_extensions": "mp3,wav"
              },
              "model_type": "speech2text",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "netease-youdao/bce-embedding-base_v1"
              },
              "model": "netease-youdao/bce-embedding-base_v1",
              "model_properties": {
                "context_size": 512,
                "max_chunks": 1
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "BAAI/bge-large-en-v1.5"
              },
              "model": "BAAI/bge-large-en-v1.5",
              "model_properties": {
                "context_size": 512,
                "max_chunks": 1
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "BAAI/bge-large-zh-v1.5"
              },
              "model": "BAAI/bge-large-zh-v1.5",
              "model_properties": {
                "context_size": 512,
                "max_chunks": 1
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "BAAI/bge-m3"
              },
              "model": "BAAI/bge-m3",
              "model_properties": {
                "context_size": 8192,
                "max_chunks": 1
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "FunAudioLLM/CosyVoice2-0.5B"
              },
              "model": "FunAudioLLM/CosyVoice2-0.5B",
              "model_properties": {
                "audio_type": "mp3",
                "default_voice": "FunAudioLLM/CosyVoice2-0.5B:alex",
                "max_workers": 5,
                "voices": [
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "FunAudioLLM/CosyVoice2-0.5B:alex",
                    "name": "Alex（男声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "FunAudioLLM/CosyVoice2-0.5B:benjamin",
                    "name": "Benjamin（男声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "FunAudioLLM/CosyVoice2-0.5B:charles",
                    "name": "Charles（男声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "FunAudioLLM/CosyVoice2-0.5B:david",
                    "name": "David（男声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "FunAudioLLM/CosyVoice2-0.5B:anna",
                    "name": "Anna（女声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "FunAudioLLM/CosyVoice2-0.5B:bella",
                    "name": "Bella（女声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "FunAudioLLM/CosyVoice2-0.5B:claire",
                    "name": "Claire（女声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "FunAudioLLM/CosyVoice2-0.5B:diana",
                    "name": "Diana（女声）"
                  }
                ]
              },
              "model_type": "tts",
              "parameter_rules": [],
              "pricing": {
                "currency": "RMB",
                "input": "50",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "fishaudio/fish-speech-1.4"
              },
              "model": "fishaudio/fish-speech-1.4",
              "model_properties": {
                "audio_type": "mp3",
                "default_voice": "fishaudio/fish-speech-1.4:alex",
                "max_workers": 5,
                "voices": [
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "fishaudio/fish-speech-1.4:alex",
                    "name": "Alex（男声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "fishaudio/fish-speech-1.4:benjamin",
                    "name": "Benjamin（男声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "fishaudio/fish-speech-1.4:charles",
                    "name": "Charles（男声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "fishaudio/fish-speech-1.4:david",
                    "name": "David（男声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "fishaudio/fish-speech-1.4:anna",
                    "name": "Anna（女声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "fishaudio/fish-speech-1.4:bella",
                    "name": "Bella（女声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "fishaudio/fish-speech-1.4:claire",
                    "name": "Claire（女声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "fishaudio/fish-speech-1.4:diana",
                    "name": "Diana（女声）"
                  }
                ]
              },
              "model_type": "tts",
              "parameter_rules": [],
              "pricing": {
                "currency": "RMB",
                "input": "105",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "fishaudio/fish-speech-1.5"
              },
              "model": "fishaudio/fish-speech-1.5",
              "model_properties": {
                "audio_type": "mp3",
                "default_voice": "fishaudio/fish-speech-1.5:alex",
                "max_workers": 5,
                "voices": [
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "fishaudio/fish-speech-1.5:alex",
                    "name": "Alex（男声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "fishaudio/fish-speech-1.5:benjamin",
                    "name": "Benjamin（男声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "fishaudio/fish-speech-1.5:charles",
                    "name": "Charles（男声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "fishaudio/fish-speech-1.5:david",
                    "name": "David（男声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "fishaudio/fish-speech-1.5:anna",
                    "name": "Anna（女声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "fishaudio/fish-speech-1.5:bella",
                    "name": "Bella（女声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "fishaudio/fish-speech-1.5:claire",
                    "name": "Claire（女声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "fishaudio/fish-speech-1.5:diana",
                    "name": "Diana（女声）"
                  }
                ]
              },
              "model_type": "tts",
              "parameter_rules": [],
              "pricing": {
                "currency": "RMB",
                "input": "105",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "RVC-Boss/GPT-SoVITS"
              },
              "model": "RVC-Boss/GPT-SoVITS",
              "model_properties": {
                "audio_type": "mp3",
                "default_voice": "RVC-Boss/GPT-SoVITS:alex",
                "max_workers": 5,
                "voices": [
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "RVC-Boss/GPT-SoVITS:alex",
                    "name": "Alex（男声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "RVC-Boss/GPT-SoVITS:benjamin",
                    "name": "Benjamin（男声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "RVC-Boss/GPT-SoVITS:charles",
                    "name": "Charles（男声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "RVC-Boss/GPT-SoVITS:david",
                    "name": "David（男声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "RVC-Boss/GPT-SoVITS:anna",
                    "name": "Anna（女声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "RVC-Boss/GPT-SoVITS:bella",
                    "name": "Bella（女声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "RVC-Boss/GPT-SoVITS:claire",
                    "name": "Claire（女声）"
                  },
                  {
                    "language": [
                      "zh-Hans",
                      "en-US"
                    ],
                    "mode": "RVC-Boss/GPT-SoVITS:diana",
                    "name": "Diana（女声）"
                  }
                ]
              },
              "model_type": "tts",
              "parameter_rules": [],
              "pricing": {
                "currency": "RMB",
                "input": "50",
                "output": "0",
                "unit": "0.000001"
              }
            }
          ],
          "position": {
            "llm": [
              "Pro/deepseek-ai/DeepSeek-R1",
              "Pro/deepseek-ai/DeepSeek-V3",
              "deepseek-ai/DeepSeek-R1",
              "deepseek-ai/DeepSeek-V3",
              "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
              "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B",
              "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
              "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
              "deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
              "deepseek-ai/DeepSeek-R1-Distill-Llama-8B",
              "Qwen/QwQ-32B",
              "Qwen/Qwen2.5-72B-Instruct",
              "Qwen/Qwen2.5-72B-Instruct-128K",
              "Qwen/Qwen2.5-32B-Instruct",
              "Qwen/Qwen2.5-14B-Instruct",
              "Qwen/Qwen2.5-7B-Instruct",
              "Qwen/Qwen2.5-Coder-32B-Instruct",
              "Qwen/Qwen2.5-Coder-7B-Instruct",
              "Qwen/Qwen2.5-VL-72B-Instruct",
              "Qwen/Qwen2.5-VL-32B-Instruct",
              "Pro/Qwen/Qwen2.5-VL-7B-Instruct",
              "OpenGVLab/InternVL2-26B",
              "Pro/OpenGVLab/InternVL2-8B",
              "THUDM/glm-4-9b-chat",
              "internlm/internlm2_5-20b-chat",
              "internlm/internlm2_5-7b-chat",
              "meta-llama/Llama-3.3-70B-Instruct",
              "meta-llama/Meta-Llama-3.1-70B-Instruct",
              "meta-llama/Meta-Llama-3.1-8B-Instruct"
            ]
          },
          "provider": "siliconflow",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              }
            ]
          },
          "supported_model_types": [
            "llm",
            "text-embedding",
            "rerank",
            "speech2text",
            "tts"
          ]
        },
        "name": "siliconflow",
        "org": "langgenius",
        "plugin_id": "langgenius/siliconflow",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/siliconflow.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": false,
              "llm": false,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "image"
          }
        ],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-09T13:53:58Z",
        "version_updated_at": "2025-04-09T13:53:58Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Model providers compatible with OpenAI's API standard, such as LM Studio.",
          "zh_Hans": "兼容 OpenAI API 的模型供应商，例如 LM Studio 。"
        },
        "category": "model",
        "created_at": "2024-11-29T09:17:34Z",
        "endpoint": {},
        "icon": "langgenius/packages/openai_api_compatible/_assets/icon.svg",
        "index_id": "langgenius___openai_api_compatible",
        "install_count": 58849,
        "introduction": "## Overview\n\nThis plugin provides access to models that are OpenAI-compatible, including LLMs, reranking, text embedding, speech-to-text (STT), and text-to-speech(TTS) models. Developers can easily add models by providing configuration parameters such as the model name and API key.\n\n## Configure\n\nConfigure the OpenAI-API-compatible model by providing its core details (Type, Name, API Key, URL) and adjusting further options like completion, context, and token limits, as well as streaming and vision settings. Save when done.\n\n![](./_assets/openai_api_compatible-01.png)\n",
        "label": {
          "en_US": "OpenAI-API-compatible"
        },
        "latest_package_identifier": "langgenius/openai_api_compatible:0.0.13@3c545e99d84bd870a5bc673d66e206e8704f9b71c9e4eb83459bc75b8352d738",
        "latest_version": "0.0.13",
        "model": {
          "background": null,
          "configurate_methods": [
            "customizable-model"
          ],
          "description": {
            "en_US": "Model providers compatible with OpenAI's API standard, such as LM Studio.",
            "zh_Hans": "兼容 OpenAI API 的模型供应商，例如 LM Studio 。"
          },
          "help": null,
          "icon_large": null,
          "icon_small": {
            "en_US": "icon.svg"
          },
          "label": {
            "en_US": "OpenAI-API-compatible"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "Model display name",
                  "zh_Hans": "模型显示名称"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "The display name of the model in the interface.",
                  "zh_Hans": "模型在界面的显示名称"
                },
                "required": false,
                "show_on": [],
                "type": "text-input",
                "variable": "display_name"
              },
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": false,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              },
              {
                "default": null,
                "label": {
                  "en_US": "API endpoint URL",
                  "zh_Hans": "API endpoint URL"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Base URL, e.g. https://api.openai.com/v1",
                  "zh_Hans": "Base URL, e.g. https://api.openai.com/v1"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "endpoint_url"
              },
              {
                "default": null,
                "label": {
                  "en_US": "model name for API endpoint",
                  "zh_Hans": "API endpoint中的模型名称"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "endpoint model name, e.g. chatgpt4.0",
                  "zh_Hans": "endpoint model name, e.g. chatgpt4.0"
                },
                "required": false,
                "show_on": [],
                "type": "text-input",
                "variable": "endpoint_model_name"
              },
              {
                "default": "chat",
                "label": {
                  "en_US": "Completion mode"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Completion",
                      "zh_Hans": "补全"
                    },
                    "show_on": [],
                    "value": "completion"
                  },
                  {
                    "label": {
                      "en_US": "Chat",
                      "zh_Hans": "对话"
                    },
                    "show_on": [],
                    "value": "chat"
                  }
                ],
                "placeholder": {
                  "en_US": "Select completion mode",
                  "zh_Hans": "选择对话类型"
                },
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "select",
                "variable": "mode"
              },
              {
                "default": "4096",
                "label": {
                  "en_US": "Model context size",
                  "zh_Hans": "模型上下文长度"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Model context size",
                  "zh_Hans": "在此输入您的模型上下文长度"
                },
                "required": true,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "text-input",
                "variable": "context_size"
              },
              {
                "default": "4096",
                "label": {
                  "en_US": "Model context size",
                  "zh_Hans": "模型上下文长度"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Model context size",
                  "zh_Hans": "在此输入您的模型上下文长度"
                },
                "required": true,
                "show_on": [
                  {
                    "value": "text-embedding",
                    "variable": "__model_type"
                  }
                ],
                "type": "text-input",
                "variable": "context_size"
              },
              {
                "default": "4096",
                "label": {
                  "en_US": "Model context size",
                  "zh_Hans": "模型上下文长度"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Model context size",
                  "zh_Hans": "在此输入您的模型上下文长度"
                },
                "required": true,
                "show_on": [
                  {
                    "value": "rerank",
                    "variable": "__model_type"
                  }
                ],
                "type": "text-input",
                "variable": "context_size"
              },
              {
                "default": "4096",
                "label": {
                  "en_US": "Upper bound for max tokens",
                  "zh_Hans": "最大 token 上限"
                },
                "max_length": 0,
                "options": [],
                "placeholder": null,
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "text-input",
                "variable": "max_tokens_to_sample"
              },
              {
                "default": "not_supported",
                "label": {
                  "en_US": "Agent Thought"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Support",
                      "zh_Hans": "支持"
                    },
                    "show_on": [],
                    "value": "supported"
                  },
                  {
                    "label": {
                      "en_US": "Not Support",
                      "zh_Hans": "不支持"
                    },
                    "show_on": [],
                    "value": "not_supported"
                  }
                ],
                "placeholder": null,
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "select",
                "variable": "agent_though_support"
              },
              {
                "default": "no_call",
                "label": {
                  "en_US": "Function calling"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Function Call",
                      "zh_Hans": "Function Call"
                    },
                    "show_on": [],
                    "value": "function_call"
                  },
                  {
                    "label": {
                      "en_US": "Tool Call",
                      "zh_Hans": "Tool Call"
                    },
                    "show_on": [],
                    "value": "tool_call"
                  },
                  {
                    "label": {
                      "en_US": "Not Support",
                      "zh_Hans": "不支持"
                    },
                    "show_on": [],
                    "value": "no_call"
                  }
                ],
                "placeholder": null,
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "select",
                "variable": "function_calling_type"
              },
              {
                "default": "not_supported",
                "label": {
                  "en_US": "Stream function calling"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Support",
                      "zh_Hans": "支持"
                    },
                    "show_on": [],
                    "value": "supported"
                  },
                  {
                    "label": {
                      "en_US": "Not Support",
                      "zh_Hans": "不支持"
                    },
                    "show_on": [],
                    "value": "not_supported"
                  }
                ],
                "placeholder": null,
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "select",
                "variable": "stream_function_calling"
              },
              {
                "default": "no_support",
                "label": {
                  "en_US": "Vision Support",
                  "zh_Hans": "Vision 支持"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Support",
                      "zh_Hans": "支持"
                    },
                    "show_on": [],
                    "value": "support"
                  },
                  {
                    "label": {
                      "en_US": "Not Support",
                      "zh_Hans": "不支持"
                    },
                    "show_on": [],
                    "value": "no_support"
                  }
                ],
                "placeholder": null,
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "select",
                "variable": "vision_support"
              },
              {
                "default": "\\n\\n",
                "label": {
                  "en_US": "Delimiter for streaming results",
                  "zh_Hans": "流模式返回结果的分隔符"
                },
                "max_length": 0,
                "options": [],
                "placeholder": null,
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "text-input",
                "variable": "stream_mode_delimiter"
              },
              {
                "default": "alloy",
                "label": {
                  "en_US": "Available Voices (comma-separated)",
                  "zh_Hans": "可用声音（用英文逗号分隔）"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "alloy,echo,fable,onyx,nova,shimmer",
                  "zh_Hans": "alloy,echo,fable,onyx,nova,shimmer"
                },
                "required": false,
                "show_on": [
                  {
                    "value": "tts",
                    "variable": "__model_type"
                  }
                ],
                "type": "text-input",
                "variable": "voices"
              }
            ],
            "model": {
              "label": {
                "en_US": "Model Name",
                "zh_Hans": "模型名称"
              },
              "placeholder": {
                "en_US": "Enter full model name",
                "zh_Hans": "输入模型全称"
              }
            }
          },
          "models": [],
          "provider": "openai_api_compatible",
          "provider_credential_schema": null,
          "supported_model_types": [
            "llm",
            "rerank",
            "text-embedding",
            "speech2text",
            "tts"
          ]
        },
        "name": "openai_api_compatible",
        "org": "langgenius",
        "plugin_id": "langgenius/openai_api_compatible",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/openai_api_compatible.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-14T11:19:58Z",
        "version_updated_at": "2025-04-14T11:19:58Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Google's Gemini model.",
          "zh_Hans": "谷歌提供的 Gemini 模型."
        },
        "category": "model",
        "created_at": "2024-12-04T04:45:59Z",
        "endpoint": {},
        "icon": "langgenius/packages/gemini/_assets/icon_s_en.svg",
        "index_id": "langgenius___gemini",
        "install_count": 33983,
        "introduction": "## Overview\nGemini is a family of multimodal AI models from Google, designed to process and generate various types of data, including text, images, audio, and video. This plugin provides access to Gemini models via a single API key, enabling developers to build versatile multimodal AI applications.\n\n## Configure\nAfter installing the Gemini plugin, configure it with your API key, which you can get from Google. Enter the key in the Model Provider settings and save.\n\n![](./_assets/gemini-01.png)\n\nIf you use `url` mode for `MULTIMODAL_SEND_FORMAT` in gemeni and other vision models meantime, you can set `Files URL` to gain better performance.",
        "label": {
          "en_US": "Gemini"
        },
        "latest_package_identifier": "langgenius/gemini:0.1.5@012c9e0467a11910db974e0436348e93a376fdc96381946a3db2c56708377381",
        "latest_version": "0.1.5",
        "model": {
          "background": "#FCFDFF",
          "configurate_methods": [
            "predefined-model"
          ],
          "description": {
            "en_US": "Google's Gemini model.",
            "zh_Hans": "谷歌提供的 Gemini 模型."
          },
          "help": {
            "title": {
              "en_US": "Get your API Key from Google",
              "zh_Hans": "从 Google 获取 API Key"
            },
            "url": {
              "en_US": "https://ai.google.dev/"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.svg"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "Gemini"
          },
          "model_credential_schema": null,
          "models": [
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document",
                "video",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 1.5 Flash 001"
              },
              "model": "gemini-1.5-flash-001",
              "model_properties": {
                "context_size": 1048576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document",
                "video",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 1.5 Flash 002"
              },
              "model": "gemini-1.5-flash-002",
              "model_properties": {
                "context_size": 1048576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document",
                "video",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 1.5 Flash 8B 0827"
              },
              "model": "gemini-1.5-flash-8b-exp-0827",
              "model_properties": {
                "context_size": 1048576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document",
                "video",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 1.5 Flash 8B 0924"
              },
              "model": "gemini-1.5-flash-8b-exp-0924",
              "model_properties": {
                "context_size": 1048576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document",
                "video",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 1.5 Flash 0827"
              },
              "model": "gemini-1.5-flash-exp-0827",
              "model_properties": {
                "context_size": 1048576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document",
                "video",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 1.5 Flash Latest"
              },
              "model": "gemini-1.5-flash-latest",
              "model_properties": {
                "context_size": 1048576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document",
                "video",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 1.5 Flash"
              },
              "model": "gemini-1.5-flash",
              "model_properties": {
                "context_size": 1048576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document",
                "video",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 1.5 Pro 001"
              },
              "model": "gemini-1.5-pro-001",
              "model_properties": {
                "context_size": 2097152,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document",
                "video",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 1.5 Pro 002"
              },
              "model": "gemini-1.5-pro-002",
              "model_properties": {
                "context_size": 2097152,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document",
                "video",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 1.5 Pro 0801"
              },
              "model": "gemini-1.5-pro-exp-0801",
              "model_properties": {
                "context_size": 2097152,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document",
                "video",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 1.5 Pro 0827"
              },
              "model": "gemini-1.5-pro-exp-0827",
              "model_properties": {
                "context_size": 2097152,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document",
                "video",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 1.5 Pro Latest"
              },
              "model": "gemini-1.5-pro-latest",
              "model_properties": {
                "context_size": 2097152,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document",
                "video",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 1.5 Pro"
              },
              "model": "gemini-1.5-pro",
              "model_properties": {
                "context_size": 2097152,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document",
                "video",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 2.0 Flash 001"
              },
              "model": "gemini-2.0-flash-001",
              "model_properties": {
                "context_size": 1048576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document",
                "video",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 2.0 Flash Exp"
              },
              "model": "gemini-2.0-flash-exp",
              "model_properties": {
                "context_size": 1048576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document",
                "video",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 2.0 Flash-Lite 001"
              },
              "model": "gemini-2.0-flash-lite-001",
              "model_properties": {
                "context_size": 1048576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document",
                "video",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 2.0 Flash-Lite Preview 02-05"
              },
              "model": "gemini-2.0-flash-lite-preview-02-05",
              "model_properties": {
                "context_size": 1048576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document",
                "video",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 2.0 Flash-Lite Preview"
              },
              "model": "gemini-2.0-flash-lite-preview",
              "model_properties": {
                "context_size": 1048576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document",
                "video",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 2.0 Flash-Lite"
              },
              "model": "gemini-2.0-flash-lite",
              "model_properties": {
                "context_size": 1048576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "document",
                "video",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 2.0 Flash Thinking Experimental 01-21"
              },
              "model": "gemini-2.0-flash-thinking-exp-01-21",
              "model_properties": {
                "context_size": 1048576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 65536,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 65536,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "document",
                "video",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 2.0 Flash Thinking Experimental"
              },
              "model": "gemini-2.0-flash-thinking-exp-1219",
              "model_properties": {
                "context_size": 1048576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 65536,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 65536,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document",
                "video",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 2.0 Flash"
              },
              "model": "gemini-2.0-flash",
              "model_properties": {
                "context_size": 1048576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "ensures responses are based on Google Search.",
                    "ja_JP": "Google検索に基づいた応答をします。"
                  },
                  "label": {
                    "en_US": "Grounding",
                    "ja_JP": "Grounding"
                  },
                  "max": null,
                  "min": null,
                  "name": "grounding",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document",
                "video",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 2.0 Pro Experimental 02-05"
              },
              "model": "gemini-2.0-pro-exp-02-05",
              "model_properties": {
                "context_size": 2097152,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document",
                "video",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 2.0 Pro Experimental"
              },
              "model": "gemini-2.0-pro-exp",
              "model_properties": {
                "context_size": 2097152,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 2.5 Flash Preview 04-17"
              },
              "model": "gemini-2.5-flash-preview-04-17",
              "model_properties": {
                "context_size": 1048576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 65536,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.15",
                "output": "0.6",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 2.5 Pro Experimental 03-25"
              },
              "model": "gemini-2.5-pro-exp-03-25",
              "model_properties": {
                "context_size": 1048576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 64000,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 2.5 Pro Preview 03-25"
              },
              "model": "gemini-2.5-pro-preview-03-25",
              "model_properties": {
                "context_size": 1048576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 65536,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "Grounding with Google Search",
                    "ja_JP": "Google検索に基づいた応答をします。",
                    "zh_Hans": "Google 事实核查"
                  },
                  "label": {
                    "en_US": "Grounding",
                    "ja_JP": "事実チェック",
                    "zh_Hans": "事实核查"
                  },
                  "max": null,
                  "min": null,
                  "name": "grounding",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "1.25",
                "output": "10",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document",
                "video",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini exp 1114"
              },
              "model": "gemini-exp-1114",
              "model_properties": {
                "context_size": 32767,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document",
                "video",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini exp 1121"
              },
              "model": "gemini-exp-1121",
              "model_properties": {
                "context_size": 32767,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document",
                "video",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini Experimental 1206"
              },
              "model": "gemini-exp-1206",
              "model_properties": {
                "context_size": 2097152,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini Pro Vision"
              },
              "model": "gemini-pro-vision",
              "model_properties": {
                "context_size": 12288,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens_to_sample"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens_to_sample",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini Pro"
              },
              "model": "gemini-pro",
              "model_properties": {
                "context_size": 30720,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens_to_sample"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens_to_sample",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document",
                "video",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "LearnLM 1.5 Pro Experimental"
              },
              "model": "learnlm-1.5-pro-experimental",
              "model_properties": {
                "context_size": 32767,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            }
          ],
          "position": {
            "llm": [
              "gemini-2.0-flash-exp",
              "gemini-2.0-flash",
              "gemini-2.0-flash-001",
              "gemini-2.0-flash-lite-001",
              "gemini-2.0-flash-lite",
              "gemini-2.0-flash-lite-preview-02-05",
              "gemini-2.0-flash-lite-preview",
              "gemini-2.0-pro-exp",
              "gemini-2.0-pro-exp-02-05",
              "gemini-exp-1206",
              "gemini-2.0-flash-thinking-exp-01-21",
              "gemini-2.0-flash-thinking-exp-1219",
              "gemini-1.5-pro",
              "gemini-1.5-pro-latest",
              "gemini-1.5-pro-001",
              "gemini-1.5-pro-002",
              "gemini-1.5-pro-exp-0801",
              "gemini-1.5-pro-exp-0827",
              "gemini-1.5-flash",
              "gemini-1.5-flash-latest",
              "gemini-1.5-flash-001",
              "gemini-1.5-flash-002",
              "gemini-1.5-flash-exp-0827",
              "gemini-1.5-flash-8b-exp-0827",
              "gemini-1.5-flash-8b-exp-0924",
              "gemini-exp-1206",
              "gemini-exp-1121",
              "gemini-exp-1114"
            ]
          },
          "provider": "google",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "google_api_key"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Files URL"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter the Local FILES URL prefix to get better upload performance",
                  "zh_Hans": "在此输入本地文件地址的URL前缀"
                },
                "required": false,
                "show_on": [],
                "type": "text-input",
                "variable": "file_url"
              }
            ]
          },
          "supported_model_types": [
            "llm"
          ]
        },
        "name": "gemini",
        "org": "langgenius",
        "plugin_id": "langgenius/gemini",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/google.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-22T13:13:10Z",
        "version_updated_at": "2025-04-22T13:13:10Z"
      },
      {
        "agent_strategy": {
          "identity": {
            "author": "langgenius",
            "description": {
              "en_US": "Agent",
              "pt_BR": "Agent",
              "zh_Hans": "Agent"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Agent",
              "pt_BR": "Agent",
              "zh_Hans": "Agent"
            },
            "name": "agent",
            "tags": []
          },
          "strategies": [
            {
              "description": {
                "en_US": "Function Calling is a basic strategy for agent, model will use the tools provided to perform the task.",
                "pt_BR": "Function Calling is a basic strategy for agent, model will use the tools provided to perform the task.",
                "zh_Hans": "Function Calling 是一个基本的 Agent 策略，模型将使用提供的工具来执行任务。"
              },
              "identity": {
                "author": "Dify",
                "label": {
                  "en_US": "FunctionCalling",
                  "pt_BR": "FunctionCalling",
                  "zh_Hans": "FunctionCalling"
                },
                "name": "function_calling"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "label": {
                    "en_US": "Model",
                    "pt_BR": "Model",
                    "zh_Hans": "模型"
                  },
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": "tool-call&llm",
                  "template": null,
                  "type": "model-selector"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "label": {
                    "en_US": "Tool list",
                    "pt_BR": "Tool list",
                    "zh_Hans": "工具列表"
                  },
                  "max": null,
                  "min": null,
                  "name": "tools",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "array[tools]"
                },
                {
                  "auto_generate": {
                    "type": "prompt_instruction"
                  },
                  "default": null,
                  "label": {
                    "en_US": "Instruction",
                    "pt_BR": "Instruction",
                    "zh_Hans": "指令"
                  },
                  "max": null,
                  "min": null,
                  "name": "instruction",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": {
                    "enabled": true
                  },
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "label": {
                    "en_US": "Query",
                    "pt_BR": "Query",
                    "zh_Hans": "查询"
                  },
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 3,
                  "label": {
                    "en_US": "Maximum Iterations",
                    "pt_BR": "Maximum Iterations",
                    "zh_Hans": "最大迭代次数"
                  },
                  "max": 30,
                  "min": 1,
                  "name": "maximum_iterations",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "en_US": "ReAct is a basic strategy for agent, model will use the tools provided to perform the task.",
                "pt_BR": "ReAct is a basic strategy for agent, model will use the tools provided to perform the task.",
                "zh_Hans": "ReAct 是一个基本的 Agent 策略，模型将使用提供的工具来执行任务。"
              },
              "identity": {
                "author": "Dify",
                "label": {
                  "en_US": "ReAct",
                  "pt_BR": "ReAct",
                  "zh_Hans": "ReAct"
                },
                "name": "ReAct"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "label": {
                    "en_US": "Model",
                    "pt_BR": "Model",
                    "zh_Hans": "模型"
                  },
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": "tool-call&llm",
                  "template": null,
                  "type": "model-selector"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "label": {
                    "en_US": "Tool list",
                    "pt_BR": "Tool list",
                    "zh_Hans": "工具列表"
                  },
                  "max": null,
                  "min": null,
                  "name": "tools",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "array[tools]"
                },
                {
                  "auto_generate": {
                    "type": "prompt_instruction"
                  },
                  "default": null,
                  "label": {
                    "en_US": "Instruction",
                    "pt_BR": "Instruction",
                    "zh_Hans": "指令"
                  },
                  "max": null,
                  "min": null,
                  "name": "instruction",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": {
                    "enabled": true
                  },
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "label": {
                    "en_US": "Query",
                    "pt_BR": "Query",
                    "zh_Hans": "查询"
                  },
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 3,
                  "label": {
                    "en_US": "Maximum Iterations",
                    "pt_BR": "Maximum Iterations",
                    "zh_Hans": "最大迭代次数"
                  },
                  "max": 30,
                  "min": 1,
                  "name": "maximum_iterations",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            }
          ]
        },
        "badges": [],
        "brief": {
          "en_US": "Dify official Agent strategies collection",
          "zh_Hans": "Dify 官方 Agent 策略集合"
        },
        "category": "agent-strategy",
        "created_at": "2025-01-08T07:40:04Z",
        "endpoint": {},
        "icon": "langgenius/packages/agent/_assets/icon.svg",
        "index_id": "langgenius___agent",
        "install_count": 27449,
        "introduction": "# Overview\nThe Agent node in Dify Chatflow/Workflow lets LLMs autonomously use tools. This plugin features two official Dify Agent reasoning strategies, enabling LLMs to dynamically select and run tools during runtime for multi-step problem-solving.\n\n## Strategies\n\n### 1. Function Calling\nFunction Calling maps user commands to specific functions or tools. The LLM identifies the user's intent, decides which function to call, and extracts the required parameters. It is a straightforward mechanism for invoking external capabilities.\n\n![](./_assets/function_calling.png)\n\n#### Pros:\n- **Precise:** Directly calls the right tool for defined tasks, avoiding complex reasoning.\n- **Easy External Integration:** Integrates external APIs and tools as callable functions.\n- **Structured Output:** Provides structured function call information for easy processing.\n\n### 2. ReAct (Reason + Act)\nReAct alternates between the LLM reasoning about the situation and taking actions. The LLM analyzes the current state and goal, selects and uses a tool, and then uses the tool's output for the next thought and action. This cycle repeats until the problem is resolved.\n\n![](./_assets/react.png)\n\n#### Pros:\n- **Leverages External Information:** Effectively uses external tools to gather information for tasks the model cannot handle alone.\n- **Explainable Reasoning:** Interwoven reasoning and action steps allow some tracking of the Agent's process.\n- **Wide Applicability:** Suitable for tasks requiring external knowledge or specific actions, such as Q&A, information retrieval, and task execution.",
        "label": {
          "en_US": "Dify Agent Strategies",
          "zh_Hans": "Dify Agent 策略"
        },
        "latest_package_identifier": "langgenius/agent:0.0.14@26958a0e80a10655ce73812bdb7c35a66ce7b16f5ac346d298bda17ff85efd1e",
        "latest_version": "0.0.14",
        "model": {},
        "name": "agent",
        "org": "langgenius",
        "plugin_id": "langgenius/agent",
        "plugins": {
          "agent_strategies": [
            "provider/agent.yaml"
          ],
          "endpoints": null,
          "models": null,
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "agent"
          }
        ],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-14T12:00:43Z",
        "version_updated_at": "2025-04-14T12:00:43Z"
      },
      {
        "agent_strategy": {},
        "badges": [
          "partner"
        ],
        "brief": {
          "en_US": "A powerful AI-native search engine and web content extraction tool that provides highly relevant search results and raw content extraction from web pages.",
          "zh_Hans": "一个强大的原生AI搜索引擎和网页内容提取工具，提供高度相关的搜索结果和网页原始内容提取。"
        },
        "category": "tool",
        "created_at": "2024-11-29T06:15:58Z",
        "endpoint": {},
        "icon": "langgenius/packages/tavily/_assets/icon.png",
        "index_id": "langgenius___tavily",
        "install_count": 27406,
        "introduction": "# Tavily\n\n## Overview\n\nTavily is a search API designed for AI agents and applications, offering precise and context-aware search results. It handles complex search queries and extracts relevant information from the web, providing structured output.\n\n## Configuration\n\n### 1. Apply for an API Key\n\nApply for an API Key at [Tavily](https://app.tavily.com/home).\n\n### 2. Get Tavily tools from Plugin Marketplace\n\nThe Tavily tools could be found at the Plugin Marketplace, please install it.\n\n### 3. Fill in the configuration in Dify\n\nOn the Dify navigation page, go to Tools > Tavily > Authentication to fill in the API Key.\n\n![](./_assets/tavily_1.PNG)\n\n### 4. Using the tool\n\nYou can use the Tavily tool in the following application types:\n\n#### Chatflow / Workflow applications\n\n![](./_assets/tavily_2.PNG)\n\nBoth Chatflow and Workflow applications support adding Tavily series tool nodes, providing two tools: extract and search.\n\n#### Agent applications\n\n![](./_assets/tavily_3.PNG)\n\nSelect the Tavily tool you need to add in the Agent application, then enter commands to call the tool.",
        "label": {
          "en_US": "Tavily",
          "zh_Hans": "Tavily"
        },
        "latest_package_identifier": "langgenius/tavily:0.0.5@caf7214ca1a237845e991615fd12e04c8db8b703d59773538fe243f3de4044e9",
        "latest_version": "0.0.5",
        "model": {},
        "name": "tavily",
        "org": "langgenius",
        "plugin_id": "langgenius/tavily",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/tavily.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "search"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Get your Tavily API key from Tavily",
                "zh_Hans": "从 Tavily 获取您的 Tavily API key"
              },
              "label": {
                "en_US": "Tavily API key",
                "zh_Hans": "Tavily API key"
              },
              "name": "tavily_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Tavily API key",
                "zh_Hans": "请输入你的 Tavily API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://app.tavily.com/home"
            }
          ],
          "identity": {
            "author": "Yash Parmar, Kalo Chin",
            "description": {
              "en_US": "A powerful AI-native search engine and web content extraction tool that provides highly relevant search results and raw content extraction from web pages.",
              "zh_Hans": "一个强大的原生AI搜索引擎和网页内容提取工具，提供高度相关的搜索结果和网页原始内容提取。"
            },
            "icon": "icon.png",
            "label": {
              "en_US": "Tavily",
              "zh_Hans": "Tavily"
            },
            "name": "tavily",
            "tags": [
              "search"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Extract web page content from one or more specified URLs using Tavily Extract.",
                  "zh_Hans": "使用 Tavily Extract 从一个或多个指定的 URL 提取网页内容。"
                },
                "llm": "Extract raw content from web pages with basic or advanced extraction modes."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Kalo Chin",
                "label": {
                  "en_US": "Tavily Extract",
                  "zh_Hans": "Tavily Extract"
                },
                "name": "tavily_extract"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "One or more URLs to extract content from (comma-separated if multiple).",
                    "zh_Hans": "要从中提取内容的一个或多个 URL（如果有多个，请用逗号分隔）。"
                  },
                  "label": {
                    "en_US": "URLs",
                    "zh_Hans": "URLs"
                  },
                  "llm_description": "One or more URLs to extract content from (comma-separated if multiple).",
                  "max": null,
                  "min": null,
                  "name": "urls",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Include a list of images extracted from the URLs in the response.",
                    "zh_Hans": "在响应中包含从 URL 提取的图像列表。"
                  },
                  "label": {
                    "en_US": "Include Images",
                    "zh_Hans": "包含图像"
                  },
                  "llm_description": "Include images from the URLs in the response. Default is false.",
                  "max": null,
                  "min": null,
                  "name": "include_images",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": "basic",
                  "form": "llm",
                  "human_description": {
                    "en_US": "The depth of the extraction process. 'advanced' retrieves more data but may increase latency and costs more credits.",
                    "zh_Hans": "提取过程的深度。\"advanced\"检索更多数据，但可能增加延迟和消耗更多积分。"
                  },
                  "label": {
                    "en_US": "Extract Depth",
                    "zh_Hans": "提取深度"
                  },
                  "llm_description": "Extraction depth - 'basic' (default, faster) or 'advanced' (more data, higher cost).",
                  "max": null,
                  "min": null,
                  "name": "extract_depth",
                  "options": [
                    {
                      "label": {
                        "en_US": "Basic",
                        "zh_Hans": "基本"
                      },
                      "value": "basic"
                    },
                    {
                      "label": {
                        "en_US": "Advanced",
                        "zh_Hans": "高级"
                      },
                      "value": "advanced"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A search engine tool built specifically for AI agents (LLMs), delivering real-time, accurate, and factual results at speed.",
                  "zh_Hans": "专为人工智能代理 (LLM) 构建的搜索引擎工具，可快速提供实时、准确和真实的结果。"
                },
                "llm": "A tool for search engine built specifically for AI agents (LLMs), delivering real-time, accurate, and factual results at speed."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Yash Parmar",
                "label": {
                  "en_US": "Tavily Search",
                  "zh_Hans": "Tavily Search"
                },
                "name": "tavily_search"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The search query you want to execute with Tavily.",
                    "zh_Hans": "您想用 Tavily 执行的搜索查询。"
                  },
                  "label": {
                    "en_US": "Query",
                    "zh_Hans": "查询"
                  },
                  "llm_description": "The search query.",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "basic",
                  "form": "llm",
                  "human_description": {
                    "en_US": "The depth of the search.",
                    "zh_Hans": "搜索的深度。"
                  },
                  "label": {
                    "en_US": "Search Depth",
                    "zh_Hans": "搜索深度"
                  },
                  "llm_description": "The depth of the search. 'basic' for standard search, 'advanced' for more comprehensive results.",
                  "max": null,
                  "min": null,
                  "name": "search_depth",
                  "options": [
                    {
                      "label": {
                        "en_US": "Basic",
                        "zh_Hans": "基本"
                      },
                      "value": "basic"
                    },
                    {
                      "label": {
                        "en_US": "Advanced",
                        "zh_Hans": "高级"
                      },
                      "value": "advanced"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "general",
                  "form": "llm",
                  "human_description": {
                    "en_US": "The category of the search.",
                    "zh_Hans": "搜索的类别。"
                  },
                  "label": {
                    "en_US": "Topic",
                    "zh_Hans": "主题"
                  },
                  "llm_description": "The category of the search. Options include 'general', 'news', or 'finance'.",
                  "max": null,
                  "min": null,
                  "name": "topic",
                  "options": [
                    {
                      "label": {
                        "en_US": "General",
                        "zh_Hans": "一般"
                      },
                      "value": "general"
                    },
                    {
                      "label": {
                        "en_US": "News",
                        "zh_Hans": "新闻"
                      },
                      "value": "news"
                    },
                    {
                      "label": {
                        "en_US": "Finance",
                        "zh_Hans": "金融"
                      },
                      "value": "finance"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 3,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The number of days back from the current date to include in the search results (only applicable when \"topic\" is \"news\").",
                    "zh_Hans": "从当前日期起向前追溯的天数，以包含在搜索结果中（仅当\"topic\"为\"news\"时适用）。"
                  },
                  "label": {
                    "en_US": "Days",
                    "zh_Hans": "天数"
                  },
                  "llm_description": "The number of days back from the current date to include in the search results. Only applicable when \"topic\" is \"news\".",
                  "max": null,
                  "min": 1,
                  "name": "days",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "not_specified",
                  "form": "llm",
                  "human_description": {
                    "en_US": "The time range back from the current date to filter results.",
                    "zh_Hans": "从当前日期起向后筛选结果的时间范围。"
                  },
                  "label": {
                    "en_US": "Time Range",
                    "zh_Hans": "时间范围"
                  },
                  "llm_description": "The time range back from the current date to filter results. Options include 'not_specified', 'day', 'week', 'month', or 'year'.",
                  "max": null,
                  "min": null,
                  "name": "time_range",
                  "options": [
                    {
                      "label": {
                        "en_US": "Not Specified",
                        "zh_Hans": "不指定"
                      },
                      "value": "not_specified"
                    },
                    {
                      "label": {
                        "en_US": "Day",
                        "zh_Hans": "天"
                      },
                      "value": "day"
                    },
                    {
                      "label": {
                        "en_US": "Week",
                        "zh_Hans": "周"
                      },
                      "value": "week"
                    },
                    {
                      "label": {
                        "en_US": "Month",
                        "zh_Hans": "月"
                      },
                      "value": "month"
                    },
                    {
                      "label": {
                        "en_US": "Year",
                        "zh_Hans": "年"
                      },
                      "value": "year"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 5,
                  "form": "form",
                  "human_description": {
                    "en_US": "The maximum number of search results to return.",
                    "zh_Hans": "要返回的最大搜索结果数。"
                  },
                  "label": {
                    "en_US": "Max Results",
                    "zh_Hans": "最大结果数"
                  },
                  "llm_description": "The maximum number of search results to return. Range is 1-20.",
                  "max": 20,
                  "min": 1,
                  "name": "max_results",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Include a list of query-related images in the response.",
                    "zh_Hans": "在响应中包含与查询相关的图片列表。"
                  },
                  "label": {
                    "en_US": "Include Images",
                    "zh_Hans": "包含图片"
                  },
                  "llm_description": "When set to true, includes a list of query-related images in the response.",
                  "max": null,
                  "min": null,
                  "name": "include_images",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "When include_images is True, adds descriptive text for each image.",
                    "zh_Hans": "当 include_images 为 True 时，为每个图像添加描述文本。"
                  },
                  "label": {
                    "en_US": "Include Image Descriptions",
                    "zh_Hans": "包含图片描述"
                  },
                  "llm_description": "When include_images is True and this is set to true, adds descriptive text for each image.",
                  "max": null,
                  "min": null,
                  "name": "include_image_descriptions",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Include a short answer to the original query in the response.",
                    "zh_Hans": "在响应中包含对原始查询的简短回答。"
                  },
                  "label": {
                    "en_US": "Include Answer",
                    "zh_Hans": "包含答案"
                  },
                  "llm_description": "When set to true, includes a short answer to the original query in the response.",
                  "max": null,
                  "min": null,
                  "name": "include_answer",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Include the cleaned and parsed HTML content of each search result.",
                    "zh_Hans": "包含每个搜索结果的已清理和解析的HTML内容。"
                  },
                  "label": {
                    "en_US": "Include Raw Content",
                    "zh_Hans": "包含原始内容"
                  },
                  "llm_description": "When set to true, includes the cleaned and parsed HTML content of each search result.",
                  "max": null,
                  "min": null,
                  "name": "include_raw_content",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "A comma-separated list of domains to specifically include in the search results.",
                    "zh_Hans": "要在搜索结果中特别包含的域的逗号分隔列表。"
                  },
                  "label": {
                    "en_US": "Include Domains",
                    "zh_Hans": "包含域"
                  },
                  "llm_description": "A comma-separated list of domains to specifically include in the search results.",
                  "max": null,
                  "min": null,
                  "name": "include_domains",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "A comma-separated list of domains to specifically exclude from the search results.",
                    "zh_Hans": "要从搜索结果中特别排除的域的逗号分隔列表。"
                  },
                  "label": {
                    "en_US": "Exclude Domains",
                    "zh_Hans": "排除域"
                  },
                  "llm_description": "A comma-separated list of domains to specifically exclude from the search results.",
                  "max": null,
                  "min": null,
                  "name": "exclude_domains",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-17T15:20:31Z",
        "version_updated_at": "2025-03-17T06:38:06Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Volcengine Ark models.",
          "zh_Hans": "火山方舟提供的模型，例如 Doubao-pro-4k、Doubao-pro-32k 和 Doubao-pro-128k。"
        },
        "category": "model",
        "created_at": "2025-01-02T09:00:17Z",
        "endpoint": {},
        "icon": "langgenius/packages/volcengine_maas/_assets/icon_s_en.svg",
        "index_id": "langgenius___volcengine_maas",
        "install_count": 26121,
        "introduction": "",
        "label": {
          "en_US": "Volcengine",
          "zh_Hans": "火山方舟"
        },
        "latest_package_identifier": "langgenius/volcengine_maas:0.0.11@030f2960ad0be9a346d619fa5458b109a4edfab3fdc3061dc2614741d9b44e0c",
        "latest_version": "0.0.11",
        "model": {
          "background": "#F9FAFB",
          "configurate_methods": [
            "customizable-model"
          ],
          "description": {
            "en_US": "Volcengine Ark models.",
            "zh_Hans": "火山方舟提供的模型，例如 Doubao-pro-4k、Doubao-pro-32k 和 Doubao-pro-128k。"
          },
          "help": {
            "title": {
              "en_US": "Get your Access Key and Secret Access Key from Volcengine Console",
              "zh_Hans": "从火山引擎控制台获取您的 Access Key 和 Secret Access Key"
            },
            "url": {
              "en_US": "https://console.volcengine.com/iam/keymanage/"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.svg",
            "zh_Hans": "icon_l_zh.svg"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "Volcengine"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": "aksk",
                "label": {
                  "en_US": "Authentication Method",
                  "zh_Hans": "鉴权方式"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "API Key"
                    },
                    "show_on": [],
                    "value": "api_key"
                  },
                  {
                    "label": {
                      "en_US": "Access Key / Secret Access Key"
                    },
                    "show_on": [],
                    "value": "aksk"
                  }
                ],
                "placeholder": {
                  "en_US": "Enter your Authentication Method",
                  "zh_Hans": "选择鉴权方式"
                },
                "required": true,
                "show_on": [],
                "type": "select",
                "variable": "auth_method"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Access Key",
                  "zh_Hans": "Access Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Access Key",
                  "zh_Hans": "输入您的 Access Key"
                },
                "required": true,
                "show_on": [
                  {
                    "value": "aksk",
                    "variable": "auth_method"
                  }
                ],
                "type": "secret-input",
                "variable": "volc_access_key_id"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Secret Access Key",
                  "zh_Hans": "Secret Access Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Secret Access Key",
                  "zh_Hans": "输入您的 Secret Access Key"
                },
                "required": true,
                "show_on": [
                  {
                    "value": "aksk",
                    "variable": "auth_method"
                  }
                ],
                "type": "secret-input",
                "variable": "volc_secret_access_key"
              },
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "输入您的 API Key"
                },
                "required": true,
                "show_on": [
                  {
                    "value": "api_key",
                    "variable": "auth_method"
                  }
                ],
                "type": "secret-input",
                "variable": "volc_api_key"
              },
              {
                "default": "cn-beijing",
                "label": {
                  "en_US": "Volcengine Region",
                  "zh_Hans": "火山引擎地域"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter Volcengine Region",
                  "zh_Hans": "输入火山引擎地域"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "volc_region"
              },
              {
                "default": "https://ark.cn-beijing.volces.com/api/v3",
                "label": {
                  "en_US": "API Endpoint Host",
                  "zh_Hans": "API Endpoint Host"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Endpoint Host",
                  "zh_Hans": "输入 API Endpoint Host"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "api_endpoint_host"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Endpoint ID",
                  "zh_Hans": "Endpoint ID"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Endpoint ID",
                  "zh_Hans": "输入您的 Endpoint ID"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "endpoint_id"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Base Model",
                  "zh_Hans": "基础模型"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Doubao-1.5-thinking-pro"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "Doubao-1.5-thinking-pro"
                  },
                  {
                    "label": {
                      "en_US": "DeepSeek-R1-Distill-Qwen-32B"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "DeepSeek-R1-Distill-Qwen-32B"
                  },
                  {
                    "label": {
                      "en_US": "DeepSeek-R1-Distill-Qwen-7B"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "DeepSeek-R1-Distill-Qwen-7B"
                  },
                  {
                    "label": {
                      "en_US": "DeepSeek-R1"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "DeepSeek-R1"
                  },
                  {
                    "label": {
                      "en_US": "DeepSeek-V3"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "DeepSeek-V3"
                  },
                  {
                    "label": {
                      "en_US": "Doubao-1.5-vision-pro-32k"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "Doubao-1.5-vision-pro-32k"
                  },
                  {
                    "label": {
                      "en_US": "Doubao-1.5-pro-32k"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "Doubao-1.5-pro-32k"
                  },
                  {
                    "label": {
                      "en_US": "Doubao-1.5-lite-32k"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "Doubao-1.5-lite-32k"
                  },
                  {
                    "label": {
                      "en_US": "Doubao-1.5-pro-256k"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "Doubao-1.5-pro-256k"
                  },
                  {
                    "label": {
                      "en_US": "Doubao-vision-pro-32k"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "Doubao-vision-pro-32k"
                  },
                  {
                    "label": {
                      "en_US": "Doubao-vision-lite-32k"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "Doubao-vision-lite-32k"
                  },
                  {
                    "label": {
                      "en_US": "Doubao-pro-4k"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "Doubao-pro-4k"
                  },
                  {
                    "label": {
                      "en_US": "Doubao-lite-4k"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "Doubao-lite-4k"
                  },
                  {
                    "label": {
                      "en_US": "Doubao-pro-32k"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "Doubao-pro-32k"
                  },
                  {
                    "label": {
                      "en_US": "Doubao-lite-32k"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "Doubao-lite-32k"
                  },
                  {
                    "label": {
                      "en_US": "Doubao-pro-128k"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "Doubao-pro-128k"
                  },
                  {
                    "label": {
                      "en_US": "Doubao-lite-128k"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "Doubao-lite-128k"
                  },
                  {
                    "label": {
                      "en_US": "Doubao-pro-256k"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "Doubao-pro-256k"
                  },
                  {
                    "label": {
                      "en_US": "Llama3-8B"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "Llama3-8B"
                  },
                  {
                    "label": {
                      "en_US": "Llama3-70B"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "Llama3-70B"
                  },
                  {
                    "label": {
                      "en_US": "Moonshot-v1-8k"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "Moonshot-v1-8k"
                  },
                  {
                    "label": {
                      "en_US": "Moonshot-v1-32k"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "Moonshot-v1-32k"
                  },
                  {
                    "label": {
                      "en_US": "Moonshot-v1-128k"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "Moonshot-v1-128k"
                  },
                  {
                    "label": {
                      "en_US": "GLM3-130B"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "GLM3-130B"
                  },
                  {
                    "label": {
                      "en_US": "GLM3-130B-Fin"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "GLM3-130B-Fin"
                  },
                  {
                    "label": {
                      "en_US": "Mistral-7B"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "Mistral-7B"
                  },
                  {
                    "label": {
                      "en_US": "Doubao-embedding"
                    },
                    "show_on": [
                      {
                        "value": "text-embedding",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "Doubao-embedding"
                  },
                  {
                    "label": {
                      "en_US": "Doubao-embedding-large"
                    },
                    "show_on": [
                      {
                        "value": "text-embedding",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "Doubao-embedding-large"
                  },
                  {
                    "label": {
                      "en_US": "Custom",
                      "zh_Hans": "自定义"
                    },
                    "show_on": [],
                    "value": "Custom"
                  }
                ],
                "placeholder": null,
                "required": true,
                "show_on": [],
                "type": "select",
                "variable": "base_model_name"
              },
              {
                "default": "chat",
                "label": {
                  "en_US": "Completion Mode",
                  "zh_Hans": "模型类型"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Completion",
                      "zh_Hans": "补全"
                    },
                    "show_on": [],
                    "value": "completion"
                  },
                  {
                    "label": {
                      "en_US": "Chat",
                      "zh_Hans": "对话"
                    },
                    "show_on": [],
                    "value": "chat"
                  }
                ],
                "placeholder": {
                  "en_US": "Select Completion Mode",
                  "zh_Hans": "选择对话类型"
                },
                "required": true,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  },
                  {
                    "value": "Custom",
                    "variable": "base_model_name"
                  }
                ],
                "type": "select",
                "variable": "mode"
              },
              {
                "default": "4096",
                "label": {
                  "en_US": "Model Context Size",
                  "zh_Hans": "模型上下文长度"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Model Context Size",
                  "zh_Hans": "输入您的模型上下文长度"
                },
                "required": true,
                "show_on": [
                  {
                    "value": "Custom",
                    "variable": "base_model_name"
                  }
                ],
                "type": "text-input",
                "variable": "context_size"
              },
              {
                "default": "4096",
                "label": {
                  "en_US": "Upper Bound for Max Tokens",
                  "zh_Hans": "最大 token 上限"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your model Upper Bound for Max Tokens",
                  "zh_Hans": "输入您的模型最大 token 上限"
                },
                "required": true,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  },
                  {
                    "value": "Custom",
                    "variable": "base_model_name"
                  }
                ],
                "type": "text-input",
                "variable": "max_tokens"
              }
            ],
            "model": {
              "label": {
                "en_US": "Model Name",
                "zh_Hans": "模型名称"
              },
              "placeholder": {
                "en_US": "Enter your Model Name",
                "zh_Hans": "输入模型名称"
              }
            }
          },
          "models": [],
          "position": {},
          "provider": "volcengine_maas",
          "provider_credential_schema": null,
          "supported_model_types": [
            "llm",
            "text-embedding"
          ]
        },
        "name": "volcengine_maas",
        "org": "langgenius",
        "plugin_id": "langgenius/volcengine_maas",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/volcengine_maas.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-19T14:02:14Z",
        "version_updated_at": "2025-04-19T14:02:14Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Anthropic's powerful models.",
          "zh_Hans": "Anthropic 的强大模型。"
        },
        "category": "model",
        "created_at": "2024-12-03T10:08:17Z",
        "endpoint": {},
        "icon": "langgenius/packages/anthropic/_assets/icon_s_en.svg",
        "index_id": "langgenius___anthropic",
        "install_count": 25213,
        "introduction": "## Overview\nAnthropic offers a suite of AI models designed for safety and helpfulness, excelling in natural language processing and generation tasks such as coding and creative writing. Using this plugin, developers can easily configure and access LLMs from the Claude family (Sonnet, Haiku, and Opus) by providing the necessary API credentials.\n\n## Configure\nYou'll need your Anthropic API Key to configure this plugin. After obtaining it from Anthropic, enter it along with your API URL in the settings below. Save to activate.\n\n![](./_assets/anthropic-01.png)\n",
        "label": {
          "en_US": "Anthropic"
        },
        "latest_package_identifier": "langgenius/anthropic:0.0.13@3c4d4e14652baa9ce1f10e934da9995b3cde0f2ec94ee6638b73fecf1ed53288",
        "latest_version": "0.0.13",
        "model": {
          "background": "#F0F0EB",
          "configurate_methods": [
            "predefined-model"
          ],
          "description": {
            "en_US": "Anthropic’s powerful models, such as Claude 3.",
            "zh_Hans": "Anthropic 的强大模型，例如 Claude 3。"
          },
          "help": {
            "title": {
              "en_US": "Get your API Key from Anthropic",
              "zh_Hans": "从 Anthropic 获取 API Key"
            },
            "url": {
              "en_US": "https://console.anthropic.com/account/keys"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.png"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "Anthropic"
          },
          "model_credential_schema": null,
          "models": [
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "claude-3-5-haiku-20241022"
              },
              "model": "claude-3-5-haiku-20241022",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "1",
                "output": "5",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "claude-3-5-sonnet-20240620"
              },
              "model": "claude-3-5-sonnet-20240620",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "3",
                "output": "15",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "claude-3-5-sonnet-20241022"
              },
              "model": "claude-3-5-sonnet-20241022",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "3",
                "output": "15",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "claude-3-7-sonnet-20250219"
              },
              "model": "claude-3-7-sonnet-20250219",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": false,
                  "help": {
                    "en_US": "Controls the model's thinking capability. When enabled, temperature, top_p and top_k will be disabled.",
                    "zh_Hans": "控制模型的推理能力。启用时，temperature、top_p和top_k将被禁用。"
                  },
                  "label": {
                    "en_US": "Thinking Mode",
                    "zh_Hans": "推理模式"
                  },
                  "max": null,
                  "min": null,
                  "name": "thinking",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Budget limit for thinking (minimum 1024), must be less than max_tokens. Only available when thinking mode is enabled.",
                    "zh_Hans": "推理的预算限制（最小1024），必须小于max_tokens。仅在推理模式启用时可用。"
                  },
                  "label": {
                    "en_US": "Thinking Budget",
                    "zh_Hans": "推理预算"
                  },
                  "max": 128000,
                  "min": 0,
                  "name": "thinking_budget",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 64000,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 128000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "Enable capability for up to 128K output tokens.",
                    "zh_Hans": "启用长达128K标记的输出能力。"
                  },
                  "label": {
                    "en_US": "Extended Output",
                    "zh_Hans": "扩展输出"
                  },
                  "max": null,
                  "min": null,
                  "name": "extended_output",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "3",
                "output": "15",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "claude-3-haiku-20240307"
              },
              "model": "claude-3-haiku-20240307",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.25",
                "output": "1.25",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "claude-3-opus-20240229"
              },
              "model": "claude-3-opus-20240229",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "15",
                "output": "75",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "claude-3-sonnet-20240229"
              },
              "model": "claude-3-sonnet-20240229",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "3",
                "output": "15",
                "unit": "0.000001"
              }
            }
          ],
          "position": {
            "llm": [
              "claude-3-5-haiku-20241022",
              "claude-3-5-sonnet-20241022",
              "claude-3-5-sonnet-20240620",
              "claude-3-7-sonnet-20250219",
              "claude-3-haiku-20240307",
              "claude-3-opus-20240229",
              "claude-3-sonnet-20240229"
            ]
          },
          "provider": "anthropic",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "anthropic_api_key"
              },
              {
                "default": null,
                "label": {
                  "en_US": "API URL"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API URL",
                  "zh_Hans": "在此输入您的 API URL"
                },
                "required": false,
                "show_on": [],
                "type": "text-input",
                "variable": "anthropic_api_url"
              }
            ]
          },
          "supported_model_types": [
            "llm"
          ]
        },
        "name": "anthropic",
        "org": "langgenius",
        "plugin_id": "langgenius/anthropic",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/anthropic.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": false,
              "llm": false,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-01T05:45:06Z",
        "version_updated_at": "2025-04-01T05:45:06Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Tools for processing JSON content using jsonpath_ng",
          "pt_BR": "Tools for processing JSON content using jsonpath_ng",
          "zh_Hans": "利用 jsonpath_ng 处理 JSON 内容的工具"
        },
        "category": "tool",
        "created_at": "2024-11-29T09:07:32Z",
        "endpoint": {},
        "icon": "langgenius/packages/json_process/_assets/icon.svg",
        "index_id": "langgenius___json_process",
        "install_count": 23697,
        "introduction": "# Overview\nJSON Process is a group of tools able to insert, delete, replace and parse within a JSON data structure.\n\n# Configure\n## JSON Insert\nJSON Insert tool adds a new value to a JSON object.\n\n![](./_assets/json_insert.png)\n\n## JSON Delete\nJSON Delete tool deletes element in a JSON data sturcture.\n![](./_assets/json_delete.png)\n\n## JSON Parse\nJSON Parse tool converts a JSON string into a JavaScript object or a Python dictionary, depending on the language being used.\n![](./_assets/json_parse.png)\n\n## JSON Replace\nJSON Replace tool replaces values within a JSON object.\n![](./_assets/json_replace.png)",
        "label": {
          "en_US": "JSON Process",
          "pt_BR": "JSON Process",
          "zh_Hans": "JSON 处理"
        },
        "latest_package_identifier": "langgenius/json_process:0.0.2@7afb534cc85b28a8e9c7f9410d1cfc31fb7bd3950023355a37059dbe809ac776",
        "latest_version": "0.0.2",
        "model": {},
        "name": "json_process",
        "org": "langgenius",
        "plugin_id": "langgenius/json_process",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/json_process.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "utilities"
          }
        ],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "Mingwei_Zhang",
            "description": {
              "en_US": "Tools for processing JSON content using jsonpath_ng",
              "pt_BR": "Tools for processing JSON content using jsonpath_ng",
              "zh_Hans": "利用 jsonpath_ng 处理 JSON 内容的工具"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "JSON Process",
              "pt_BR": "JSON Process",
              "zh_Hans": "JSON 处理"
            },
            "name": "json_process",
            "tags": [
              "utilities"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool for extracting JSON objects",
                  "pt_BR": "A tool for extracting JSON objects",
                  "zh_Hans": "一个解析JSON对象的工具"
                },
                "llm": "A tool for extracting JSON objects"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Mingwei_Zhang",
                "label": {
                  "en_US": "JSON Parse",
                  "pt_BR": "JSON Parse",
                  "zh_Hans": "JSON 解析"
                },
                "name": "parse"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "JSON data",
                    "pt_BR": "JSON数据",
                    "zh_Hans": "JSON数据"
                  },
                  "label": {
                    "en_US": "JSON data",
                    "pt_BR": "JSON data",
                    "zh_Hans": "JSON数据"
                  },
                  "llm_description": "JSON data to be processed",
                  "max": null,
                  "min": null,
                  "name": "content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "JSON fields to be parsed",
                    "pt_BR": "JSON fields to be parsed",
                    "zh_Hans": "需要解析的 JSON 字段"
                  },
                  "label": {
                    "en_US": "JSON filter",
                    "pt_BR": "JSON filter",
                    "zh_Hans": "JSON解析对象"
                  },
                  "llm_description": "JSON fields to be parsed",
                  "max": null,
                  "min": null,
                  "name": "json_filter",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "Ensure the JSON output is ASCII encoded",
                    "pt_BR": "Ensure the JSON output is ASCII encoded",
                    "zh_Hans": "确保输出的 JSON 是 ASCII 编码"
                  },
                  "label": {
                    "en_US": "Ensure ASCII",
                    "pt_BR": "Ensure ASCII",
                    "zh_Hans": "确保 ASCII"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "ensure_ascii",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for deleting JSON content",
                  "pt_BR": "A tool for deleting JSON content",
                  "zh_Hans": "一个删除 JSON 内容的工具"
                },
                "llm": "A tool for deleting JSON content"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Mingwei_Zhang",
                "label": {
                  "en_US": "JSON Delete",
                  "pt_BR": "JSON Delete",
                  "zh_Hans": "JSON 删除"
                },
                "name": "json_delete"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "JSON content to be processed",
                    "pt_BR": "JSON content to be processed",
                    "zh_Hans": "待处理的 JSON 内容"
                  },
                  "label": {
                    "en_US": "JSON content",
                    "pt_BR": "JSON content",
                    "zh_Hans": "JSON 内容"
                  },
                  "llm_description": "JSON content to be processed",
                  "max": null,
                  "min": null,
                  "name": "content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "JSONPath query to locate the element to delete",
                    "pt_BR": "JSONPath query to locate the element to delete",
                    "zh_Hans": "用于定位要删除元素的 JSONPath 查询"
                  },
                  "label": {
                    "en_US": "Query",
                    "pt_BR": "Query",
                    "zh_Hans": "查询"
                  },
                  "llm_description": "JSONPath query to locate the element to delete",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "Ensure the JSON output is ASCII encoded",
                    "pt_BR": "Ensure the JSON output is ASCII encoded",
                    "zh_Hans": "确保输出的 JSON 是 ASCII 编码"
                  },
                  "label": {
                    "en_US": "Ensure ASCII",
                    "pt_BR": "Ensure ASCII",
                    "zh_Hans": "确保 ASCII"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "ensure_ascii",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for replacing JSON content",
                  "pt_BR": "A tool for replacing JSON content",
                  "zh_Hans": "一个替换 JSON 内容的工具"
                },
                "llm": "A tool for replacing JSON content"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Mingwei_Zhang",
                "label": {
                  "en_US": "JSON Replace",
                  "pt_BR": "JSON Replace",
                  "zh_Hans": "JSON 替换"
                },
                "name": "json_replace"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "JSON content",
                    "pt_BR": "JSON content",
                    "zh_Hans": "JSON 内容"
                  },
                  "label": {
                    "en_US": "JSON content",
                    "pt_BR": "JSON content",
                    "zh_Hans": "JSON 内容"
                  },
                  "llm_description": "JSON content to be processed",
                  "max": null,
                  "min": null,
                  "name": "content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Query",
                    "pt_BR": "Query",
                    "zh_Hans": "查询"
                  },
                  "label": {
                    "en_US": "Query",
                    "pt_BR": "Query",
                    "zh_Hans": "查询"
                  },
                  "llm_description": "JSONPath query to locate the element to replace",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "String to be replaced",
                    "pt_BR": "String to be replaced",
                    "zh_Hans": "待替换字符串"
                  },
                  "label": {
                    "en_US": "String to be replaced",
                    "pt_BR": "String to be replaced",
                    "zh_Hans": "待替换字符串"
                  },
                  "llm_description": "String to be replaced",
                  "max": null,
                  "min": null,
                  "name": "replace_pattern",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "New Value",
                    "pt_BR": "New Value",
                    "zh_Hans": "新值"
                  },
                  "label": {
                    "en_US": "Replace Value",
                    "pt_BR": "Replace Value",
                    "zh_Hans": "替换值"
                  },
                  "llm_description": "New Value to replace",
                  "max": null,
                  "min": null,
                  "name": "replace_value",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to decode the value to a JSON object (Does not apply to replace key)",
                    "pt_BR": "Whether to decode the value to a JSON object (Does not apply to replace key)",
                    "zh_Hans": "是否将值解码为 JSON 对象 (不适用于键替换)"
                  },
                  "label": {
                    "en_US": "Decode Value",
                    "pt_BR": "Decode Value",
                    "zh_Hans": "解码值"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "value_decode",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": "pattern",
                  "form": "form",
                  "human_description": {
                    "en_US": "Replace Model",
                    "pt_BR": "Replace Model",
                    "zh_Hans": "替换模式"
                  },
                  "label": {
                    "en_US": "Replace Model",
                    "pt_BR": "Replace Model",
                    "zh_Hans": "替换模式"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "replace_model",
                  "options": [
                    {
                      "label": {
                        "en_US": "replace key",
                        "pt_BR": "replace key",
                        "zh_Hans": "键替换"
                      },
                      "value": "key"
                    },
                    {
                      "label": {
                        "en_US": "replace value",
                        "pt_BR": "replace value",
                        "zh_Hans": "值替换"
                      },
                      "value": "value"
                    },
                    {
                      "label": {
                        "en_US": "replace string",
                        "pt_BR": "replace string",
                        "zh_Hans": "字符串替换"
                      },
                      "value": "pattern"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "Ensure the JSON output is ASCII encoded",
                    "pt_BR": "Ensure the JSON output is ASCII encoded",
                    "zh_Hans": "确保输出的 JSON 是 ASCII 编码"
                  },
                  "label": {
                    "en_US": "Ensure ASCII",
                    "pt_BR": "Ensure ASCII",
                    "zh_Hans": "确保 ASCII"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "ensure_ascii",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for inserting JSON content",
                  "pt_BR": "A tool for inserting JSON content",
                  "zh_Hans": "一个插入 JSON 内容的工具"
                },
                "llm": "A tool for inserting JSON content"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Mingwei_Zhang",
                "label": {
                  "en_US": "JSON Insert",
                  "pt_BR": "JSON Insert",
                  "zh_Hans": "JSON 插入"
                },
                "name": "json_insert"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "JSON content",
                    "pt_BR": "JSON content",
                    "zh_Hans": "JSON 内容"
                  },
                  "label": {
                    "en_US": "JSON content",
                    "pt_BR": "JSON content",
                    "zh_Hans": "JSON 内容"
                  },
                  "llm_description": "JSON content to be processed",
                  "max": null,
                  "min": null,
                  "name": "content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Object to insert",
                    "pt_BR": "Object to insert",
                    "zh_Hans": "待插入的对象"
                  },
                  "label": {
                    "en_US": "Query",
                    "pt_BR": "Query",
                    "zh_Hans": "查询"
                  },
                  "llm_description": "JSONPath query to locate the element to insert",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "New Value",
                    "pt_BR": "New Value",
                    "zh_Hans": "插入的新值"
                  },
                  "label": {
                    "en_US": "New Value",
                    "pt_BR": "New Value",
                    "zh_Hans": "新值"
                  },
                  "llm_description": "New Value to insert",
                  "max": null,
                  "min": null,
                  "name": "new_value",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to decode the value to a JSON object",
                    "pt_BR": "Whether to decode the value to a JSON object",
                    "zh_Hans": "是否将值解码为 JSON 对象"
                  },
                  "label": {
                    "en_US": "Decode Value",
                    "pt_BR": "Decode Value",
                    "zh_Hans": "解码值"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "value_decode",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": "False",
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to create a path when the path does not exist",
                    "pt_BR": "Whether to create a path when the path does not exist",
                    "zh_Hans": "查询路径不存在时是否创建路径"
                  },
                  "label": {
                    "en_US": "Whether to create a path",
                    "pt_BR": "Whether to create a path",
                    "zh_Hans": "是否创建路径"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "create_path",
                  "options": [
                    {
                      "label": {
                        "en_US": "Yes",
                        "pt_BR": "Yes",
                        "zh_Hans": "是"
                      },
                      "value": "True"
                    },
                    {
                      "label": {
                        "en_US": "No",
                        "pt_BR": "No",
                        "zh_Hans": "否"
                      },
                      "value": "False"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "Ensure the JSON output is ASCII encoded",
                    "pt_BR": "Ensure the JSON output is ASCII encoded",
                    "zh_Hans": "确保输出的 JSON 是 ASCII 编码"
                  },
                  "label": {
                    "en_US": "Ensure ASCII",
                    "pt_BR": "Ensure ASCII",
                    "zh_Hans": "确保 ASCII"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "ensure_ascii",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:05:30Z",
        "version_updated_at": "2025-02-17T07:05:30Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Xorbits Inference"
        },
        "category": "model",
        "created_at": "2024-12-05T09:11:48Z",
        "endpoint": {},
        "icon": "langgenius/packages/xinference/_assets/icon_s_en.svg",
        "index_id": "langgenius___xinference",
        "install_count": 22178,
        "introduction": "",
        "label": {
          "en_US": "Xorbits Inference"
        },
        "latest_package_identifier": "langgenius/xinference:0.0.3@2f59f67f45ca4f626aaeef0d9c656cc0e38ab9fbf2c9b4673e3e20162eed9e4f",
        "latest_version": "0.0.3",
        "model": {
          "background": "#FAF5FF",
          "configurate_methods": [
            "customizable-model"
          ],
          "description": {
            "en_US": "Xorbits Inference"
          },
          "help": {
            "title": {
              "en_US": "How to deploy Xinference",
              "zh_Hans": "如何部署 Xinference"
            },
            "url": {
              "en_US": "https://github.com/xorbitsai/inference"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.svg"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "Xorbits Inference"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "Server url",
                  "zh_Hans": "服务器URL"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter the url of your Xinference, e.g. http://192.168.1.100:9997",
                  "zh_Hans": "在此输入Xinference的服务器地址，如 http://192.168.1.100:9997"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "server_url"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Model uid",
                  "zh_Hans": "模型UID"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter the model uid",
                  "zh_Hans": "在此输入您的Model UID"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "model_uid"
              },
              {
                "default": null,
                "label": {
                  "en_US": "API key",
                  "zh_Hans": "API密钥"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter the api key",
                  "zh_Hans": "在此输入您的API密钥"
                },
                "required": false,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              },
              {
                "default": "60",
                "label": {
                  "en_US": "invoke timeout (unit:second)",
                  "zh_Hans": "调用超时时间 (单位:秒)"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter invoke timeout value",
                  "zh_Hans": "在此输入调用超时时间"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "invoke_timeout"
              },
              {
                "default": "3",
                "label": {
                  "en_US": "max retries",
                  "zh_Hans": "调用重试次数"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter max retries",
                  "zh_Hans": "在此输入调用重试次数"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "max_retries"
              }
            ],
            "model": {
              "label": {
                "en_US": "Model Name",
                "zh_Hans": "模型名称"
              },
              "placeholder": {
                "en_US": "Enter your model name",
                "zh_Hans": "输入模型名称"
              }
            }
          },
          "models": [],
          "provider": "xinference",
          "provider_credential_schema": null,
          "supported_model_types": [
            "llm",
            "text-embedding",
            "rerank",
            "speech2text",
            "tts"
          ]
        },
        "name": "xinference",
        "org": "langgenius",
        "plugin_id": "langgenius/xinference",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/xinference.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-03T05:28:50Z",
        "version_updated_at": "2025-04-03T05:28:50Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "A tool for performing a Google SERP search and extracting snippets and webpages.Input should be a search query.",
          "zh_Hans": "一个用于执行 Google SERP 搜索并提取片段和网页的工具。输入应该是一个搜索查询。"
        },
        "category": "tool",
        "created_at": "2024-12-05T13:13:45Z",
        "endpoint": {},
        "icon": "langgenius/packages/google/_assets/icon.svg",
        "index_id": "langgenius___google",
        "install_count": 19687,
        "introduction": "# Google Search\n\n## Overview\n\nThe Google Search tool is a real-time API that extracts search engine results, providing structured data from Google. It supports various search types, including web, image, news, and maps.\n\n## Configuration\n\n### 1. Apply for an API Key\n\nPlease apply for an API Key on the [SerpApi](https://serpapi.com/dashboard).\n\n![](./_assets/google_3.png)\n\n### 2. Get Google tools from Plugin Marketplace\n\nThe Google tools could be found at the Plugin Marketplace, please install it first.\n\n### 3. Fill in the configuration in Dify\n\nOn the Dify navigation page, click `Tools > Google > To authorize` filling in the API Key.\n\n![](./_assets/google_1.png)\n\n### 4. Use the tool\n\nYou can use the Google tool in the following application types:\n\n![](./_assets/google_2.png)\n\n#### Chatflow / Workflow applications\n\nBoth Chatflow and Workflow applications support adding a Google tool node.\n\n#### Agent applications\n\nAdd the Google tool in the Agent application, then enter online search instructions to call this tool.",
        "label": {
          "en_US": "Google"
        },
        "latest_package_identifier": "langgenius/google:0.0.8@3efcf55ffeef9d0f77715e0afb23534952ae0cb385c051d0637e86d71199d1a6",
        "latest_version": "0.0.8",
        "model": {},
        "name": "google",
        "org": "langgenius",
        "plugin_id": "langgenius/google",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/google.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "search"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "SerpApi API key",
                "pt_BR": "SerpApi API key",
                "zh_Hans": "SerpApi API key"
              },
              "name": "serpapi_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your SerpApi API key",
                "pt_BR": "Please input your SerpApi API key",
                "zh_Hans": "请输入你的 SerpApi API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://serpapi.com/manage-api-key"
            }
          ],
          "identity": {
            "author": "Dify",
            "description": {
              "en_US": "Google",
              "pt_BR": "Google",
              "zh_Hans": "GoogleSearch"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Google",
              "pt_BR": "Google",
              "zh_Hans": "Google"
            },
            "name": "google",
            "tags": [
              "search"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool for performing a Google SERP search and extracting snippets and webpages.Input should be a search query.",
                  "pt_BR": "A tool for performing a Google SERP search and extracting snippets and webpages.Input should be a search query.",
                  "zh_Hans": "一个用于执行 Google SERP 搜索并提取片段和网页的工具。输入应该是一个搜索查询。"
                },
                "llm": "A tool for performing a Google SERP search and extracting snippets and webpages.Input should be a search query."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Dify",
                "label": {
                  "en_US": "GoogleSearch",
                  "pt_BR": "GoogleSearch",
                  "zh_Hans": "谷歌搜索"
                },
                "name": "google_search"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "used for searching",
                    "pt_BR": "used for searching",
                    "zh_Hans": "用于搜索网页内容"
                  },
                  "label": {
                    "en_US": "Query string",
                    "pt_BR": "Query string",
                    "zh_Hans": "查询语句"
                  },
                  "llm_description": "key words for searching",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:07:33Z",
        "version_updated_at": "2025-02-17T07:07:33Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Bing Search",
          "pt_BR": "Bing Search",
          "zh_Hans": "Bing Search"
        },
        "category": "tool",
        "created_at": "2024-12-03T10:09:32Z",
        "endpoint": {},
        "icon": "langgenius/packages/bing/_assets/icon.svg",
        "index_id": "langgenius___bing",
        "install_count": 15686,
        "introduction": "# Bing\n\n## Overview\n\nThe Bing search tool can help you obtain online search results when using LLM applications. Below are the steps to configure and use the Bing search tool in Dify.\n\n## Configuration\n\n### 1. Apply for Bing API Key\n\nPlease apply for an API Key on the [Azure platform](https://www.microsoft.com/en-us/bing/apis/bing-web-search-api).\n\n### 2. Get Azure tools from Plugin Marketplace\n\nThe Bing tools could be found at the Plugin Marketplace, please install it.\n\n![](./_assets/bing_1.PNG)\n\n### 3. Fill in the configuration in Dify\n\nOn the Dify navigation page, click Tools > Azure > Authorize to fill in the API Key.\n\n![](./_assets/bing_2.png)\n\n### 4. Use the tool\n\nYou can use the Bing tool in the following application types.\n\n![](./_assets/bing_3.PNG)\n\n#### Chatflow / Workflow applications\n\nBoth Chatflow and Workflow applications support adding Bing tool nodes.\n\n#### Agent applications\n\nAdd the Bing tool in the Agent application, then enter the online search command to call this tool.",
        "label": {
          "en_US": "Bing"
        },
        "latest_package_identifier": "langgenius/bing:0.0.4@e69b2b474650cd94cffebedc8bf68614105e72932cdfd2e7b1b652d6662f44e3",
        "latest_version": "0.0.4",
        "model": {},
        "name": "bing",
        "org": "langgenius",
        "plugin_id": "langgenius/bing",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/bing.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Get your Bing subscription key from Bing",
                "pt_BR": "Get your Bing subscription key from Bing",
                "zh_Hans": "从 Bing 获取您的 Bing subscription key"
              },
              "label": {
                "en_US": "Bing subscription key",
                "pt_BR": "Bing subscription key",
                "zh_Hans": "Bing subscription key"
              },
              "name": "subscription_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Bing subscription key",
                "pt_BR": "Please input your Bing subscription key",
                "zh_Hans": "请输入你的 Bing subscription key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://www.microsoft.com/cognitive-services/en-us/bing-web-search-api"
            },
            {
              "default": "https://api.bing.microsoft.com/v7.0/search",
              "help": {
                "en_US": "An endpoint is like \"https://api.bing.microsoft.com/v7.0/search\"",
                "pt_BR": "An endpoint is like \"https://api.bing.microsoft.com/v7.0/search\"",
                "zh_Hans": "例如 \"https://api.bing.microsoft.com/v7.0/search\""
              },
              "label": {
                "en_US": "Bing endpoint",
                "pt_BR": "Bing endpoint",
                "zh_Hans": "Bing endpoint"
              },
              "name": "server_url",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Bing endpoint",
                "pt_BR": "Please input your Bing endpoint",
                "zh_Hans": "请输入你的 Bing 端点"
              },
              "required": false,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": true,
              "help": {
                "en_US": "Does your subscription plan allow entity search",
                "pt_BR": "Does your subscription plan allow entity search",
                "zh_Hans": "您的订阅计划是否支持实体搜索"
              },
              "label": {
                "en_US": "Allow Entities Search",
                "pt_BR": "Allow Entities Search",
                "zh_Hans": "支持实体搜索"
              },
              "name": "allow_entities",
              "options": null,
              "placeholder": null,
              "required": false,
              "scope": null,
              "type": "boolean",
              "url": null
            },
            {
              "default": true,
              "help": {
                "en_US": "Does your subscription plan allow web pages search",
                "pt_BR": "Does your subscription plan allow web pages search",
                "zh_Hans": "您的订阅计划是否支持网页搜索"
              },
              "label": {
                "en_US": "Allow Web Pages Search",
                "pt_BR": "Allow Web Pages Search",
                "zh_Hans": "支持网页搜索"
              },
              "name": "allow_web_pages",
              "options": null,
              "placeholder": null,
              "required": false,
              "scope": null,
              "type": "boolean",
              "url": null
            },
            {
              "default": false,
              "help": {
                "en_US": "Does your subscription plan allow computation search",
                "pt_BR": "Does your subscription plan allow computation search",
                "zh_Hans": "您的订阅计划是否支持计算搜索"
              },
              "label": {
                "en_US": "Allow Computation Search",
                "pt_BR": "Allow Computation Search",
                "zh_Hans": "支持计算搜索"
              },
              "name": "allow_computation",
              "options": null,
              "placeholder": null,
              "required": false,
              "scope": null,
              "type": "boolean",
              "url": null
            },
            {
              "default": false,
              "help": {
                "en_US": "Does your subscription plan allow news search",
                "pt_BR": "Does your subscription plan allow news search",
                "zh_Hans": "您的订阅计划是否支持新闻搜索"
              },
              "label": {
                "en_US": "Allow News Search",
                "pt_BR": "Allow News Search",
                "zh_Hans": "支持新闻搜索"
              },
              "name": "allow_news",
              "options": null,
              "placeholder": null,
              "required": false,
              "scope": null,
              "type": "boolean",
              "url": null
            },
            {
              "default": false,
              "help": {
                "en_US": "Does your subscription plan allow related searches",
                "pt_BR": "Does your subscription plan allow related searches",
                "zh_Hans": "您的订阅计划是否支持相关搜索"
              },
              "label": {
                "en_US": "Allow Related Searches",
                "pt_BR": "Allow Related Searches",
                "zh_Hans": "支持相关搜索"
              },
              "name": "allow_related_searches",
              "options": null,
              "placeholder": null,
              "required": false,
              "scope": null,
              "type": "boolean",
              "url": null
            }
          ],
          "identity": {
            "author": "langgenius",
            "description": {
              "en_US": "Bing Search",
              "pt_BR": "Bing Search",
              "zh_Hans": "Bing 搜索"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Bing",
              "pt_BR": "Bing",
              "zh_Hans": "Bing"
            },
            "name": "bing",
            "tags": [
              "search"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool for performing a Bing SERP search and extracting snippets and webpages.Input should be a search query.",
                  "pt_BR": "A tool for performing a Bing SERP search and extracting snippets and webpages.Input should be a search query.",
                  "zh_Hans": "一个用于执行 Bing SERP 搜索并提取片段和网页的工具。输入应该是一个搜索查询。"
                },
                "llm": "A tool for performing a Bing SERP search and extracting snippets and webpages.Input should be a search query."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "BingWebSearch",
                  "pt_BR": "BingWebSearch",
                  "zh_Hans": "必应网页搜索"
                },
                "name": "bing_web_search"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "used for searching",
                    "pt_BR": "used for searching",
                    "zh_Hans": "用于搜索网页内容"
                  },
                  "label": {
                    "en_US": "Query string",
                    "pt_BR": "Query string",
                    "zh_Hans": "查询语句"
                  },
                  "llm_description": "key words for searching",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "enable computation",
                    "pt_BR": "enable computation",
                    "zh_Hans": "启用计算"
                  },
                  "label": {
                    "en_US": "Enable computation",
                    "pt_BR": "Enable computation",
                    "zh_Hans": "启用计算"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "enable_computation",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "enable entities",
                    "pt_BR": "enable entities",
                    "zh_Hans": "启用实体搜索"
                  },
                  "label": {
                    "en_US": "Enable entities",
                    "pt_BR": "Enable entities",
                    "zh_Hans": "启用实体搜索"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "enable_entities",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "enable news",
                    "pt_BR": "enable news",
                    "zh_Hans": "启用新闻搜索"
                  },
                  "label": {
                    "en_US": "Enable news",
                    "pt_BR": "Enable news",
                    "zh_Hans": "启用新闻搜索"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "enable_news",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "enable related search",
                    "pt_BR": "enable related search",
                    "zh_Hans": "启用相关搜索"
                  },
                  "label": {
                    "en_US": "Enable related search",
                    "pt_BR": "Enable related search",
                    "zh_Hans": "启用相关搜索"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "enable_related_search",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "enable webpages search",
                    "pt_BR": "enable webpages search",
                    "zh_Hans": "启用网页搜索"
                  },
                  "label": {
                    "en_US": "Enable webpages search",
                    "pt_BR": "Enable webpages search",
                    "zh_Hans": "启用网页搜索"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "enable_webpages",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": 5,
                  "form": "form",
                  "human_description": {
                    "en_US": "limit the number of results",
                    "pt_BR": "limit the number of results",
                    "zh_Hans": "限制返回结果的数量"
                  },
                  "label": {
                    "en_US": "Limit for results length",
                    "pt_BR": "Limit for results length",
                    "zh_Hans": "返回长度限制"
                  },
                  "llm_description": "",
                  "max": 10,
                  "min": 1,
                  "name": "limit",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "text",
                  "form": "form",
                  "human_description": {
                    "en_US": "return a list of links or texts",
                    "pt_BR": "return a list of links or texts",
                    "zh_Hans": "返回一个连接列表还是纯文本内容"
                  },
                  "label": {
                    "en_US": "result type",
                    "pt_BR": "result type",
                    "zh_Hans": "结果类型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "result_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "Link",
                        "pt_BR": "Link",
                        "zh_Hans": "链接"
                      },
                      "value": "link"
                    },
                    {
                      "label": {
                        "en_US": "Text",
                        "pt_BR": "Text",
                        "zh_Hans": "文本"
                      },
                      "value": "text"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "US",
                  "form": "form",
                  "human_description": {
                    "en_US": "market takes responsibility for the region",
                    "pt_BR": "market takes responsibility for the region",
                    "zh_Hans": "市场决定了搜索结果的地区"
                  },
                  "label": {
                    "en_US": "Market",
                    "pt_BR": "Market",
                    "zh_Hans": "市场"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "market",
                  "options": [
                    {
                      "label": {
                        "en_US": "Argentina",
                        "pt_BR": "Argentina",
                        "zh_Hans": "阿根廷"
                      },
                      "value": "AR"
                    },
                    {
                      "label": {
                        "en_US": "Australia",
                        "pt_BR": "Australia",
                        "zh_Hans": "澳大利亚"
                      },
                      "value": "AU"
                    },
                    {
                      "label": {
                        "en_US": "Austria",
                        "pt_BR": "Austria",
                        "zh_Hans": "奥地利"
                      },
                      "value": "AT"
                    },
                    {
                      "label": {
                        "en_US": "Belgium",
                        "pt_BR": "Belgium",
                        "zh_Hans": "比利时"
                      },
                      "value": "BE"
                    },
                    {
                      "label": {
                        "en_US": "Brazil",
                        "pt_BR": "Brazil",
                        "zh_Hans": "巴西"
                      },
                      "value": "BR"
                    },
                    {
                      "label": {
                        "en_US": "Canada",
                        "pt_BR": "Canada",
                        "zh_Hans": "加拿大"
                      },
                      "value": "CA"
                    },
                    {
                      "label": {
                        "en_US": "Chile",
                        "pt_BR": "Chile",
                        "zh_Hans": "智利"
                      },
                      "value": "CL"
                    },
                    {
                      "label": {
                        "en_US": "Colombia",
                        "pt_BR": "Colombia",
                        "zh_Hans": "哥伦比亚"
                      },
                      "value": "CO"
                    },
                    {
                      "label": {
                        "en_US": "China",
                        "pt_BR": "China",
                        "zh_Hans": "中国"
                      },
                      "value": "CN"
                    },
                    {
                      "label": {
                        "en_US": "Czech Republic",
                        "pt_BR": "Czech Republic",
                        "zh_Hans": "捷克共和国"
                      },
                      "value": "CZ"
                    },
                    {
                      "label": {
                        "en_US": "Denmark",
                        "pt_BR": "Denmark",
                        "zh_Hans": "丹麦"
                      },
                      "value": "DK"
                    },
                    {
                      "label": {
                        "en_US": "Finland",
                        "pt_BR": "Finland",
                        "zh_Hans": "芬兰"
                      },
                      "value": "FI"
                    },
                    {
                      "label": {
                        "en_US": "France",
                        "pt_BR": "France",
                        "zh_Hans": "法国"
                      },
                      "value": "FR"
                    },
                    {
                      "label": {
                        "en_US": "Germany",
                        "pt_BR": "Germany",
                        "zh_Hans": "德国"
                      },
                      "value": "DE"
                    },
                    {
                      "label": {
                        "en_US": "Hong Kong",
                        "pt_BR": "Hong Kong",
                        "zh_Hans": "香港"
                      },
                      "value": "HK"
                    },
                    {
                      "label": {
                        "en_US": "India",
                        "pt_BR": "India",
                        "zh_Hans": "印度"
                      },
                      "value": "IN"
                    },
                    {
                      "label": {
                        "en_US": "Indonesia",
                        "pt_BR": "Indonesia",
                        "zh_Hans": "印度尼西亚"
                      },
                      "value": "ID"
                    },
                    {
                      "label": {
                        "en_US": "Italy",
                        "pt_BR": "Italy",
                        "zh_Hans": "意大利"
                      },
                      "value": "IT"
                    },
                    {
                      "label": {
                        "en_US": "Japan",
                        "pt_BR": "Japan",
                        "zh_Hans": "日本"
                      },
                      "value": "JP"
                    },
                    {
                      "label": {
                        "en_US": "Korea",
                        "pt_BR": "Korea",
                        "zh_Hans": "韩国"
                      },
                      "value": "KR"
                    },
                    {
                      "label": {
                        "en_US": "Malaysia",
                        "pt_BR": "Malaysia",
                        "zh_Hans": "马来西亚"
                      },
                      "value": "MY"
                    },
                    {
                      "label": {
                        "en_US": "Mexico",
                        "pt_BR": "Mexico",
                        "zh_Hans": "墨西哥"
                      },
                      "value": "MX"
                    },
                    {
                      "label": {
                        "en_US": "Netherlands",
                        "pt_BR": "Netherlands",
                        "zh_Hans": "荷兰"
                      },
                      "value": "NL"
                    },
                    {
                      "label": {
                        "en_US": "New Zealand",
                        "pt_BR": "New Zealand",
                        "zh_Hans": "新西兰"
                      },
                      "value": "NZ"
                    },
                    {
                      "label": {
                        "en_US": "Norway",
                        "pt_BR": "Norway",
                        "zh_Hans": "挪威"
                      },
                      "value": "NO"
                    },
                    {
                      "label": {
                        "en_US": "Philippines",
                        "pt_BR": "Philippines",
                        "zh_Hans": "菲律宾"
                      },
                      "value": "PH"
                    },
                    {
                      "label": {
                        "en_US": "Poland",
                        "pt_BR": "Poland",
                        "zh_Hans": "波兰"
                      },
                      "value": "PL"
                    },
                    {
                      "label": {
                        "en_US": "Portugal",
                        "pt_BR": "Portugal",
                        "zh_Hans": "葡萄牙"
                      },
                      "value": "PT"
                    },
                    {
                      "label": {
                        "en_US": "Russia",
                        "pt_BR": "Russia",
                        "zh_Hans": "俄罗斯"
                      },
                      "value": "RU"
                    },
                    {
                      "label": {
                        "en_US": "Saudi Arabia",
                        "pt_BR": "Saudi Arabia",
                        "zh_Hans": "沙特阿拉伯"
                      },
                      "value": "SA"
                    },
                    {
                      "label": {
                        "en_US": "Singapore",
                        "pt_BR": "Singapore",
                        "zh_Hans": "新加坡"
                      },
                      "value": "SG"
                    },
                    {
                      "label": {
                        "en_US": "South Africa",
                        "pt_BR": "South Africa",
                        "zh_Hans": "南非"
                      },
                      "value": "ZA"
                    },
                    {
                      "label": {
                        "en_US": "Spain",
                        "pt_BR": "Spain",
                        "zh_Hans": "西班牙"
                      },
                      "value": "ES"
                    },
                    {
                      "label": {
                        "en_US": "Sweden",
                        "pt_BR": "Sweden",
                        "zh_Hans": "瑞典"
                      },
                      "value": "SE"
                    },
                    {
                      "label": {
                        "en_US": "Switzerland",
                        "pt_BR": "Switzerland",
                        "zh_Hans": "瑞士"
                      },
                      "value": "CH"
                    },
                    {
                      "label": {
                        "en_US": "Taiwan",
                        "pt_BR": "Taiwan",
                        "zh_Hans": "台湾"
                      },
                      "value": "TW"
                    },
                    {
                      "label": {
                        "en_US": "Thailand",
                        "pt_BR": "Thailand",
                        "zh_Hans": "泰国"
                      },
                      "value": "TH"
                    },
                    {
                      "label": {
                        "en_US": "Turkey",
                        "pt_BR": "Turkey",
                        "zh_Hans": "土耳其"
                      },
                      "value": "TR"
                    },
                    {
                      "label": {
                        "en_US": "United Kingdom",
                        "pt_BR": "United Kingdom",
                        "zh_Hans": "英国"
                      },
                      "value": "GB"
                    },
                    {
                      "label": {
                        "en_US": "United States",
                        "pt_BR": "United States",
                        "zh_Hans": "美国"
                      },
                      "value": "US"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "en",
                  "form": "form",
                  "human_description": {
                    "en_US": "language takes responsibility for the language of the search result",
                    "pt_BR": "language takes responsibility for the language of the search result",
                    "zh_Hans": "语言决定了搜索结果的语言"
                  },
                  "label": {
                    "en_US": "Language",
                    "pt_BR": "Language",
                    "zh_Hans": "语言"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "language",
                  "options": [
                    {
                      "label": {
                        "en_US": "Arabic",
                        "pt_BR": "Arabic",
                        "zh_Hans": "阿拉伯语"
                      },
                      "value": "ar"
                    },
                    {
                      "label": {
                        "en_US": "Bulgarian",
                        "pt_BR": "Bulgarian",
                        "zh_Hans": "保加利亚语"
                      },
                      "value": "bg"
                    },
                    {
                      "label": {
                        "en_US": "Catalan",
                        "pt_BR": "Catalan",
                        "zh_Hans": "加泰罗尼亚语"
                      },
                      "value": "ca"
                    },
                    {
                      "label": {
                        "en_US": "Chinese (Simplified)",
                        "pt_BR": "Chinese (Simplified)",
                        "zh_Hans": "中文（简体）"
                      },
                      "value": "zh-hans"
                    },
                    {
                      "label": {
                        "en_US": "Chinese (Traditional)",
                        "pt_BR": "Chinese (Traditional)",
                        "zh_Hans": "中文（繁体）"
                      },
                      "value": "zh-hant"
                    },
                    {
                      "label": {
                        "en_US": "Czech",
                        "pt_BR": "Czech",
                        "zh_Hans": "捷克语"
                      },
                      "value": "cs"
                    },
                    {
                      "label": {
                        "en_US": "Danish",
                        "pt_BR": "Danish",
                        "zh_Hans": "丹麦语"
                      },
                      "value": "da"
                    },
                    {
                      "label": {
                        "en_US": "Dutch",
                        "pt_BR": "Dutch",
                        "zh_Hans": "荷兰语"
                      },
                      "value": "nl"
                    },
                    {
                      "label": {
                        "en_US": "English",
                        "pt_BR": "English",
                        "zh_Hans": "英语"
                      },
                      "value": "en"
                    },
                    {
                      "label": {
                        "en_US": "Estonian",
                        "pt_BR": "Estonian",
                        "zh_Hans": "爱沙尼亚语"
                      },
                      "value": "et"
                    },
                    {
                      "label": {
                        "en_US": "Finnish",
                        "pt_BR": "Finnish",
                        "zh_Hans": "芬兰语"
                      },
                      "value": "fi"
                    },
                    {
                      "label": {
                        "en_US": "French",
                        "pt_BR": "French",
                        "zh_Hans": "法语"
                      },
                      "value": "fr"
                    },
                    {
                      "label": {
                        "en_US": "German",
                        "pt_BR": "German",
                        "zh_Hans": "德语"
                      },
                      "value": "de"
                    },
                    {
                      "label": {
                        "en_US": "Greek",
                        "pt_BR": "Greek",
                        "zh_Hans": "希腊语"
                      },
                      "value": "el"
                    },
                    {
                      "label": {
                        "en_US": "Hebrew",
                        "pt_BR": "Hebrew",
                        "zh_Hans": "希伯来语"
                      },
                      "value": "he"
                    },
                    {
                      "label": {
                        "en_US": "Hindi",
                        "pt_BR": "Hindi",
                        "zh_Hans": "印地语"
                      },
                      "value": "hi"
                    },
                    {
                      "label": {
                        "en_US": "Hungarian",
                        "pt_BR": "Hungarian",
                        "zh_Hans": "匈牙利语"
                      },
                      "value": "hu"
                    },
                    {
                      "label": {
                        "en_US": "Indonesian",
                        "pt_BR": "Indonesian",
                        "zh_Hans": "印尼语"
                      },
                      "value": "id"
                    },
                    {
                      "label": {
                        "en_US": "Italian",
                        "pt_BR": "Italian",
                        "zh_Hans": "意大利语"
                      },
                      "value": "it"
                    },
                    {
                      "label": {
                        "en_US": "Japanese",
                        "pt_BR": "Japanese",
                        "zh_Hans": "日语"
                      },
                      "value": "jp"
                    },
                    {
                      "label": {
                        "en_US": "Kannada",
                        "pt_BR": "Kannada",
                        "zh_Hans": "卡纳达语"
                      },
                      "value": "kn"
                    },
                    {
                      "label": {
                        "en_US": "Korean",
                        "pt_BR": "Korean",
                        "zh_Hans": "韩语"
                      },
                      "value": "ko"
                    },
                    {
                      "label": {
                        "en_US": "Latvian",
                        "pt_BR": "Latvian",
                        "zh_Hans": "拉脱维亚语"
                      },
                      "value": "lv"
                    },
                    {
                      "label": {
                        "en_US": "Lithuanian",
                        "pt_BR": "Lithuanian",
                        "zh_Hans": "立陶宛语"
                      },
                      "value": "lt"
                    },
                    {
                      "label": {
                        "en_US": "Malay",
                        "pt_BR": "Malay",
                        "zh_Hans": "马来语"
                      },
                      "value": "ms"
                    },
                    {
                      "label": {
                        "en_US": "Malayalam",
                        "pt_BR": "Malayalam",
                        "zh_Hans": "马拉雅拉姆语"
                      },
                      "value": "ml"
                    },
                    {
                      "label": {
                        "en_US": "Marathi",
                        "pt_BR": "Marathi",
                        "zh_Hans": "马拉地语"
                      },
                      "value": "mr"
                    },
                    {
                      "label": {
                        "en_US": "Norwegian",
                        "pt_BR": "Norwegian",
                        "zh_Hans": "挪威语"
                      },
                      "value": "nb"
                    },
                    {
                      "label": {
                        "en_US": "Polish",
                        "pt_BR": "Polish",
                        "zh_Hans": "波兰语"
                      },
                      "value": "pl"
                    },
                    {
                      "label": {
                        "en_US": "Portuguese (Brazil)",
                        "pt_BR": "Portuguese (Brazil)",
                        "zh_Hans": "葡萄牙语（巴西）"
                      },
                      "value": "pt-br"
                    },
                    {
                      "label": {
                        "en_US": "Portuguese (Portugal)",
                        "pt_BR": "Portuguese (Portugal)",
                        "zh_Hans": "葡萄牙语（葡萄牙）"
                      },
                      "value": "pt-pt"
                    },
                    {
                      "label": {
                        "en_US": "Punjabi",
                        "pt_BR": "Punjabi",
                        "zh_Hans": "旁遮普语"
                      },
                      "value": "pa"
                    },
                    {
                      "label": {
                        "en_US": "Romanian",
                        "pt_BR": "Romanian",
                        "zh_Hans": "罗马尼亚语"
                      },
                      "value": "ro"
                    },
                    {
                      "label": {
                        "en_US": "Russian",
                        "pt_BR": "Russian",
                        "zh_Hans": "俄语"
                      },
                      "value": "ru"
                    },
                    {
                      "label": {
                        "en_US": "Serbian",
                        "pt_BR": "Serbian",
                        "zh_Hans": "塞尔维亚语"
                      },
                      "value": "sr"
                    },
                    {
                      "label": {
                        "en_US": "Slovak",
                        "pt_BR": "Slovak",
                        "zh_Hans": "斯洛伐克语"
                      },
                      "value": "sk"
                    },
                    {
                      "label": {
                        "en_US": "Slovenian",
                        "pt_BR": "Slovenian",
                        "zh_Hans": "斯洛文尼亚语"
                      },
                      "value": "sl"
                    },
                    {
                      "label": {
                        "en_US": "Spanish",
                        "pt_BR": "Spanish",
                        "zh_Hans": "西班牙语"
                      },
                      "value": "es"
                    },
                    {
                      "label": {
                        "en_US": "Swedish",
                        "pt_BR": "Swedish",
                        "zh_Hans": "瑞典语"
                      },
                      "value": "sv"
                    },
                    {
                      "label": {
                        "en_US": "Tamil",
                        "pt_BR": "Tamil",
                        "zh_Hans": "泰米尔语"
                      },
                      "value": "ta"
                    },
                    {
                      "label": {
                        "en_US": "Telugu",
                        "pt_BR": "Telugu",
                        "zh_Hans": "泰卢固语"
                      },
                      "value": "te"
                    },
                    {
                      "label": {
                        "en_US": "Thai",
                        "pt_BR": "Thai",
                        "zh_Hans": "泰语"
                      },
                      "value": "th"
                    },
                    {
                      "label": {
                        "en_US": "Turkish",
                        "pt_BR": "Turkish",
                        "zh_Hans": "土耳其语"
                      },
                      "value": "tr"
                    },
                    {
                      "label": {
                        "en_US": "Ukrainian",
                        "pt_BR": "Ukrainian",
                        "zh_Hans": "乌克兰语"
                      },
                      "value": "uk"
                    },
                    {
                      "label": {
                        "en_US": "Vietnamese",
                        "pt_BR": "Vietnamese",
                        "zh_Hans": "越南语"
                      },
                      "value": "vi"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-25T02:28:18Z",
        "version_updated_at": "2025-03-25T02:28:18Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Your Search Foundation, Supercharged!",
          "pt_BR": "Your Search Foundation, Supercharged!",
          "zh_Hans": "您的搜索底座，从此不同!"
        },
        "category": "tool",
        "created_at": "2024-12-04T08:54:55Z",
        "endpoint": {},
        "icon": "langgenius/packages/jina_tool/_assets/icon.svg",
        "index_id": "langgenius___jina_tool",
        "install_count": 15545,
        "introduction": "# Jina AI\n\n## Overview\n\nJina AI is an open-source neural search framework for building scalable, multimodal AI applications. It provides tools for indexing and retrieving diverse data, including the ability to segment webpages, fetch single pages, and search websites. It focuses on simplifying complex AI search functionalities, and making web data processing easier.\n\n## Configuration\n\n### 1. Apply for Jina API Key\n\nPlease apply for an API Key on the [Jina homepage](https://jina.ai/).\n\n![](./_assets/jina_3.png)\n\n### 2. Get Jina AI tools from Plugin Marketplace\n\nThe Jina tools could be found at the Plugin Marketplace, please install it first.\n\n### 3. Fill in the configuration in Dify\n\nOn the Dify navigation page, click `Tools > Jina AI > To Authorize` and filling the API Key.\n\n![](./_assets/jina_1.png)\n\n### 4. Use the tool\n\nYou can use the Jina tool in the following application types:\n\n#### Chatflow / Workflow applications\n\n![](./_assets/jina_2.PNG)\n\nBoth Chatflow and Workflow applications support adding `Jina` tool nodes.\n\n#### Agent applications\n\nAdd the Jina tool in the Agent application, then enter the online search command to call this tool.",
        "label": {
          "en_US": "Jina AI",
          "pt_BR": "Jina AI",
          "zh_Hans": "Jina AI"
        },
        "latest_package_identifier": "langgenius/jina_tool:0.0.7@51cf3dfcc4ff002171f2378aa02ec7ce5390ddfe23c02ede532b08f48a75e82c",
        "latest_version": "0.0.7",
        "model": {},
        "name": "jina_tool",
        "org": "langgenius",
        "plugin_id": "langgenius/jina_tool",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/jina.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "search"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Get your Jina AI API key from Jina AI (optional, but you can get a higher rate)",
                "pt_BR": "Obtenha sua chave de API do Jina AI na Jina AI (opcional, mas você pode obter uma taxa mais alta)",
                "zh_Hans": "从 Jina AI 获取您的 Jina AI API 密钥（非必须，能得到更高的速率）"
              },
              "label": {
                "en_US": "API Key (leave empty if you don't have one)",
                "pt_BR": "Chave API (deixe vazio se você não tiver uma)",
                "zh_Hans": "API 密钥（可留空）"
              },
              "name": "api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please enter your Jina AI API key",
                "pt_BR": "Por favor, insira sua chave de API do Jina AI",
                "zh_Hans": "请输入你的 Jina AI API 密钥"
              },
              "required": false,
              "scope": null,
              "type": "secret-input",
              "url": "https://jina.ai"
            }
          ],
          "identity": {
            "author": "langgenius",
            "description": {
              "en_US": "Your Search Foundation, Supercharged!",
              "pt_BR": "Your Search Foundation, Supercharged!",
              "zh_Hans": "您的搜索底座，从此不同!"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Jina AI",
              "pt_BR": "Jina AI",
              "zh_Hans": "Jina AI"
            },
            "name": "jina",
            "tags": [
              "search",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Split long text into chunks and do tokenization.",
                  "pt_BR": "Dividir o texto longo em pedaços e fazer tokenização.",
                  "zh_Hans": "将长文本拆分成小段落，并做分词处理。"
                },
                "llm": "Free API to tokenize text and segment long text into chunks."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "hjlarry",
                "label": {
                  "en_US": "Segment",
                  "pt_BR": "Segment",
                  "zh_Hans": "切分器"
                },
                "name": "jina_tokenizer"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The content which need to tokenize or segment.",
                    "pt_BR": "O conteúdo que precisa ser tokenizado ou segmentado.",
                    "zh_Hans": "需要分词或分段的内容。"
                  },
                  "label": {
                    "en_US": "Content",
                    "pt_BR": "Conteúdo",
                    "zh_Hans": "内容"
                  },
                  "llm_description": "the content which need to tokenize or segment",
                  "max": null,
                  "min": null,
                  "name": "content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Return the tokens and their corresponding ids in the response.",
                    "pt_BR": "Retornar os tokens e seus respectivos ids na resposta.",
                    "zh_Hans": "返回tokens及其对应的ids。"
                  },
                  "label": {
                    "en_US": "Return the tokens",
                    "pt_BR": "Retornar os tokens",
                    "zh_Hans": "是否返回tokens"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "return_tokens",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Chunking the input into semantically meaningful segments while handling a wide variety of text types and edge cases based on common structural cues.",
                    "pt_BR": "Dividir o texto de entrada em segmentos semanticamente significativos, enquanto lida com uma ampla variedade de tipos de texto e casos de borda com base em pistas estruturais comuns.",
                    "zh_Hans": "将输入文本分块为语义有意义的片段，同时基于常见的结构线索处理各种文本类型和特殊情况。"
                  },
                  "label": {
                    "en_US": "Return the chunks",
                    "pt_BR": "Retornar os chunks",
                    "zh_Hans": "是否分块"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "return_chunks",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "· cl100k_base --- gpt-4, gpt-3.5-turbo, gpt-3.5\n· o200k_base  --- gpt-4o, gpt-4o-mini\n· p50k_base   --- text-davinci-003, text-davinci-002\n· r50k_base   --- text-davinci-001, text-curie-001\n· p50k_edit   --- text-davinci-edit-001, code-davinci-edit-001\n· gpt2        --- gpt-2\n"
                  },
                  "label": {
                    "en_US": "Tokenizer"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "tokenizer",
                  "options": [
                    {
                      "label": {
                        "en_US": "cl100k_base"
                      },
                      "value": "cl100k_base"
                    },
                    {
                      "label": {
                        "en_US": "o200k_base"
                      },
                      "value": "o200k_base"
                    },
                    {
                      "label": {
                        "en_US": "p50k_base"
                      },
                      "value": "p50k_base"
                    },
                    {
                      "label": {
                        "en_US": "r50k_base"
                      },
                      "value": "r50k_base"
                    },
                    {
                      "label": {
                        "en_US": "p50k_edit"
                      },
                      "value": "p50k_edit"
                    },
                    {
                      "label": {
                        "en_US": "gpt2"
                      },
                      "value": "gpt2"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Fetch the target URL (can be a PDF) and convert it into a LLM-friendly markdown.",
                  "pt_BR": "Busque a URL de destino (que pode ser um PDF) e converta em um Markdown LLM-friendly.",
                  "zh_Hans": "获取目标网址（可以是 PDF），并将其转换为适合大模型处理的 Markdown 格式。"
                },
                "llm": "A tool for scraping webpages. Input should be a URL."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Fetch Single Page",
                  "pt_BR": "Fetch Single Page",
                  "zh_Hans": "获取单页面"
                },
                "name": "jina_reader"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Web link",
                    "pt_BR": "URL da web",
                    "zh_Hans": "网页链接"
                  },
                  "label": {
                    "en_US": "URL",
                    "pt_BR": "URL",
                    "zh_Hans": "网址"
                  },
                  "llm_description": "url para scraping",
                  "max": null,
                  "min": null,
                  "name": "url",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "request parameters, format: {\"key1\": \"value1\", \"key2\": \"value2\"}\n",
                    "pt_BR": "parâmetros de solicitação, formato: {\"key1\": \"value1\", \"key2\": \"value2\"}\n",
                    "zh_Hans": "请求参数，格式：{\"key1\": \"value1\", \"key2\": \"value2\"}\n"
                  },
                  "label": {
                    "en_US": "Request params",
                    "pt_BR": "Parâmetros de solicitação",
                    "zh_Hans": "请求参数"
                  },
                  "llm_description": "request parameters",
                  "max": null,
                  "min": null,
                  "name": "request_params",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "css selector for scraping specific elements",
                    "pt_BR": "css selector para scraping de elementos específicos",
                    "zh_Hans": "css 选择器用于抓取特定元素"
                  },
                  "label": {
                    "en_US": "Target selector",
                    "pt_BR": "Seletor de destino",
                    "zh_Hans": "目标选择器"
                  },
                  "llm_description": "css selector of the target element to scrape",
                  "max": null,
                  "min": null,
                  "name": "target_selector",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "css selector for waiting for specific elements",
                    "pt_BR": "css selector para aguardar elementos específicos",
                    "zh_Hans": "css 选择器用于等待特定元素"
                  },
                  "label": {
                    "en_US": "Wait for selector",
                    "pt_BR": "Aguardar por seletor",
                    "zh_Hans": "等待选择器"
                  },
                  "llm_description": "css selector of the target element to wait for",
                  "max": null,
                  "min": null,
                  "name": "wait_for_selector",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Remove all images from the response.",
                    "zh_Hans": "从响应中删除所有图片。"
                  },
                  "label": {
                    "en_US": "Remove images",
                    "zh_Hans": "删除图片"
                  },
                  "llm_description": "Remove all images from the response",
                  "max": null,
                  "min": null,
                  "name": "remove_images",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Captions all images at the specified URL, adding 'Image [idx]: [caption]' as an alt tag for those without one. This allows downstream LLMs to interact with the images in activities such as reasoning and summarizing.",
                    "pt_BR": "Adiciona legendas a todas as imagens na URL especificada, adicionando 'Imagem [idx]: [legenda]' como uma tag alt para aquelas que não têm uma. Isso permite que os modelos LLM inferiores interajam com as imagens em atividades como raciocínio e resumo.",
                    "zh_Hans": "为指定 URL 上的所有图像添加标题，为没有标题的图像添加“Image [idx]: [caption]”作为 alt 标签，以支持下游模型的图像交互。"
                  },
                  "label": {
                    "en_US": "Image caption",
                    "pt_BR": "Legenda da imagem",
                    "zh_Hans": "图片说明"
                  },
                  "llm_description": "Captions all images at the specified URL",
                  "max": null,
                  "min": null,
                  "name": "image_caption",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "A \"Buttons & Links\" section will be created at the end. This helps the downstream LLMs or web agents navigating the page or take further actions.",
                    "pt_BR": "Um \"Botões & Links\" section will be created at the end. This helps the downstream LLMs or web agents navigating the page or take further actions.",
                    "zh_Hans": "末尾将添加“按钮和链接”部分，方便下游模型或网络代理做页面导航或执行进一步操作。"
                  },
                  "label": {
                    "en_US": "Gather all links at the end",
                    "pt_BR": "Coletar todos os links ao final",
                    "zh_Hans": "将所有链接集中到最后"
                  },
                  "llm_description": "Gather all links at the end",
                  "max": null,
                  "min": null,
                  "name": "gather_all_links_at_the_end",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "An \"Images\" section will be created at the end. This gives the downstream LLMs an overview of all visuals on the page, which may improve reasoning.",
                    "pt_BR": "Um \"Imagens\" section will be created at the end. This gives the downstream LLMs an overview of all visuals on the page, which may improve reasoning.",
                    "zh_Hans": "末尾会新增“图片”部分，方便下游模型全面了解页面的视觉内容，提升推理效果。"
                  },
                  "label": {
                    "en_US": "Gather all images at the end",
                    "pt_BR": "Coletar todas as imagens ao final",
                    "zh_Hans": "将所有图片集中到最后"
                  },
                  "llm_description": "Gather all images at the end",
                  "max": null,
                  "min": null,
                  "name": "gather_all_images_at_the_end",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Use proxy to access URLs",
                    "pt_BR": "Use proxy to access URLs",
                    "zh_Hans": "利用代理访问 URL"
                  },
                  "label": {
                    "en_US": "Proxy server",
                    "pt_BR": "Servidor de proxy",
                    "zh_Hans": "代理服务器"
                  },
                  "llm_description": "Use proxy to access URLs",
                  "max": null,
                  "min": null,
                  "name": "proxy_server",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Bypass the Cache",
                    "pt_BR": "Ignorar o cache",
                    "zh_Hans": "是否绕过缓存"
                  },
                  "label": {
                    "en_US": "Bypass the Cache",
                    "pt_BR": "Ignorar o cache",
                    "zh_Hans": "绕过缓存"
                  },
                  "llm_description": "bypass the cache",
                  "max": null,
                  "min": null,
                  "name": "no_cache",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "When enabled, request results won't be cached on jina servers.",
                    "zh_Hans": "启用后，请求结果将不会被缓存在 jina 服务器上。"
                  },
                  "label": {
                    "en_US": "Do Not Cache/Track",
                    "zh_Hans": "请勿缓存/追踪"
                  },
                  "llm_description": "Do Not Cache/Track",
                  "max": null,
                  "min": null,
                  "name": "no_cache_track",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Enable summary for the output",
                    "pt_BR": "Habilitar resumo para a saída",
                    "zh_Hans": "为输出启用摘要"
                  },
                  "label": {
                    "en_US": "Enable summary",
                    "pt_BR": "Habilitar resumo",
                    "zh_Hans": "是否启用摘要"
                  },
                  "llm_description": "enable summary",
                  "max": null,
                  "min": null,
                  "name": "summary",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": 3,
                  "form": "form",
                  "human_description": {
                    "en_US": "Number of times to retry the request if it fails",
                    "pt_BR": "Número de vezes para repetir a solicitação se falhar",
                    "zh_Hans": "请求失败时重试的次数"
                  },
                  "label": {
                    "en_US": "Retry",
                    "pt_BR": "Repetir",
                    "zh_Hans": "重试"
                  },
                  "llm_description": "Number of times to retry the request if it fails",
                  "max": null,
                  "min": null,
                  "name": "max_retries",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Search on the public web of a given query and return the top results as LLM-friendly markdown.",
                  "pt_BR": "Procurar na web pública de uma consulta fornecida e retornar os melhores resultados como markdown para LLMs.",
                  "zh_Hans": "针对给定的查询在互联网上进行搜索，并以适合大模型处理的 Markdown 格式返回最相关的结果。"
                },
                "llm": "A tool for searching results on the web for grounding. Input should be a simple question."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Search the web",
                  "pt_BR": "Search the web",
                  "zh_Hans": "联网搜索"
                },
                "name": "jina_search"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "used to find information on the web",
                    "pt_BR": "Usado para encontrar informações na web",
                    "zh_Hans": "在网络上搜索信息"
                  },
                  "label": {
                    "en_US": "Question (Query)",
                    "pt_BR": "Pergunta (Consulta)",
                    "zh_Hans": "查询"
                  },
                  "llm_description": "Pergunta simples para fazer na web",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Captions all images at the specified URL, adding 'Image [idx]: [caption]' as an alt tag for those without one. This allows downstream LLMs to interact with the images in activities such as reasoning and summarizing.",
                    "pt_BR": "Captions all images at the specified URL, adding 'Image [idx]: [caption]' as an alt tag for those without one. This allows downstream LLMs to interact with the images in activities such as reasoning and summarizing.",
                    "zh_Hans": "为指定 URL 上的所有图像添加标题，为没有标题的图像添加“Image [idx]: [caption]”作为 alt 标签，以支持下游模型的图像交互。"
                  },
                  "label": {
                    "en_US": "Image caption",
                    "pt_BR": "Legenda da imagem",
                    "zh_Hans": "图片说明"
                  },
                  "llm_description": "Captions all images at the specified URL",
                  "max": null,
                  "min": null,
                  "name": "image_caption",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "A \"Buttons & Links\" section will be created at the end. This helps the downstream LLMs or web agents navigating the page or take further actions.",
                    "pt_BR": "Um \"Botão & Links\" seção será criada no final. Isso ajuda os LLMs ou agentes da web navegando pela página ou executar ações adicionais.",
                    "zh_Hans": "末尾将添加“按钮和链接”部分，汇总页面上的所有链接。方便下游模型或网络代理做页面导航或执行进一步操作。"
                  },
                  "label": {
                    "en_US": "Gather all links at the end",
                    "pt_BR": "Coletar todos os links ao final",
                    "zh_Hans": "将所有链接集中到最后"
                  },
                  "llm_description": "Gather all links at the end",
                  "max": null,
                  "min": null,
                  "name": "gather_all_links_at_the_end",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "An \"Images\" section will be created at the end. This gives the downstream LLMs an overview of all visuals on the page, which may improve reasoning.",
                    "pt_BR": "Um \"Imagens\" seção será criada no final. Isso fornece uma visão geral de todas as imagens na página para os LLMs, que pode melhorar a razão.",
                    "zh_Hans": "末尾会新增“图片”部分，汇总页面上的所有图片。方便下游模型概览页面的视觉内容，提升推理效果。"
                  },
                  "label": {
                    "en_US": "Gather all images at the end",
                    "pt_BR": "Coletar todas as imagens ao final",
                    "zh_Hans": "将所有图片集中到最后"
                  },
                  "llm_description": "Gather all images at the end",
                  "max": null,
                  "min": null,
                  "name": "gather_all_images_at_the_end",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Use proxy to access URLs",
                    "pt_BR": "Usar proxy para acessar URLs",
                    "zh_Hans": "利用代理访问 URL"
                  },
                  "label": {
                    "en_US": "Proxy server",
                    "pt_BR": "Servidor de proxy",
                    "zh_Hans": "代理服务器"
                  },
                  "llm_description": "Use proxy to access URLs",
                  "max": null,
                  "min": null,
                  "name": "proxy_server",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Bypass the Cache",
                    "pt_BR": "Ignorar o cache",
                    "zh_Hans": "是否绕过缓存"
                  },
                  "label": {
                    "en_US": "Bypass the Cache",
                    "pt_BR": "Ignorar o cache",
                    "zh_Hans": "是否绕过缓存"
                  },
                  "llm_description": "bypass the cache",
                  "max": null,
                  "min": null,
                  "name": "no_cache",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": 3,
                  "form": "form",
                  "human_description": {
                    "en_US": "Number of times to retry the request if it fails",
                    "pt_BR": "Número de vezes para repetir a solicitação se falhar",
                    "zh_Hans": "请求失败时重试的次数"
                  },
                  "label": {
                    "en_US": "Retry",
                    "pt_BR": "Repetir",
                    "zh_Hans": "重试"
                  },
                  "llm_description": "Number of times to retry the request if it fails",
                  "max": null,
                  "min": null,
                  "name": "max_retries",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-13T03:00:18Z",
        "version_updated_at": "2025-03-13T03:00:18Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Firecrawl API integration for web crawling and scraping.",
          "zh_Hans": "Firecrawl API 集成，用于网页爬取和数据抓取。"
        },
        "category": "tool",
        "created_at": "2024-12-30T13:25:03Z",
        "endpoint": {},
        "icon": "langgenius/packages/firecrawl/_assets/icon.svg",
        "index_id": "langgenius___firecrawl",
        "install_count": 14302,
        "introduction": "## Overview\n\n**Firecrawl** is a powerful API integration for web crawling and data scraping. It allows users to extract URLs, scrape website content, and retrieve structured data from web pages. With its modular tools, Firecrawl simplifies the process of gathering web data efficiently. You can now use it in your application workflows for automated web data extraction and analysis.\n\n## Configuration\n\nTo set up Firecrawl, follow these steps:\n\n1. **Install Firecrawl Tool**\nAccess the Plugin Marketplace, locate the Firecrawl tool, and install it.\n\n2. **Apply for a Firecrawl API Key**\nGo to the [Firecrawl API Keys](https://www.firecrawl.dev/app/api-keys) page, create a new API Key, and ensure your account has sufficient balance.\n\n3. **Authorize Firecrawl**\nNavigate to **Plugins > Firecrawl > To Authorize** in Dify, and input your API Key to enable the tool.\n\n![](./_assets/firecrawl-01.png)\n\n## Tool Features\n\nThe Firecrawl tool provides four actions for web crawling and scraping:\n\n### Crawl Job\n\nRetrieve scraping results based on a Job ID or cancel an ongoing scraping task. This is ideal for managing and monitoring your workflows.\n\n<img src=\"./_assets/firecrawl-02.png\" width=\"400\" />\n\n### Crawl\n\nPerform a recursive crawl of a website's subdomains to gather content. Perfect for extracting extensive datasets from interconnected pages.\n\n<img src=\"./_assets/firecrawl-03.png\" width=\"400\" />\n\n### Map\n\nWhen using the **Map** action to generate a complete map of all URLs present on a site, you need to configure the following input parameters.\n\n<img src=\"./_assets/firecrawl-04.png\" width=\"400\" />\n\n### Scrape\n\nConvert any URL into clean, structured data, transforming raw HTML into actionable insights.\n\n<img src=\"./_assets/firecrawl-05.png\" width=\"400\" />\n\n## Usage\n\nFirecrawl can be seamlessly integrated into both **Chatflow / Workflow Apps** and **Agent Apps**.\n\n### Chatflow / Workflow Apps\n\nIntegrate Firecrawl into your pipeline by following these steps:\n\n1. Add the Firecrawl node to the Chatflow or Workflow pipeline.\n2. Please select one of Firecrawl's actions (e.g., Map, Crawl, Scrape) and insert it into the pipeline.\n3. Define the input variables and UI elements for your use case.\n4. Execute the pipeline to trigger the Firecrawl nodes sequentially and crawl web page data.\n\n![](./_assets/firecrawl-06.png)\n\n### Agent Apps\n\nAdd the Firecrawl tool in the Agent application, then send the URL. The tool will help to scrape the online content, so the LLM will have the ability to get the latest online data.\n\n1. Add the Firecrawl tool to the Agent application.\n2. Input a URL in the chat, and Firecrawl will scrape the content from the specified webpage.\n3. The extracted data is processed and made accessible to the LLM, enabling the app to fetch and analyze the latest online information.\n\n![](./_assets/firecrawl-07.png)\n",
        "label": {
          "en_US": "Firecrawl"
        },
        "latest_package_identifier": "langgenius/firecrawl:0.0.3@d668b3ad841e8bb27f735a8500568e44f9673156d1d4db72c304d0437bf80fd7",
        "latest_version": "0.0.3",
        "model": {},
        "name": "firecrawl",
        "org": "langgenius",
        "plugin_id": "langgenius/firecrawl",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/firecrawl.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "utilities"
          },
          {
            "name": "search"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "Firecrawl server's Base URL",
                "zh_Hans": "Firecrawl服务器的API URL"
              },
              "name": "base_url",
              "options": null,
              "placeholder": {
                "en_US": "https://api.firecrawl.dev"
              },
              "required": false,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "Firecrawl API Key",
                "zh_Hans": "Firecrawl API 密钥"
              },
              "name": "firecrawl_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Firecrawl API key",
                "zh_Hans": "请输入您的 Firecrawl API 密钥，如果是自托管版本，可以随意填写密钥"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://www.firecrawl.dev/account"
            }
          ],
          "identity": {
            "author": "Richards_Tu",
            "description": {
              "en_US": "Firecrawl API integration for web crawling and scraping.",
              "zh_Hans": "Firecrawl API 集成，用于网页爬取和数据抓取。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Firecrawl"
            },
            "name": "firecrawl",
            "tags": [
              "search",
              "utilities"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Retrieve the scraping results based on the job ID, or cancel the scraping task.",
                  "zh_Hans": "根据爬取任务ID获取爬取结果，或者取消爬取任务"
                },
                "llm": "Retrieve the scraping results based on the job ID, or cancel the scraping task."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "hjlarry",
                "label": {
                  "en_US": "Crawl Job",
                  "zh_Hans": "爬取任务处理"
                },
                "name": "crawl_job"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Set wait_for_results to false in the Crawl tool can get the job ID.",
                    "zh_Hans": "在深度爬取工具中将等待爬取结果设置为否可以获取Job ID。"
                  },
                  "label": {
                    "en_US": "Job ID"
                  },
                  "llm_description": "Set wait_for_results to false in the Crawl tool can get the job ID.",
                  "max": null,
                  "min": null,
                  "name": "job_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "choose the operation to perform. `get` is for getting the crawl status, `cancel` is for cancelling the crawl job.",
                    "zh_Hans": "选择操作类型。"
                  },
                  "label": {
                    "en_US": "operation",
                    "zh_Hans": "操作"
                  },
                  "llm_description": "choose the operation to perform. `get` is for getting the crawl status, `cancel` is for cancelling the crawl job.",
                  "max": null,
                  "min": null,
                  "name": "operation",
                  "options": [
                    {
                      "label": {
                        "en_US": "get crawl status"
                      },
                      "value": "get"
                    },
                    {
                      "label": {
                        "en_US": "cancel crawl job"
                      },
                      "value": "cancel"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Recursively search through a urls subdomains, and gather the content.",
                  "zh_Hans": "递归爬取一个网址的子域名，并收集内容。"
                },
                "llm": "This tool initiates a web crawl to extract data from a specified URL. It allows configuring crawler options such as including or excluding URL patterns, generating alt text for images using LLMs (paid plan required), limiting the maximum number of pages to crawl, and returning only the main content of the page. The tool can return either a list of crawled documents or a list of URLs based on the provided options."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Richards_Tu",
                "label": {
                  "en_US": "Crawl",
                  "zh_Hans": "深度爬取"
                },
                "name": "crawl"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The base URL to start crawling from.",
                    "zh_Hans": "要爬取网站的起始URL。"
                  },
                  "label": {
                    "en_US": "Start URL",
                    "zh_Hans": "起始URL"
                  },
                  "llm_description": "The URL of the website that needs to be crawled. This is a required parameter.",
                  "max": null,
                  "min": null,
                  "name": "url",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "If you choose not to wait, it will directly return a job ID. You can use this job ID to check the crawling results or cancel the crawling task, which is usually very useful for a large-scale crawling task.",
                    "zh_Hans": "如果选择不等待，则会直接返回一个job_id，可以通过job_id查询爬取结果或取消爬取任务，这通常对于一个大型爬取任务来说非常有用。"
                  },
                  "label": {
                    "en_US": "Wait For Results",
                    "zh_Hans": "等待爬取结果"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "wait_for_results",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Pages matching these patterns will be skipped. Example: blog/*, about/*",
                    "zh_Hans": "匹配这些模式的页面将被跳过。示例：blog/*, about/*"
                  },
                  "label": {
                    "en_US": "URL patterns to exclude",
                    "zh_Hans": "要排除的URL模式"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "excludePaths",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Only pages matching these patterns will be crawled. Example: blog/*, about/*",
                    "zh_Hans": "只有与这些模式匹配的页面才会被爬取。示例：blog/*, about/*"
                  },
                  "label": {
                    "en_US": "URL patterns to include",
                    "zh_Hans": "要包含的URL模式"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "includePaths",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 2,
                  "form": "form",
                  "human_description": {
                    "en_US": "Maximum depth to crawl relative to the entered URL. A maxDepth of 0 scrapes only the entered URL. A maxDepth of 1 scrapes the entered URL and all pages one level deep. A maxDepth of 2 scrapes the entered URL and all pages up to two levels deep. Higher values follow the same pattern.",
                    "zh_Hans": "相对于输入的URL，爬取的最大深度。maxDepth为0时，仅抓取输入的URL。maxDepth为1时，抓取输入的URL以及所有一级深层页面。maxDepth为2时，抓取输入的URL以及所有两级深层页面。更高值遵循相同模式。"
                  },
                  "label": {
                    "en_US": "Maximum crawl depth",
                    "zh_Hans": "爬取深度"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": 0,
                  "name": "maxDepth",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "Ignore the website sitemap when crawling.",
                    "zh_Hans": "爬取时忽略网站站点地图。"
                  },
                  "label": {
                    "en_US": "ignore Sitemap",
                    "zh_Hans": "忽略站点地图"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "ignoreSitemap",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": 5,
                  "form": "form",
                  "human_description": {
                    "en_US": "Specify the maximum number of pages to crawl. The crawler will stop after reaching this limit.",
                    "zh_Hans": "指定要爬取的最大页面数。爬虫将在达到此限制后停止。"
                  },
                  "label": {
                    "en_US": "Maximum pages to crawl",
                    "zh_Hans": "最大爬取页面数"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": 1,
                  "name": "limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Enables the crawler to navigate from a specific URL to previously linked pages. For instance, from 'example.com/product/123' back to 'example.com/product'",
                    "zh_Hans": "使爬虫能够从特定URL导航到之前链接的页面。例如，从'example.com/product/123'返回到'example.com/product'"
                  },
                  "label": {
                    "en_US": "allow Backward Crawling",
                    "zh_Hans": "允许向后爬取"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "allowBackwardLinks",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Allows the crawler to follow links to external websites."
                  },
                  "label": {
                    "en_US": "allow External Content Links",
                    "zh_Hans": "允许爬取外链"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "allowExternalLinks",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The URL to send the webhook to. This will trigger for crawl started (crawl.started) ,every page crawled (crawl.page) and when the crawl is completed (crawl.completed or crawl.failed). The response will be the same as the /scrape endpoint.",
                    "zh_Hans": "发送Webhook的URL。这将在开始爬取（crawl.started）、每爬取一个页面（crawl.page）以及爬取完成（crawl.completed或crawl.failed）时触发。响应将与/scrape端点相同。"
                  },
                  "label": {
                    "en_US": "webhook"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "webhook",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Formats to include in the output. Available options: markdown, html, rawHtml, links, screenshot",
                    "zh_Hans": "输出中应包含的格式。可以填入: markdown, html, rawHtml, links, screenshot"
                  },
                  "label": {
                    "en_US": "Formats",
                    "zh_Hans": "结果的格式"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "formats",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Headers to send with the request. Can be used to send cookies, user-agent, etc. Example: {\"cookies\": \"testcookies\"}",
                    "zh_Hans": "随请求发送的头部。可以用来发送cookies、用户代理等。示例：{\"cookies\": \"testcookies\"}"
                  },
                  "label": {
                    "en_US": "headers",
                    "zh_Hans": "请求头"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "headers",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Only include tags, classes and ids from the page in the final output. Use comma separated values. Example: script, .ad, #footer",
                    "zh_Hans": "仅在最终输出中包含HTML页面的这些标签，可以通过标签名、类或ID来设定，使用逗号分隔值。示例：script, .ad, #footer"
                  },
                  "label": {
                    "en_US": "Include Tags",
                    "zh_Hans": "仅抓取这些标签"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "includeTags",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Tags, classes and ids to remove from the page. Use comma separated values. Example: script, .ad, #footer",
                    "zh_Hans": "要在最终输出中移除HTML页面的这些标签，可以通过标签名、类或ID来设定，使用逗号分隔值。示例：script, .ad, #footer"
                  },
                  "label": {
                    "en_US": "Exclude Tags",
                    "zh_Hans": "要移除这些标签"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "excludeTags",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Only return the main content of the page excluding headers, navs, footers, etc.",
                    "zh_Hans": "只返回页面的主要内容，不包括头部、导航栏、尾部等。"
                  },
                  "label": {
                    "en_US": "only Main Content",
                    "zh_Hans": "仅抓取主要内容"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "onlyMainContent",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Wait x amount of milliseconds for the page to load to fetch content.",
                    "zh_Hans": "等待x毫秒以使页面加载并获取内容。"
                  },
                  "label": {
                    "en_US": "wait For",
                    "zh_Hans": "等待时间"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": 0,
                  "name": "waitFor",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Input a website and get all the urls on the website - extremly fast",
                  "zh_Hans": "输入一个网站，快速获取网站上的所有网址。"
                },
                "llm": "Input a website and get all the urls on the website - extremly fast"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "hjlarry",
                "label": {
                  "en_US": "Map",
                  "zh_Hans": "地图式快爬"
                },
                "name": "map"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The base URL to start crawling from.",
                    "zh_Hans": "要爬取网站的起始URL。"
                  },
                  "label": {
                    "en_US": "Start URL",
                    "zh_Hans": "起始URL"
                  },
                  "llm_description": "The URL of the website that needs to be crawled. This is a required parameter.",
                  "max": null,
                  "min": null,
                  "name": "url",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Search query to use for mapping. During the Alpha phase, the 'smart' part of the search functionality is limited to 100 search results. However, if map finds more results, there is no limit applied.",
                    "zh_Hans": "用于映射的搜索查询。在Alpha阶段，搜索功能的“智能”部分限制为最多100个搜索结果。然而，如果地图找到了更多结果，则不施加任何限制。"
                  },
                  "label": {
                    "en_US": "search",
                    "zh_Hans": "搜索查询"
                  },
                  "llm_description": "Search query to use for mapping. During the Alpha phase, the 'smart' part of the search functionality is limited to 100 search results. However, if map finds more results, there is no limit applied.",
                  "max": null,
                  "min": null,
                  "name": "search",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Ignore the website sitemap when crawling.",
                    "zh_Hans": "爬取时忽略网站站点地图。"
                  },
                  "label": {
                    "en_US": "ignore Sitemap",
                    "zh_Hans": "忽略站点地图"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "ignoreSitemap",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "include Subdomains.",
                    "zh_Hans": "包含子域名。"
                  },
                  "label": {
                    "en_US": "include Subdomains",
                    "zh_Hans": "包含子域名"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "includeSubdomains",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": 5000,
                  "form": "form",
                  "human_description": {
                    "en_US": "maximum results.",
                    "zh_Hans": "最大结果数量。"
                  },
                  "label": {
                    "en_US": "Maximum results",
                    "zh_Hans": "最大结果数量"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": 0,
                  "name": "limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Turn any url into clean data.",
                  "zh_Hans": "将任何网址转换为干净的数据。"
                },
                "llm": "This tool is designed to scrape URL and output the content in Markdown format."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "ahasasjeb",
                "label": {
                  "en_US": "Scrape",
                  "zh_Hans": "单页面抓取"
                },
                "name": "scrape"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The URL of the website to scrape and extract data from.",
                    "zh_Hans": "要抓取并提取数据的网站URL。"
                  },
                  "label": {
                    "en_US": "URL to scrape",
                    "zh_Hans": "要抓取的URL"
                  },
                  "llm_description": "The URL of the website that needs to be crawled. This is a required parameter.",
                  "max": null,
                  "min": null,
                  "name": "url",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Formats to include in the output. Available options: markdown, html, rawHtml, links, screenshot, extract, screenshot@fullPage",
                    "zh_Hans": "输出中应包含的格式。可以填入: markdown, html, rawHtml, links, screenshot, extract, screenshot@fullPage"
                  },
                  "label": {
                    "en_US": "Formats",
                    "zh_Hans": "结果的格式"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "formats",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Only return the main content of the page excluding headers, navs, footers, etc.",
                    "zh_Hans": "只返回页面的主要内容，不包括头部、导航栏、尾部等。"
                  },
                  "label": {
                    "en_US": "only Main Content",
                    "zh_Hans": "仅抓取主要内容"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "onlyMainContent",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Only include tags, classes and ids from the page in the final output. Use comma separated values. Example: script, .ad, #footer",
                    "zh_Hans": "仅在最终输出中包含HTML页面的这些标签，可以通过标签名、类或ID来设定，使用逗号分隔值。示例：script, .ad, #footer"
                  },
                  "label": {
                    "en_US": "Include Tags",
                    "zh_Hans": "仅抓取这些标签"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "includeTags",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Tags, classes and ids to remove from the page. Use comma separated values. Example: script, .ad, #footer\n",
                    "zh_Hans": "要在最终输出中移除HTML页面的这些标签，可以通过标签名、类或ID来设定，使用逗号分隔值。示例：script, .ad, #footer\n"
                  },
                  "label": {
                    "en_US": "Exclude Tags",
                    "zh_Hans": "要移除这些标签"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "excludeTags",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Headers to send with the request. Can be used to send cookies, user-agent, etc. Example: {\"cookies\": \"testcookies\"}",
                    "zh_Hans": "随请求发送的头部。可以用来发送cookies、用户代理等。示例：{\"cookies\": \"testcookies\"}"
                  },
                  "label": {
                    "en_US": "headers",
                    "zh_Hans": "请求头"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "headers",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 0,
                  "form": "form",
                  "human_description": {
                    "en_US": "Wait x amount of milliseconds for the page to load to fetch content.",
                    "zh_Hans": "等待x毫秒以使页面加载并获取内容。"
                  },
                  "label": {
                    "en_US": "wait For",
                    "zh_Hans": "等待时间"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": 0,
                  "name": "waitFor",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 30000,
                  "form": "form",
                  "human_description": {
                    "en_US": "Timeout in milliseconds for the request.",
                    "zh_Hans": "请求的超时时间（以毫秒为单位）。"
                  },
                  "label": {
                    "en_US": "Timeout"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": 0,
                  "name": "timeout",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The schema for the data to be extracted. Example: {\n    \"type\": \"object\",\n    \"properties\": {\"company_mission\": {\"type\": \"string\"}},\n    \"required\": [\"company_mission\"]\n}\n",
                    "zh_Hans": "使用该结构去提取，示例：{\n     \"type\": \"object\",\n     \"properties\": {\"company_mission\": {\"type\": \"string\"}},\n     \"required\": [\"company_mission\"]\n }\n"
                  },
                  "label": {
                    "en_US": "Extractor Schema",
                    "zh_Hans": "提取时的结构"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "schema",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The system prompt to use for the extraction.",
                    "zh_Hans": "用于提取的系统提示。"
                  },
                  "label": {
                    "en_US": "Extractor System Prompt",
                    "zh_Hans": "提取时的系统提示词"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "systemPrompt",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The prompt to use for the extraction without a schema.",
                    "zh_Hans": "用于无schema时提取的提示词"
                  },
                  "label": {
                    "en_US": "Extractor Prompt",
                    "zh_Hans": "提取时的提示词"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "prompt",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:06:46Z",
        "version_updated_at": "2025-02-17T07:06:46Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "DALL-E art",
          "pt_BR": "DALL-E art",
          "zh_Hans": "DALL-E 绘画"
        },
        "category": "tool",
        "created_at": "2024-11-27T10:53:55Z",
        "endpoint": {},
        "icon": "langgenius/packages/dalle/_assets/icon.png",
        "index_id": "langgenius___dalle",
        "install_count": 14130,
        "introduction": "# DALL-E\r\n\r\n## Overview\r\n\r\nDALL-E is an AI image generator developed by OpenAI that generates images based on text prompts. Dify has integrated the DALL-E tool, and the following are the steps to configure and use the DALL-E tool in Dify.\r\n\r\n## Configure\r\n\r\n### 1. Apply for Dall-E API Key\r\n\r\nPlease apply for an API Key on the [OpenAI Platform](https://platform.openai.com/).\r\n\r\n### 2. Get Dall-E tools from Plugin Marketplace\r\n\r\nThe Dall-E tools could be found at the Plugin Marketplace, please install it first.\r\n\r\n### 3. Fill in the configuration in Dify\r\n\r\nOn the Dify navigation page, click `Tools > DALL-E > Authorize` and fill in the API Key.\r\n\r\n**Note:** Base URL and Organization ID are optional. The Organization IDs can be found on your [Organization settings](https://platform.openai.com/settings/organization/general) page.\r\n\r\n![DALL-E Configuration](./_assets/dalle_1.PNG)\r\n\r\n### 4. Use the tool\r\n\r\nYou can use the Dall-E tool in the following application types:\r\n\r\n#### Chatflow / Workflow applications\r\n\r\n![Chatflow/Workflow Application](./_assets/dalle_2.PNG)\r\n\r\nBoth Chatflow and Workflow applications support the `DALL-E` tool node. After adding it, you need to fill in the \"Input Variables → Prompt\" in the node with variables to reference the user's input prompt or the content generated by the previous node. Finally, use the variable to reference the image output by `DALL-E` in the \"End\" node.\r\n\r\n#### Agent applications\r\n\r\n![Agent Application](./_assets/dalle_3.PNG)\r\n\r\nAdd the Dall-E tool in the Agent application, then send a picture description in the dialog box to call the tool to generate an AI image.\r\n",
        "label": {
          "en_US": "DALL-E",
          "pt_BR": "DALL-E",
          "zh_Hans": "DALL-E 绘画"
        },
        "latest_package_identifier": "langgenius/dalle:0.0.4@c0d3625ef2fe13b8e8f6125fb4335822904d382e9c65e592f0d44dca037e3f6a",
        "latest_version": "0.0.4",
        "model": {},
        "name": "dalle",
        "org": "langgenius",
        "plugin_id": "langgenius/dalle",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/dalle.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "image"
          },
          {
            "name": "productivity"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "OpenAI API key",
                "pt_BR": "OpenAI API key",
                "zh_Hans": "OpenAI API key"
              },
              "name": "openai_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your OpenAI API key",
                "pt_BR": "Please input your OpenAI API key",
                "zh_Hans": "请输入你的 OpenAI API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "OpenAI base URL",
                "pt_BR": "OpenAI base URL",
                "zh_Hans": "OpenAI base URL"
              },
              "name": "openai_base_url",
              "options": null,
              "placeholder": {
                "en_US": "Please input your OpenAI base URL",
                "pt_BR": "Please input your OpenAI base URL",
                "zh_Hans": "请输入你的 OpenAI base URL"
              },
              "required": false,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "OpenAI organization ID",
                "pt_BR": "OpenAI organization ID",
                "zh_Hans": "OpenAI organization ID"
              },
              "name": "openai_organization_id",
              "options": null,
              "placeholder": {
                "en_US": "Please input your OpenAI organization ID",
                "pt_BR": "Please input your OpenAI organization ID",
                "zh_Hans": "请输入你的 OpenAI organization ID"
              },
              "required": false,
              "scope": null,
              "type": "text-input",
              "url": null
            }
          ],
          "identity": {
            "author": "langgenius",
            "description": {
              "en_US": "DALL-E art",
              "pt_BR": "DALL-E art",
              "zh_Hans": "DALL-E 绘画"
            },
            "icon": "icon.png",
            "label": {
              "en_US": "DALL-E",
              "pt_BR": "DALL-E",
              "zh_Hans": "DALL-E 绘画"
            },
            "name": "dalle",
            "tags": [
              "image",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "DALL-E is a text to image tool",
                  "pt_BR": "DALL-E is a text to image tool",
                  "zh_Hans": "DALL-E 是一个文本到图像的工具"
                },
                "llm": "DALL-E is a tool used to generate images from text"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "DALL-E 2",
                  "zh_Hans": "DALL-E 2 绘画"
                },
                "name": "dalle2"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Image prompt, you can check the official documentation of DallE 2",
                    "pt_BR": "Image prompt, you can check the official documentation of DallE 2",
                    "zh_Hans": "图像提示词，您可以查看 DallE 2 的官方文档"
                  },
                  "label": {
                    "en_US": "Prompt",
                    "pt_BR": "Prompt",
                    "zh_Hans": "提示词"
                  },
                  "llm_description": "Image prompt of DallE 2, you should describe the image you want to generate as a list of words as possible as detailed",
                  "max": null,
                  "min": null,
                  "name": "prompt",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "large",
                  "form": "form",
                  "human_description": {
                    "en_US": "used for selecting the image size",
                    "pt_BR": "used for selecting the image size",
                    "zh_Hans": "用于选择图像大小"
                  },
                  "label": {
                    "en_US": "Image size",
                    "pt_BR": "Image size",
                    "zh_Hans": "图像大小"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "size",
                  "options": [
                    {
                      "label": {
                        "en_US": "Small(256x256)",
                        "pt_BR": "Small(256x256)",
                        "zh_Hans": "小(256x256)"
                      },
                      "value": "small"
                    },
                    {
                      "label": {
                        "en_US": "Medium(512x512)",
                        "pt_BR": "Medium(512x512)",
                        "zh_Hans": "中(512x512)"
                      },
                      "value": "medium"
                    },
                    {
                      "label": {
                        "en_US": "Large(1024x1024)",
                        "pt_BR": "Large(1024x1024)",
                        "zh_Hans": "大(1024x1024)"
                      },
                      "value": "large"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 1,
                  "form": "form",
                  "human_description": {
                    "en_US": "used for selecting the number of images",
                    "pt_BR": "used for selecting the number of images",
                    "zh_Hans": "用于选择图像数量"
                  },
                  "label": {
                    "en_US": "Number of images",
                    "pt_BR": "Number of images",
                    "zh_Hans": "图像数量"
                  },
                  "llm_description": "",
                  "max": 10,
                  "min": 1,
                  "name": "n",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "DALL-E is a text to image tool",
                  "pt_BR": "DALL-E is a text to image tool",
                  "zh_Hans": "DALL-E 是一个文本到图像的工具"
                },
                "llm": "DALL-E is a tool used to generate images from text"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "DALL-E 3",
                  "pt_BR": "DALL-E 3",
                  "zh_Hans": "DALL-E 3 绘画"
                },
                "name": "dalle3"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Image prompt, you can check the official documentation of DallE 3",
                    "pt_BR": "Image prompt, you can check the official documentation of DallE 3",
                    "zh_Hans": "图像提示词，您可以查看 DallE 3 的官方文档"
                  },
                  "label": {
                    "en_US": "Prompt",
                    "pt_BR": "Prompt",
                    "zh_Hans": "提示词"
                  },
                  "llm_description": "Image prompt of DallE 3, you should describe the image you want to generate as a list of words as possible as detailed",
                  "max": null,
                  "min": null,
                  "name": "prompt",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "square",
                  "form": "form",
                  "human_description": {
                    "en_US": "selecting the image size",
                    "pt_BR": "selecting the image size",
                    "zh_Hans": "选择图像大小"
                  },
                  "label": {
                    "en_US": "Image size",
                    "pt_BR": "Image size",
                    "zh_Hans": "图像大小"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "size",
                  "options": [
                    {
                      "label": {
                        "en_US": "Squre(1024x1024)",
                        "pt_BR": "Squre(1024x1024)",
                        "zh_Hans": "方(1024x1024)"
                      },
                      "value": "square"
                    },
                    {
                      "label": {
                        "en_US": "Vertical(1024x1792)",
                        "pt_BR": "Vertical(1024x1792)",
                        "zh_Hans": "竖屏(1024x1792)"
                      },
                      "value": "vertical"
                    },
                    {
                      "label": {
                        "en_US": "Horizontal(1792x1024)",
                        "pt_BR": "Horizontal(1792x1024)",
                        "zh_Hans": "横屏(1792x1024)"
                      },
                      "value": "horizontal"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 1,
                  "form": "form",
                  "human_description": {
                    "en_US": "selecting the number of images",
                    "pt_BR": "selecting the number of images",
                    "zh_Hans": "选择图像数量"
                  },
                  "label": {
                    "en_US": "Number of images",
                    "pt_BR": "Number of images",
                    "zh_Hans": "图像数量"
                  },
                  "llm_description": "",
                  "max": 1,
                  "min": 1,
                  "name": "n",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "standard",
                  "form": "form",
                  "human_description": {
                    "en_US": "selecting the image quality",
                    "pt_BR": "selecting the image quality",
                    "zh_Hans": "选择图像质量"
                  },
                  "label": {
                    "en_US": "Image quality",
                    "pt_BR": "Image quality",
                    "zh_Hans": "图像质量"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "quality",
                  "options": [
                    {
                      "label": {
                        "en_US": "Standard",
                        "pt_BR": "Standard",
                        "zh_Hans": "标准"
                      },
                      "value": "standard"
                    },
                    {
                      "label": {
                        "en_US": "HD",
                        "pt_BR": "HD",
                        "zh_Hans": "高清"
                      },
                      "value": "hd"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "vivid",
                  "form": "form",
                  "human_description": {
                    "en_US": "selecting the image style",
                    "pt_BR": "selecting the image style",
                    "zh_Hans": "选择图像风格"
                  },
                  "label": {
                    "en_US": "Image style",
                    "pt_BR": "Image style",
                    "zh_Hans": "图像风格"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "style",
                  "options": [
                    {
                      "label": {
                        "en_US": "Vivid",
                        "pt_BR": "Vivid",
                        "zh_Hans": "生动"
                      },
                      "value": "vivid"
                    },
                    {
                      "label": {
                        "en_US": "Natural",
                        "pt_BR": "Natural",
                        "zh_Hans": "自然"
                      },
                      "value": "natural"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:13:15Z",
        "version_updated_at": "2025-02-17T07:13:15Z"
      },
      {
        "agent_strategy": {
          "identity": {
            "author": "svcvit",
            "description": {
              "en_US": "Store conversation context information for multi-turn dialogue memory processing",
              "zh_Hans": "存储对话上下文信息，用于多轮对话记忆处理"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Dialogue",
              "zh_Hans": "对话"
            },
            "name": "agent",
            "tags": []
          },
          "strategies": [
            {
              "description": {
                "en_US": "A dialogue strategy for information collection through multi-turn conversations",
                "zh_Hans": "通过多轮对话收集信息的对话策略"
              },
              "identity": {
                "author": "Dify",
                "label": {
                  "en_US": "InformationCollection",
                  "zh_Hans": "信息收集"
                },
                "name": "TOD"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "label": {
                    "en_US": "Model",
                    "zh_Hans": "模型"
                  },
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": "llm",
                  "template": null,
                  "type": "model-selector"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "label": {
                    "en_US": "Information Schema",
                    "zh_Hans": "信息集合 Schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "information_schema",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "label": {
                    "en_US": "User Query",
                    "zh_Hans": "用户输入"
                  },
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "label": {
                    "en_US": "Storage Key",
                    "zh_Hans": "存储键值"
                  },
                  "max": null,
                  "min": null,
                  "name": "storage_key",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "en_US": "A dialogue strategy for managing multi-turn conversations with context awareness",
                "zh_Hans": "一个支持上下文感知的多轮对话策略"
              },
              "identity": {
                "author": "Dify",
                "label": {
                  "en_US": "MultiTurnConversation",
                  "zh_Hans": "多轮对话"
                },
                "name": "MTD"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "label": {
                    "en_US": "Model",
                    "zh_Hans": "模型"
                  },
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": "llm",
                  "template": null,
                  "type": "model-selector"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "label": {
                    "en_US": "Instruction",
                    "zh_Hans": "指令"
                  },
                  "max": null,
                  "min": null,
                  "name": "instruction",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "label": {
                    "en_US": "User Query",
                    "zh_Hans": "用户输入"
                  },
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "label": {
                    "en_US": "Storage Key",
                    "zh_Hans": "存储键值"
                  },
                  "max": null,
                  "min": null,
                  "name": "storage_key",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "badges": [],
        "brief": {
          "en_US": "An advanced dialogue agent optimized for conversational scenarios",
          "zh_Hans": "针对对话场景优化的Agent策略，例如：多轮对话、上下文理解、信息收集等"
        },
        "category": "agent-strategy",
        "created_at": "2025-03-03T11:03:47Z",
        "endpoint": {},
        "icon": "svcvit/packages/agent/_assets/icon.svg",
        "index_id": "svcvit___agent",
        "install_count": 14053,
        "introduction": "# Dialogue Agent\n\n**Author:** [svcvit](https://github.com/svcvit)\n**Version:** 0.0.3\n\n### Description\n\n![](./snapshots/tod.jpg)\n\n![](./snapshots/mtd.jpg)\n\nA powerful task-oriented dialogue agent that can collect information through structured conversations. It supports dynamic field validation, multi-field information extraction, and state management. The agent now includes two dialogue strategies: TOD (Task-Oriented Dialogue) for information collection and MTD (Multi-Turn Dialogue) for general conversations.\n\n### Features\n\n- Task-oriented dialogue management\n- Dynamic field validation\n- Multi-field information extraction\n- Conversation state persistence\n- Automatic answer validation\n- Context-aware information collection\n- Natural language interaction\n- Multiple dialogue strategies support (TOD & MTD)\n\n### Usage Guide\n\n#### Dialogue Strategies\n\nThe agent supports two dialogue strategies:\n\n1. **TOD (Task-Oriented Dialogue)**\n   - A dialogue strategy for structured information collection\n   - Suitable for form filling and information gathering scenarios\n   - Supports dynamic field validation and state management\n\n2. **MTD (Multi-Turn Dialogue)**\n   - A strategy for general multi-turn conversations\n   - Supports context awareness\n   - Suitable for open-ended dialogue scenarios\n\n#### TOD Strategy Parameters\n\n1. **information_schema** (Required)\n   - Type: string (JSON)\n   - Description: Schema defining the fields to collect\n   - Example:\n     ```json\n     {\n       \"fields\": [\n         {\n           \"name\": \"destination\",\n           \"question\": \"请问您想去哪里旅行？\",\n           \"required\": true\n         },\n         {\n           \"name\": \"duration\",\n           \"question\": \"您计划旅行多长时间？\",\n           \"required\": true\n         },\n         {\n           \"name\": \"budget\",\n           \"question\": \"您的预算大约是多少？\",\n           \"required\": true\n         }\n       ]\n     }\n     ```\n\n2. **query** (Required)\n   - Type: string\n   - Description: User's input text\n\n3. **model** (Required)\n   - Type: AgentModelConfig\n   - Description: LLM model configuration\n   - Example: Configuration for GPT or other LLM models\n\n4. **storage_key** (Required)\n   - Type: string\n   - Description: Unique key for storing conversation state\n   - Example: `\"conversation-123\"`\n\n#### MTD Strategy Parameters\n\n1. **instruction** (Required)\n   - Type: string\n   - Description: Dialogue instruction or system prompt\n   - Example: \n     ```\n      你是一个专业的医生。\n      - 问用户有什么不适症状\n      - 问用户最近有没有吃药\n      - 问如果用户回答吃药了，询问吃的什么药，以及剂量。\n      - 最后询问用户有没有药物过敏。\n      - 最后询问用户有没有其他症状。\n     ```\n\n2. **query** (Required)\n   - Type: string\n   - Description: User's input text\n\n3. **model** (Required)\n   - Type: AgentModelConfig\n   - Description: LLM model configuration\n   - Example: Configuration for GPT or other LLM models\n\n4. **storage_key** (Required)\n   - Type: string\n   - Description: Unique key for storing conversation state\n   - Example: `\"mtd-conversation-123\"`\n\n### Changelog\n\n#### v0.0.3\n- Added MTD (Multi-Turn Dialogue) strategy support\n- Fixed data type validation bugs\n- Added support for schema JSON without leading spaces (compatible with Dify official update)\n  \n#### v0.0.2\n- Added logging functionality\n- Added token usage statistics\n- Optimized code structure and performance\n\n#### v0.0.1\n- Project initialization\n- Implemented multi-turn dialogue\n- Implemented conversation state storage\n- Implemented intelligent Q&A content extraction",
        "label": {
          "en_US": "Dialogue Agent",
          "zh_Hans": "对话 Agent"
        },
        "latest_package_identifier": "svcvit/agent:0.0.3@44466059969469f29cac1818fb2fab6268cc277d44a2b14a0e1b7549fa8ebf05",
        "latest_version": "0.0.3",
        "model": {},
        "name": "agent",
        "org": "svcvit",
        "plugin_id": "svcvit/agent",
        "plugins": {
          "agent_strategies": [
            "provider/agent.yaml"
          ],
          "endpoints": null,
          "models": null,
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "storage": {
              "enabled": true,
              "size": 1073741824
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "agent"
          }
        ],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-03-31T07:12:54Z",
        "version_updated_at": "2025-03-31T07:12:54Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Azure OpenAI Service Model"
        },
        "category": "model",
        "created_at": "2024-12-13T13:52:33Z",
        "endpoint": {},
        "icon": "langgenius/packages/azure_openai/_assets/icon_s_en.svg",
        "index_id": "langgenius___azure_openai",
        "install_count": 12839,
        "introduction": "## Overview\nAzure OpenAI Service is a cloud-based platform that provides access to advanced AI models developed by OpenAI, integrated with Microsoft's Azure infrastructure. This plugin allows users to leverage cutting-edge generative AI capabilities such as LLMs, text embedding, speech-to-text (STT), and text-to-speech (TTS) for various applications, ensuring security and compliance through Azure's robust framework.\n\n## Configure\nOnce the plugin is installed, configure your Azure OpenAI Service Model by providing the Model Type, Deployment Name, API Endpoint URL, your API Key, the API Version, and the Base Model. Find your API key on Azure. Save to complete the setup.\n\n<img src=\"./_assets/azure_openai-01.png\" width=\"400\" />\n",
        "label": {
          "en_US": "Azure OpenAI"
        },
        "latest_package_identifier": "langgenius/azure_openai:0.0.14@165b7e3d62f84ab2c28c2082250ff31d189a8533924fc1e9378bd902392267c0",
        "latest_version": "0.0.14",
        "model": {
          "background": "#E3F0FF",
          "configurate_methods": [
            "customizable-model"
          ],
          "description": {
            "en_US": "Azure OpenAI Service Model"
          },
          "help": {
            "title": {
              "en_US": "Get your API key from Azure",
              "zh_Hans": "从 Azure 获取 API Key"
            },
            "url": {
              "en_US": "https://azure.microsoft.com/en-us/products/ai-services/openai-service"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.png"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "Azure OpenAI Service Model"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Endpoint URL",
                  "zh_Hans": "API 域名"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Endpoint, eg: https://example.com/xxx",
                  "zh_Hans": "在此输入您的 API 域名，如：https://example.com/xxx"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "openai_api_base"
              },
              {
                "default": null,
                "label": {
                  "en_US": "API Key",
                  "zh_Hans": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API key here",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "openai_api_key"
              },
              {
                "default": null,
                "label": {
                  "en_US": "API Version",
                  "zh_Hans": "API 版本"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "2025-03-01-preview"
                    },
                    "show_on": [],
                    "value": "2025-03-01-preview"
                  },
                  {
                    "label": {
                      "en_US": "2025-02-01-preview"
                    },
                    "show_on": [],
                    "value": "2025-02-01-preview"
                  },
                  {
                    "label": {
                      "en_US": "2025-01-01-preview"
                    },
                    "show_on": [],
                    "value": "2025-01-01-preview"
                  },
                  {
                    "label": {
                      "en_US": "2024-12-01-preview"
                    },
                    "show_on": [],
                    "value": "2024-12-01-preview"
                  },
                  {
                    "label": {
                      "en_US": "2024-10-01-preview"
                    },
                    "show_on": [],
                    "value": "2024-10-01-preview"
                  },
                  {
                    "label": {
                      "en_US": "2024-09-01-preview"
                    },
                    "show_on": [],
                    "value": "2024-09-01-preview"
                  },
                  {
                    "label": {
                      "en_US": "2024-08-01-preview"
                    },
                    "show_on": [],
                    "value": "2024-08-01-preview"
                  },
                  {
                    "label": {
                      "en_US": "2024-07-01-preview"
                    },
                    "show_on": [],
                    "value": "2024-07-01-preview"
                  },
                  {
                    "label": {
                      "en_US": "2024-05-01-preview"
                    },
                    "show_on": [],
                    "value": "2024-05-01-preview"
                  },
                  {
                    "label": {
                      "en_US": "2024-04-01-preview"
                    },
                    "show_on": [],
                    "value": "2024-04-01-preview"
                  },
                  {
                    "label": {
                      "en_US": "2024-03-01-preview"
                    },
                    "show_on": [],
                    "value": "2024-03-01-preview"
                  },
                  {
                    "label": {
                      "en_US": "2024-02-15-preview"
                    },
                    "show_on": [],
                    "value": "2024-02-15-preview"
                  },
                  {
                    "label": {
                      "en_US": "2023-12-01-preview"
                    },
                    "show_on": [],
                    "value": "2023-12-01-preview"
                  },
                  {
                    "label": {
                      "en_US": "2024-02-01"
                    },
                    "show_on": [],
                    "value": "2024-02-01"
                  },
                  {
                    "label": {
                      "en_US": "2024-06-01"
                    },
                    "show_on": [],
                    "value": "2024-06-01"
                  },
                  {
                    "label": {
                      "en_US": "2024-10-21"
                    },
                    "show_on": [],
                    "value": "2024-10-21"
                  }
                ],
                "placeholder": {
                  "en_US": "Select your API Version here",
                  "zh_Hans": "在此选择您的 API 版本"
                },
                "required": true,
                "show_on": [],
                "type": "select",
                "variable": "openai_api_version"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Base Model",
                  "zh_Hans": "基础模型"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "gpt-35-turbo"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "gpt-35-turbo"
                  },
                  {
                    "label": {
                      "en_US": "gpt-35-turbo-0125"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "gpt-35-turbo-0125"
                  },
                  {
                    "label": {
                      "en_US": "gpt-35-turbo-16k"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "gpt-35-turbo-16k"
                  },
                  {
                    "label": {
                      "en_US": "gpt-4"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "gpt-4"
                  },
                  {
                    "label": {
                      "en_US": "gpt-4-32k"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "gpt-4-32k"
                  },
                  {
                    "label": {
                      "en_US": "gpt-4.5-preview"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "gpt-4.5-preview"
                  },
                  {
                    "label": {
                      "en_US": "o3-mini"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "o3-mini"
                  },
                  {
                    "label": {
                      "en_US": "o3"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "o3"
                  },
                  {
                    "label": {
                      "en_US": "o4-mini"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "o4-mini"
                  },
                  {
                    "label": {
                      "en_US": "o1-mini"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "o1-mini"
                  },
                  {
                    "label": {
                      "en_US": "o1-preview"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "o1-preview"
                  },
                  {
                    "label": {
                      "en_US": "o1"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "o1"
                  },
                  {
                    "label": {
                      "en_US": "gpt-4o-mini"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "gpt-4o-mini"
                  },
                  {
                    "label": {
                      "en_US": "gpt-4o-mini-2024-07-18"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "gpt-4o-mini-2024-07-18"
                  },
                  {
                    "label": {
                      "en_US": "gpt-4o"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "gpt-4o"
                  },
                  {
                    "label": {
                      "en_US": "gpt-4o-2024-05-13"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "gpt-4o-2024-05-13"
                  },
                  {
                    "label": {
                      "en_US": "gpt-4o-2024-08-06"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "gpt-4o-2024-08-06"
                  },
                  {
                    "label": {
                      "en_US": "gpt-4.1"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "gpt-4.1"
                  },
                  {
                    "label": {
                      "en_US": "gpt-4.1-mini"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "gpt-4.1-mini"
                  },
                  {
                    "label": {
                      "en_US": "gpt-4.1-nano"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "gpt-4.1-nano"
                  },
                  {
                    "label": {
                      "en_US": "gpt-4-turbo"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "gpt-4-turbo"
                  },
                  {
                    "label": {
                      "en_US": "gpt-4-turbo-2024-04-09"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "gpt-4-turbo-2024-04-09"
                  },
                  {
                    "label": {
                      "en_US": "gpt-4o-2024-11-20"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "gpt-4o-2024-11-20"
                  },
                  {
                    "label": {
                      "en_US": "gpt-4-0125-preview"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "gpt-4-0125-preview"
                  },
                  {
                    "label": {
                      "en_US": "gpt-4-1106-preview"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "gpt-4-1106-preview"
                  },
                  {
                    "label": {
                      "en_US": "gpt-4-vision-preview"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "gpt-4-vision-preview"
                  },
                  {
                    "label": {
                      "en_US": "gpt-35-turbo-instruct"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "gpt-35-turbo-instruct"
                  },
                  {
                    "label": {
                      "en_US": "text-embedding-ada-002"
                    },
                    "show_on": [
                      {
                        "value": "text-embedding",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "text-embedding-ada-002"
                  },
                  {
                    "label": {
                      "en_US": "text-embedding-3-small"
                    },
                    "show_on": [
                      {
                        "value": "text-embedding",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "text-embedding-3-small"
                  },
                  {
                    "label": {
                      "en_US": "text-embedding-3-large"
                    },
                    "show_on": [
                      {
                        "value": "text-embedding",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "text-embedding-3-large"
                  },
                  {
                    "label": {
                      "en_US": "whisper-1"
                    },
                    "show_on": [
                      {
                        "value": "speech2text",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "whisper-1"
                  },
                  {
                    "label": {
                      "en_US": "tts-1"
                    },
                    "show_on": [
                      {
                        "value": "tts",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "tts-1"
                  },
                  {
                    "label": {
                      "en_US": "tts-1-hd"
                    },
                    "show_on": [
                      {
                        "value": "tts",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "tts-1-hd"
                  }
                ],
                "placeholder": {
                  "en_US": "Enter your model version",
                  "zh_Hans": "在此输入您的模型版本"
                },
                "required": true,
                "show_on": [],
                "type": "select",
                "variable": "base_model_name"
              }
            ],
            "model": {
              "label": {
                "en_US": "Deployment Name",
                "zh_Hans": "部署名称"
              },
              "placeholder": {
                "en_US": "Enter your Deployment Name here, matching the Azure deployment name.",
                "zh_Hans": "在此输入您的部署名称，与 Azure 部署名称匹配。"
              }
            }
          },
          "models": [],
          "position": {},
          "provider": "azure_openai",
          "provider_credential_schema": null,
          "supported_model_types": [
            "llm",
            "text-embedding",
            "speech2text",
            "tts"
          ]
        },
        "name": "azure_openai",
        "org": "langgenius",
        "plugin_id": "langgenius/azure_openai",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/azure_openai.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": false,
              "llm": false,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-17T12:32:43Z",
        "version_updated_at": "2025-04-17T12:32:43Z"
      },
      {
        "agent_strategy": {},
        "badges": [
          "partner"
        ],
        "brief": {
          "en_US": "OpenRouter is a powerful platform that provides access to a diverse set of language models, including both commercial and open-source options.",
          "zh_Hans": "OpenRouter 是一个强大的平台，提供对多种语言模型的访问，包括商业和开源选项。"
        },
        "category": "model",
        "created_at": "2024-12-04T08:33:06Z",
        "endpoint": {},
        "icon": "langgenius/packages/openrouter/_assets/openrouter_square.svg",
        "index_id": "langgenius___openrouter",
        "install_count": 12648,
        "introduction": "# Overview\nOpenRouter is a powerful platform that provides access to a diverse set of language models, including both commercial and open-source options. It enables developers to integrate various AI capabilities such as text generation, image generation, audio processing, and more through a unified API. OpenRouter supports models like GPT-4, Anthropic's Claude, Google's Gemini, and many others, allowing users to leverage advanced AI functionalities in their applications.\n\n# Configuration\nAfter installation, you need to get API keys from [OpenRouter](https://openrouter.ai/keys) and setup in Settings -> Model Provider.\n\n![](_assets/openrouter.PNG)",
        "label": {
          "en_US": "OpenRouter"
        },
        "latest_package_identifier": "langgenius/openrouter:0.0.7@c7d9867337da290e42a09410d8a51a797351d354e199bac0cb16046d927a283c",
        "latest_version": "0.0.7",
        "model": {
          "background": "#F1EFED",
          "configurate_methods": [
            "predefined-model",
            "customizable-model"
          ],
          "description": {
            "en_US": "OpenRouter is a powerful platform that provides access to a diverse set of language models, including both commercial and open-source options.",
            "zh_Hans": "OpenRouter 是一个强大的平台，提供对多种语言模型的访问，包括商业和开源选项。"
          },
          "help": {
            "title": {
              "en_US": "Get your API key from openrouter.ai",
              "zh_Hans": "从 openrouter.ai 获取 API Key"
            },
            "url": {
              "en_US": "https://openrouter.ai/keys"
            }
          },
          "icon_large": {
            "en_US": "openrouter.svg"
          },
          "icon_small": {
            "en_US": "openrouter_square.svg"
          },
          "label": {
            "en_US": "OpenRouter"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              },
              {
                "default": "chat",
                "label": {
                  "en_US": "Completion mode"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Completion",
                      "zh_Hans": "补全"
                    },
                    "show_on": [],
                    "value": "completion"
                  },
                  {
                    "label": {
                      "en_US": "Chat",
                      "zh_Hans": "对话"
                    },
                    "show_on": [],
                    "value": "chat"
                  }
                ],
                "placeholder": {
                  "en_US": "Select completion mode",
                  "zh_Hans": "选择对话类型"
                },
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "select",
                "variable": "mode"
              },
              {
                "default": "4096",
                "label": {
                  "en_US": "Model context size",
                  "zh_Hans": "模型上下文长度"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Model context size",
                  "zh_Hans": "在此输入您的模型上下文长度"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "context_size"
              },
              {
                "default": "4096",
                "label": {
                  "en_US": "Upper bound for max tokens",
                  "zh_Hans": "最大 token 上限"
                },
                "max_length": 0,
                "options": [],
                "placeholder": null,
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "text-input",
                "variable": "max_tokens_to_sample"
              },
              {
                "default": "no_support",
                "label": {
                  "en_US": "Vision Support",
                  "zh_Hans": "是否支持 Vision"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Yes",
                      "zh_Hans": "是"
                    },
                    "show_on": [],
                    "value": "support"
                  },
                  {
                    "label": {
                      "en_US": "No",
                      "zh_Hans": "否"
                    },
                    "show_on": [],
                    "value": "no_support"
                  }
                ],
                "placeholder": null,
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "radio",
                "variable": "vision_support"
              }
            ],
            "model": {
              "label": {
                "en_US": "Model Name",
                "zh_Hans": "模型名称"
              },
              "placeholder": {
                "en_US": "Enter full model name",
                "zh_Hans": "输入模型全称"
              }
            }
          },
          "models": [
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "claude-3-5-haiku"
              },
              "model": "anthropic/claude-3-5-haiku",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "1",
                "output": "5",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "claude-3.5-sonnet"
              },
              "model": "anthropic/claude-3.5-sonnet",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "3",
                "output": "15",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "claude-3-haiku"
              },
              "model": "anthropic/claude-3-haiku",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.25",
                "output": "1.25",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "claude-3-opus"
              },
              "model": "anthropic/claude-3-opus",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "15",
                "output": "75",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "claude-3-sonnet"
              },
              "model": "anthropic/claude-3-sonnet",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "3",
                "output": "15",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "command-r-plus"
              },
              "model": "cohere/command-r-plus",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 5,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.75,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.99,
                  "min": 0.01,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "3",
                "output": "15",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "command-r"
              },
              "model": "cohere/command-r",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 5,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.75,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.99,
                  "min": 0.01,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.5",
                "output": "1.5",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "deepseek-chat"
              },
              "model": "deepseek/deepseek-chat",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Control the diversity and randomness of generated results. The smaller the value, the more rigorous it is; the larger the value, the more divergent it is.",
                    "zh_Hans": "控制生成结果的多样性和随机性。数值越小，越严谨；数值越大，越发散。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Control the randomness of generated results. The smaller the value, the weaker the randomness; the larger the value, the stronger the randomness. Generally speaking, you can adjust one of the two parameters top_p and temperature.",
                    "zh_Hans": "控制生成结果的随机性。数值越小，随机性越弱；数值越大，随机性越强。一般而言，top_p 和 temperature 两个参数选择一个进行调整即可。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0.01,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "A number between -2.0 and 2.0. If the value is positive, new tokens are penalized based on their frequency of occurrence in existing text, reducing the likelihood that the model will repeat the same content.",
                    "zh_Hans": "介于 -2.0 和 2.0 之间的数字。如果该值为正，那么新 token 会根据其在已有文本中的出现频率受到相应的惩罚，降低模型重复相同内容的可能性。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.14",
                "output": "0.28",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "deepseek-coder"
              },
              "model": "deepseek/deepseek-coder",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.14",
                "output": "0.28",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gemini-flash-1.5"
              },
              "model": "google/gemini-flash-1.5",
              "model_properties": {
                "context_size": 1048576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.25",
                "output": "0.75",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gemini-pro-1.5"
              },
              "model": "google/gemini-pro-1.5",
              "model_properties": {
                "context_size": 1048576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "2.5",
                "output": "7.5",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gemini-pro"
              },
              "model": "google/gemini-pro",
              "model_properties": {
                "context_size": 30720,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.125",
                "output": "0.375",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-3.5-turbo"
              },
              "model": "openai/gpt-3.5-turbo",
              "model_properties": {
                "context_size": 16385,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.5",
                "output": "1.5",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-4-32k"
              },
              "model": "openai/gpt-4-32k",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 32768,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "If specified, model will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.",
                    "zh_Hans": "如果指定，模型将尽最大努力进行确定性采样，使得重复的具有相同种子和参数的请求应该返回相同的结果。不能保证确定性，您应该参考 system_fingerprint 响应参数来监视变化。"
                  },
                  "label": {
                    "en_US": "Seed",
                    "zh_Hans": "种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "60",
                "output": "120",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-4"
              },
              "model": "openai/gpt-4",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "If specified, model will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.",
                    "zh_Hans": "如果指定，模型将尽最大努力进行确定性采样，使得重复的具有相同种子和参数的请求应该返回相同的结果。不能保证确定性，您应该参考 system_fingerprint 响应参数来监视变化。"
                  },
                  "label": {
                    "en_US": "Seed",
                    "zh_Hans": "种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "30",
                "output": "60",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-4o-2024-08-06",
                "zh_Hans": "gpt-4o-2024-08-06"
              },
              "model": "gpt-4o-2024-08-06",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 16384,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "2.5",
                "output": "10",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-4o-mini"
              },
              "model": "openai/gpt-4o-mini",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 16384,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.15",
                "output": "0.6",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-4o"
              },
              "model": "openai/gpt-4o",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "5",
                "output": "15",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "llama-3-70b-instruct"
              },
              "model": "meta-llama/llama-3-70b-instruct",
              "model_properties": {
                "context_size": 8192,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.59",
                "output": "0.79",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "llama-3-8b-instruct"
              },
              "model": "meta-llama/llama-3-8b-instruct",
              "model_properties": {
                "context_size": 8192,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.07",
                "output": "0.07",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "llama-3.1-405b-instruct"
              },
              "model": "meta-llama/llama-3.1-405b-instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 131072,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "2.7",
                "output": "2.7",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "llama-3.1-70b-instruct"
              },
              "model": "meta-llama/llama-3.1-70b-instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 131072,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.52",
                "output": "0.75",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "llama-3.1-8b-instruct"
              },
              "model": "meta-llama/llama-3.1-8b-instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 131072,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.06",
                "output": "0.06",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "llama-3.2-11b-vision-instruct",
                "zh_Hans": "llama-3.2-11b-vision-instruct"
              },
              "model": "meta-llama/llama-3.2-11b-vision-instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 64,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": "None",
                  "help": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "label": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "max": null,
                  "min": null,
                  "name": "context_length_exceeded_behavior",
                  "options": [
                    "None",
                    "truncate",
                    "error"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.055",
                "output": "0.055",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "llama-3.2-1b-instruct",
                "zh_Hans": "llama-3.2-1b-instruct"
              },
              "model": "meta-llama/llama-3.2-1b-instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 64,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": "None",
                  "help": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "label": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "max": null,
                  "min": null,
                  "name": "context_length_exceeded_behavior",
                  "options": [
                    "None",
                    "truncate",
                    "error"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.01",
                "output": "0.02",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "llama-3.2-3b-instruct",
                "zh_Hans": "llama-3.2-3b-instruct"
              },
              "model": "meta-llama/llama-3.2-3b-instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 64,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": "None",
                  "help": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "label": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "max": null,
                  "min": null,
                  "name": "context_length_exceeded_behavior",
                  "options": [
                    "None",
                    "truncate",
                    "error"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.03",
                "output": "0.05",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "llama-3.2-90b-vision-instruct",
                "zh_Hans": "llama-3.2-90b-vision-instruct"
              },
              "model": "meta-llama/llama-3.2-90b-vision-instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 64,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": "None",
                  "help": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "label": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "max": null,
                  "min": null,
                  "name": "context_length_exceeded_behavior",
                  "options": [
                    "None",
                    "truncate",
                    "error"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.35",
                "output": "0.4",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "mistral-7b-instruct"
              },
              "model": "mistralai/mistral-7b-instruct",
              "model_properties": {
                "context_size": 8000,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.07",
                "output": "0.07",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "mixtral-8x22b-instruct"
              },
              "model": "mistralai/mixtral-8x22b-instruct",
              "model_properties": {
                "context_size": 64000,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.65",
                "output": "0.65",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "mixtral-8x7b-instruct",
                "zh_Hans": "mixtral-8x7b-instruct"
              },
              "model": "mistralai/mixtral-8x7b-instruct",
              "model_properties": {
                "context_size": 32000,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.24",
                "output": "0.24",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "o1-mini"
              },
              "model": "openai/o1-mini",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 65536,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "response_format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "3",
                "output": "12",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "o1-preview"
              },
              "model": "openai/o1-preview",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 32768,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "response_format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "15",
                "output": "60",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "o3-mini-2025-01-31"
              },
              "model": "openai/o3-mini-2025-01-31",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 100000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "response_format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "1.1",
                "output": "4.4",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "o3-mini"
              },
              "model": "openai/o3-mini",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 100000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "response_format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "1.1",
                "output": "4.4",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-2-72b-instruct"
              },
              "model": "qwen/qwen-2-72b-instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.59",
                "output": "0.79",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen-2.5-72b-instruct"
              },
              "model": "qwen/qwen-2.5-72b-instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.35",
                "output": "0.4",
                "unit": "0.000001"
              }
            }
          ],
          "position": {
            "llm": [
              "openai/o3-mini",
              "openai/o3-mini-2025-01-31",
              "openai/o1-preview",
              "openai/o1-mini",
              "openai/gpt-4o",
              "openai/gpt-4o-mini",
              "openai/gpt-4",
              "openai/gpt-4-32k",
              "openai/gpt-3.5-turbo",
              "anthropic/claude-3.5-sonnet",
              "anthropic/claude-3-haiku",
              "anthropic/claude-3-opus",
              "anthropic/claude-3-sonnet",
              "google/gemini-pro-1.5",
              "google/gemini-flash-1.5",
              "google/gemini-pro",
              "cohere/command-r-plus",
              "cohere/command-r",
              "meta-llama/llama-3.2-1b-instruct",
              "meta-llama/llama-3.2-3b-instruct",
              "meta-llama/llama-3.2-11b-vision-instruct",
              "meta-llama/llama-3.2-90b-vision-instruct",
              "meta-llama/llama-3.1-405b-instruct",
              "meta-llama/llama-3.1-70b-instruct",
              "meta-llama/llama-3.1-8b-instruct",
              "meta-llama/llama-3-70b-instruct",
              "meta-llama/llama-3-8b-instruct",
              "mistralai/mixtral-8x22b-instruct",
              "mistralai/mixtral-8x7b-instruct",
              "mistralai/mistral-7b-instruct",
              "qwen/qwen-2.5-72b-instruct",
              "qwen/qwen-2-72b-instruct",
              "deepseek/deepseek-chat",
              "deepseek/deepseek-coder"
            ]
          },
          "provider": "openrouter",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              }
            ]
          },
          "supported_model_types": [
            "llm"
          ]
        },
        "name": "openrouter",
        "org": "langgenius",
        "plugin_id": "langgenius/openrouter",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/openrouter.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": false,
              "llm": false,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-07T04:51:17Z",
        "version_updated_at": "2025-04-07T04:51:17Z"
      },
      {
        "agent_strategy": {
          "identity": {
            "author": "junjiem",
            "description": {
              "en_US": "Support MCP Tools Agent",
              "zh_Hans": "支持 MCP 工具的 Agent"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Support MCP Tools Agent",
              "zh_Hans": "支持 MCP 工具的 Agent"
            },
            "name": "mcp_see_agent",
            "tags": []
          },
          "strategies": [
            {
              "description": {
                "en_US": "Function Calling is a basic strategy for agent, model will use the Dify and MCP tools provided to perform the task.",
                "zh_Hans": "Function Calling 是一个基本的 Agent 策略，模型将使用提供的 Dify 和 MCP 工具来执行任务。"
              },
              "identity": {
                "author": "junjiem",
                "label": {
                  "en_US": "FunctionCalling (Support MCP Tools)",
                  "zh_Hans": "FunctionCalling (Support MCP Tools)"
                },
                "name": "mcp_sse_function_calling"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "label": {
                    "en_US": "Model",
                    "zh_Hans": "模型"
                  },
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": "tool-call&llm",
                  "template": null,
                  "type": "model-selector"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "label": {
                    "en_US": "Tool list",
                    "zh_Hans": "工具列表"
                  },
                  "max": null,
                  "min": null,
                  "name": "tools",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "array[tools]"
                },
                {
                  "auto_generate": null,
                  "default": "{\n  \"server_name1\": {\n    \"transport\": \"sse\",\n    \"url\": \"http://127.0.0.1:8000/sse\"\n  }, \n  \"server_name2\": {\n    \"transport\": \"streamable_http\",\n    \"url\": \"http://127.0.0.1:8000/mcp\"\n  }\n}",
                  "label": {
                    "en_US": "MCP Servers config",
                    "zh_Hans": "MCP 服务配置"
                  },
                  "max": null,
                  "min": null,
                  "name": "mcp_servers_config",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": {
                    "type": "prompt_instruction"
                  },
                  "default": null,
                  "label": {
                    "en_US": "Instruction",
                    "zh_Hans": "指令"
                  },
                  "max": null,
                  "min": null,
                  "name": "instruction",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": {
                    "enabled": true
                  },
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "label": {
                    "en_US": "Query",
                    "zh_Hans": "查询"
                  },
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 5,
                  "label": {
                    "en_US": "Maximum Iterations",
                    "zh_Hans": "最大迭代次数"
                  },
                  "max": 30,
                  "min": 1,
                  "name": "maximum_iterations",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "en_US": "ReAct is a basic strategy for agent, model will use the Dify and MCP tools provided to perform the task.",
                "zh_Hans": "ReAct 是一个基本的 Agent 策略，模型将使用提供的 Dify 和 MCP 工具来执行任务。"
              },
              "identity": {
                "author": "junjiem",
                "label": {
                  "en_US": "ReAct (Support MCP Tools)",
                  "zh_Hans": "ReAct (Support MCP Tools)"
                },
                "name": "mcp_sse_ReAct"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "label": {
                    "en_US": "Model",
                    "zh_Hans": "模型"
                  },
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": "tool-call&llm",
                  "template": null,
                  "type": "model-selector"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "label": {
                    "en_US": "Tool list",
                    "zh_Hans": "工具列表"
                  },
                  "max": null,
                  "min": null,
                  "name": "tools",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "array[tools]"
                },
                {
                  "auto_generate": null,
                  "default": "{\n  \"server_name1\": {\n    \"transport\": \"sse\",\n    \"url\": \"http://127.0.0.1:8000/sse\"\n  }, \n  \"server_name2\": {\n    \"transport\": \"streamable_http\",\n    \"url\": \"http://127.0.0.1:8000/mcp\"\n  }\n}",
                  "label": {
                    "en_US": "MCP Servers config",
                    "zh_Hans": "MCP 服务配置"
                  },
                  "max": null,
                  "min": null,
                  "name": "mcp_servers_config",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": {
                    "type": "prompt_instruction"
                  },
                  "default": null,
                  "label": {
                    "en_US": "Instruction",
                    "zh_Hans": "指令"
                  },
                  "max": null,
                  "min": null,
                  "name": "instruction",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": {
                    "enabled": true
                  },
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "label": {
                    "en_US": "Query",
                    "zh_Hans": "查询"
                  },
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 5,
                  "label": {
                    "en_US": "Maximum Iterations",
                    "zh_Hans": "最大迭代次数"
                  },
                  "max": 30,
                  "min": 1,
                  "name": "maximum_iterations",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            }
          ]
        },
        "badges": [],
        "brief": {
          "en_US": "Agent strategies collection that provide Function Calling and ReAct (Support MCP SSE / StreamableHTTP fetch and call tools).",
          "zh_Hans": "提供 Function Calling 和 ReAct 的 Agent 策略集合（支持 MCP SSE / StreamableHTTP 发现和调用工具）。"
        },
        "category": "agent-strategy",
        "created_at": "2025-03-17T11:20:17Z",
        "endpoint": {},
        "icon": "junjiem/packages/mcp_see_agent/_assets/icon.svg",
        "index_id": "junjiem___mcp_see_agent",
        "install_count": 12549,
        "introduction": "## Dify 1.0 Plugin Support MCP Tools Agent strategies\n\n**Author:** [Junjie.M](https://github.com/junjiem)   \n**Type:** agent-strategy  \n**Github Repo:** [https://github.com/junjiem/dify-plugin-agent-mcp_sse](https://github.com/junjiem/dify-plugin-agent-mcp_sse)   \n**Github Issues:** [issues](https://github.com/junjiem/dify-plugin-agent-mcp_sse/issues)  \n\n\n---\n\n\n### Description\n\nAgent strategies collection that provide `Function Calling` and `ReAct` \n(Support `fetch and call tools` by `MCP` protocol through `HTTP with SSE` or `Streamable HTTP` transport).\n\n提供 `Function Calling` 和 `ReAct` 的 Agent 策略集合\n（支持通过 `HTTP with SSE` 或 `Streamable HTTP` 传输方式使用 `MCP` 协议来`发现和调用工具`）。\n\n![mcp_sse_agent](_assets/mcp_sse_agent.png)\n\n![mcp_sse_agent_strategies](_assets/mcp_sse_agent_strategies.png)\n\n![mcp_sse_agent_react](_assets/mcp_sse_agent_react.png)\n\n\nMCP Servers config, support multiple MCP services. The following example:\n\nMCP服务配置，支持多个MCP服务。 如下示例：\n\n```json\n{\n  \"server_name1\": {\n    \"transport\": \"sse\",\n    \"url\": \"http://127.0.0.1:8000/sse\",\n    \"headers\": {},\n    \"timeout\": 60,\n    \"sse_read_timeout\": 300\n  },\n  \"server_name2\": {\n    \"transport\": \"sse\",\n    \"url\": \"http://127.0.0.1:8001/sse\"\n  },\n  \"server_name3\": {\n    \"transport\": \"streamable_http\",\n    \"url\": \"http://127.0.0.1:8002/mcp\",\n    \"headers\": {},\n    \"timeout\": 60\n  },\n  \"server_name4\": {\n    \"transport\": \"streamable_http\",\n    \"url\": \"http://127.0.0.1:8003/mcp\"\n  }\n}\n```\nOR\n```json\n{\n  \"mcpServers\": {\n      \"server_name1\": {\n        \"transport\": \"sse\",\n        \"url\": \"http://127.0.0.1:8000/sse\",\n        \"headers\": {},\n        \"timeout\": 60,\n        \"sse_read_timeout\": 300\n      },\n      \"server_name2\": {\n        \"transport\": \"sse\",\n        \"url\": \"http://127.0.0.1:8001/sse\"\n      },\n      \"server_name3\": {\n        \"transport\": \"streamable_http\",\n        \"url\": \"http://127.0.0.1:8002/mcp\",\n        \"headers\": {},\n        \"timeout\": 60\n      },\n      \"server_name4\": {\n        \"transport\": \"streamable_http\",\n        \"url\": \"http://127.0.0.1:8003/mcp\"\n      }\n    }\n}\n```\n\n> **Note:** \"transport\" parameter as `sse` or `streamable_http`, default `sse`.\n\n> **注：**  \"transport\" 参数为 `sse` 或 `streamable_http` ，默认为 `sse`。\n\n\n\n---\n\n\n\n### Managed MCP Servers 托管的MCP服务器\n\nIf you want to try MCP but don't know how to deploy SSE transport's MCP Server, can you try connect to Managed MCP Servers.\n\n如果你想尝试 MCP，但是不知道如何部署 SSE 传输的 MCP Server，可以尝试连接托管的 MCP 服务器。\n\n#### Example 1  示例1\n\n[Composio Managed MCP Servers](https://mcp.composio.dev)\n\n[Composio 托管的 MCP 服务器](https://mcp.composio.dev)\n\n![composio_mcp_list](_assets/composio_mcp_list.png)\n\nReference Cursor Settings, shown below:\n\n参考 Cursor 设置，如下图：\n\n![composio_mcp_cursor](_assets/composio_mcp_cursor.png)\n![composio_mcp_cursor2](_assets/composio_mcp_cursor2.png)\n\nMCP Servers config, shown below:\n\nMCP 服务配置，如下示例：\n\n```json\n{\n  \"tavily\": {\n    \"url\": \"https://mcp.composio.dev/tavily/xxxx-xxxx-xxxx-xxxx\"\n  }\n}\n```\n\n\n\n#### Example 2  示例2\n\n[Zapier Managed MCP Servers](https://actions.zapier.com/settings/mcp)\n\n[Zapier 托管的 MCP 服务器](https://actions.zapier.com/settings/mcp)\n\nCopy the MCP Server URL for use in the Dify plug-in configuration.\n\n复制 MCP Server URL，在 Dify 插件配置中使用。\n\n![zapier_mcp_servers](_assets/zapier_mcp_servers.png)\n\nMCP Servers config, shown below:\n\nMCP 服务配置，如下示例：\n\n```json\n{\n  \"zapier-mcp\": {\n    \"url\": \"https://actions.zapier.com/mcp/sk-xxxxxxxxxx/sse\"\n  }\n}\n```\n\nClick \"Edit MCP Actions\" to go to the page for adding tools and actions.\n\n点击 “Edit MCP Actions” ，进入工具和操作的添加页面。\n\n![zapier_mcp_edit_actions](_assets/zapier_mcp_edit_actions.png)\n\nClick \"Add a new action\" to add the required MCP service instance.\n\n点击 “Add a new action”，添加需要的MCP服务实例。\n\n![zapier_mcp_add_actions](_assets/zapier_mcp_add_actions.png)\n\nYou can also continue to add different actions to enrich the tool set available to the Agent.\n\n你还可以继续添加不同的 Action，丰富 Agent 可用的工具集。\n\n\n#### Example 3  示例3\n\n[MCP.so Managed MCP Servers](https://mcp.so/playground)\n\n[MCP.so 托管的 MCP 服务器](https://mcp.so/playground)\n\n##### `Streamable HTTP`\n\n![mcpso_mcp_servers_streamable_http](_assets/mcpso_mcp_servers_streamable_http.png)\n\nMCP Servers config, shown below:\n\nMCP 服务配置，如下示例：\n\n```json\n{\n  \"tavily-mcp\": {\n    \"transport\": \"streamable_http\",\n    \"url\": \"https://router.mcp.so/mcp/xxxxxxxxxxx\"\n  }\n}\n```\n\n##### `SSE` \n\n![mcpso_mcp_servers_sse](_assets/mcpso_mcp_servers_sse.png)\n\nMCP Servers config, shown below:\n\nMCP 服务配置，如下示例：\n\n```json\n{\n  \"tavily-mcp\": {\n    \"url\": \"https://router.mcp.so/sse/xxxxxxxxxxx\"\n  }\n}\n```\n\n\n\n---\n\n\n\n### Installing Plugins via GitHub  通过 GitHub 安装插件\n\nCan install the plugin using the GitHub repository address. Visit the Dify platform's plugin management page, choose to install via GitHub, enter the repository address, select version number and package file to complete installation.\n\n可以通过 GitHub 仓库地址安装该插件。访问 Dify 平台的插件管理页，选择通过 GitHub 安装插件，输入仓库地址后，选择版本号和包文件完成安装。\n\n![install_plugin_via_github](_assets/install_plugin_via_github.png)\n\n\n\n---\n\n\n\n### FAQ\n\n#### 1. How to Handle Errors When Installing Plugins? 安装插件时遇到异常应如何处理？\n\n**Issue**: If you encounter the error message: plugin verification has been enabled, and the plugin you want to install has a bad signature, how to handle the issue?\n\n**Solution**: Add the following line to the end of your .env configuration file: FORCE_VERIFYING_SIGNATURE=false\nOnce this field is added, the Dify platform will allow the installation of all plugins that are not listed (and thus not verified) in the Dify Marketplace.\n\n**问题描述**：安装插件时遇到异常信息：plugin verification has been enabled, and the plugin you want to install has a bad signature，应该如何处理？\n\n**解决办法**：在 .env 配置文件的末尾添加 FORCE_VERIFYING_SIGNATURE=false 字段即可解决该问题。\n添加该字段后，Dify 平台将允许安装所有未在 Dify Marketplace 上架（审核）的插件，可能存在安全隐患。\n\n\n#### 2. How to install the offline version 如何安装离线版本\n\nScripting tool for downloading Dify plugin package from Dify Marketplace and Github and repackaging [true] offline package (contains dependencies, no need to be connected to the Internet).\n\n从Dify市场和Github下载Dify插件包并重新打【真】离线包（包含依赖，不需要再联网）的脚本工具。\n\nGithub Repo: https://github.com/junjiem/dify-plugin-repackaging\n\n",
        "label": {
          "en_US": "Agent Strategies (Support MCP Tools)",
          "zh_Hans": "Agent 策略（支持 MCP 工具）"
        },
        "latest_package_identifier": "junjiem/mcp_see_agent:0.1.0@2056b7f7cbe4265f1f8647ccb61c390246da9cc8d303548d14a337f3d3064879",
        "latest_version": "0.1.0",
        "model": {},
        "name": "mcp_see_agent",
        "org": "junjiem",
        "plugin_id": "junjiem/mcp_see_agent",
        "plugins": {
          "agent_strategies": [
            "provider/agent.yaml"
          ],
          "endpoints": null,
          "models": null,
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "storage": {
              "enabled": true,
              "size": 1073741824
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-21T20:49:13Z",
        "version_updated_at": "2025-04-21T20:49:13Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "This tool is used to execute SQL in an existing database.",
          "ja_JP": "This tool is used to execute SQL in an existing database.",
          "pt_BR": "This tool is used to execute SQL in an existing database.",
          "zh_Hans": "This tool is used to execute SQL in an existing database."
        },
        "category": "tool",
        "created_at": "2025-03-03T06:37:33Z",
        "endpoint": {
          "endpoints": [
            {
              "hidden": false,
              "method": "POST",
              "path": "/sql"
            }
          ],
          "settings": []
        },
        "icon": "hjlarry/packages/database/_assets/icon.svg",
        "index_id": "hjlarry___database",
        "install_count": 12416,
        "introduction": "## database\n\n**Author:** hjlarry  \n**Version:** 0.0.5  \n**Type:** tool   \n**Repo:** [https://github.com/hjlarry/dify-plugin-database](https://github.com/hjlarry/dify-plugin-database)  \n**Feature Request:** [issues](https://github.com/hjlarry/dify-plugin-database/issues)  \n**中文文档** [README_CN.md](README_CN.md)\n\n### Be Carefull!\n**The sql_execute tool can run any SQL query; for enhanced security, always use a read-only database account.**\n\n### Description\n\nA database tool make it easy to query data from existing databases.\n\nYou can get different format of data, like `json`, `csv`, `yaml`, `xlsx`, `html`, `md` etc. Also support use a url to get those data.\n\n### Usage\n\n#### 1. Input a databaseURI for Authorization. Now support `mysql`, `postgresql`, `sqlite`, `sqlserver`, `oracle`, example format:\n```shell\nmysql+pymysql://root:123456@localhost:3306/test\npostgresql+psycopg2://postgres:123456@localhost:5432/test\nsqlite:///test.db\nmssql+pymssql://<username>:<password>@<freetds_name>/?charset=utf8\noracle+oracledb://user:pass@hostname:port[/dbname][?service_name=<service>[&key=value&key=value...]]\n```\n\n> **Note:**: this plugin always run in a docker, so the `localhost` always means docker internal network, try `host.docker.internal` instead.\n\n#### 2. Use the `SQL Execute` tool to query data from the database.\n![sql](./_assets/sql_execute.png)\nThe `OUTPUT FORMAT` is used to specify the format of the output data. If you don't specify it, the default format is `json` and will output in the `json` variable of workflow node. `md` will output in the `text` variable, other format will create file and output in the `files` variable.\n\nIf you input the `DB URI` field, it will overwrite the default authorization uri, so this will be useful if you want to use different databases in the same workflow.\n\n#### 3. Use the `Text to SQL` tool can transform user input to a valid sql query.\n![text](./_assets/text.png)\n\nThis tool will use the default prompt [here](https://github.com/hjlarry/dify-plugin-database/blob/d6dd3695840e8eb5d673611784af148b1789da97/tools/text2sql.py#L9) to generate a sql query. If you specify the `TABLES` field, it will only get those tables' schema into the LLM context.\n\n#### 4. Use the `Get Table Schema` tool can get the schema of tables.\n\nIf the `Text to SQL` tool can't generate a helpful sql query, you can use this tool to get the schema of tables, then use the schema orginze with your own prompt or other information to a LLM node to generate a helpful sql query. \n\n#### 5. The `CSV Query` tool can execute a sql query from a csv file.\n![csv](./_assets/csv.png)  \nThe table name is always `csv`,  the column name is the csv file's first line. It support output `json` and `md`.\n\n#### 6. Use the `endpoint` tool to get the data from a url request.\n\nexample url request format:\n```shell\ncurl -X POST 'https://daemon-plugin.dify.dev/o3wvwZfYFLU5iGopr5CxYmGaM5mWV7xf/sql' -H 'Content-Type: application/json' -d '{\"query\":\"select * from test\", \"format\": \"md\"}'\n```\n\n\n### Changelog\n\n#### 0.0.5\n1. support `with` in sql query\n2. fix `text2sql` generate double quotes sql string\n3. fix  `too many clients already`\n4. add connect option of sqlalchemy\n5. change the `db_uri` of authorization to an optional field\n6. add a `Get Table Schema` to directly response the schema of tables\n7. add a `CSV Query` tool to execute a sql query from a csv file\n8. fix `oracle` authorization can't run `select 1`\n\n#### 0.0.4\n1. support `sqlserver`, `oracle` connection\n2. change `db_url` to a llm format, so that user can use a environment variable of workflow to set the database uri\n3. fix in a agent app, `sql_execute` tool only response the first result\n4. migrate the table schema info of the `text2sql` tool to a user prompt, to prevent system prompt too long then response nothing\n\n#### 0.0.3\n1. add `cryptography` to requirements.txt to support mysql 8.1 sha256 link\n2. remove database uri setting of the endpoint\n3. add a `db_uri` to support link to multiple databases\n4. change the `output` of sql_execute tool to a form format\n5. change the `tables` of text2sql tool to a llm format\n6. fix sql query being converted to lowercase [issue](https://github.com/hjlarry/dify-plugin-database/issues/2)\n\n\n### Contact\n![1](_assets/contact.jpg)",
        "label": {
          "en_US": "database",
          "ja_JP": "database",
          "pt_BR": "database",
          "zh_Hans": "database"
        },
        "latest_package_identifier": "hjlarry/database:0.0.5@20c5020a28c47834253cddf96c954596b96fffa93062bbd801e69515c710b894",
        "latest_version": "0.0.5",
        "model": {},
        "name": "database",
        "org": "hjlarry",
        "plugin_id": "hjlarry/database",
        "plugins": {
          "agent_strategies": null,
          "endpoints": [
            "provider/endpoint.yaml"
          ],
          "models": null,
          "tools": [
            "provider/database.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "endpoint": {
              "enabled": true
            },
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "For example `mysql+pymysql://<user>:<password>@<host>:<port>/<database>`",
                "zh_Hans": "例如 `mysql+pymysql://<user>:<password>@<host>:<port>/<database>`"
              },
              "label": {
                "en_US": "Database URI",
                "zh_Hans": "数据库 URI"
              },
              "name": "db_uri",
              "options": null,
              "placeholder": {
                "en_US": "Please enter the database URI",
                "zh_Hans": "请输入数据库 URI"
              },
              "required": false,
              "scope": null,
              "type": "secret-input",
              "url": null
            }
          ],
          "identity": {
            "author": "hjlarry",
            "description": {
              "en_US": "This tool is used to execute SQL in an existing database.",
              "zh_Hans": "此工具用于在已存在的数据库中执行 SQL 查询。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Database"
            },
            "name": "database",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "This tool is used to execute SQL in an existing database.",
                  "zh_Hans": "此工具用于在已存在的数据库中执行 SQL 查询。"
                },
                "llm": "This tool is used to execute SQL in an existing database."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "hjlarry",
                "label": {
                  "en_US": "SQL Execute"
                },
                "name": "sql_execute"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The SQL query string.",
                    "zh_Hans": "SQL 查询语句。"
                  },
                  "label": {
                    "en_US": "SQL Query",
                    "zh_Hans": "SQL 查询语句"
                  },
                  "llm_description": "The SQL query string.",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional, Filling in this field will overwrite the database connection entered during authorization.",
                    "zh_Hans": "选填，填写后将覆盖授权时填写的数据库连接。"
                  },
                  "label": {
                    "en_US": "DB URI"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "db_uri",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "json",
                  "form": "form",
                  "human_description": {
                    "en_US": "Choose the output format.",
                    "zh_Hans": "选择输出格式。"
                  },
                  "label": {
                    "en_US": "Output format",
                    "zh_Hans": "输出格式"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "format",
                  "options": [
                    {
                      "label": {
                        "en_US": "JSON",
                        "zh_Hans": "JSON"
                      },
                      "value": "json"
                    },
                    {
                      "label": {
                        "en_US": "CSV",
                        "zh_Hans": "CSV"
                      },
                      "value": "csv"
                    },
                    {
                      "label": {
                        "en_US": "YAML",
                        "zh_Hans": "YAML"
                      },
                      "value": "yaml"
                    },
                    {
                      "label": {
                        "en_US": "Markdown",
                        "zh_Hans": "Markdown"
                      },
                      "value": "md"
                    },
                    {
                      "label": {
                        "en_US": "Excel",
                        "zh_Hans": "Excel"
                      },
                      "value": "xlsx"
                    },
                    {
                      "label": {
                        "en_US": "HTML",
                        "zh_Hans": "HTML"
                      },
                      "value": "html"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Optional. For example {\"connect_args\": {\"ssl\": {\"ca\": \"/path/to/ca.pem\"}}}\nMore connection options can be found at https://docs.sqlalchemy.org/en/20/core/engines.html#sqlalchemy.create_engine\n",
                    "zh_Hans": "选填项。例如 {\"connect_args\": {\"ssl\": {\"ca\": \"/path/to/ca.pem\"}}}\n更多连接选项可参考 https://docs.sqlalchemy.org/en/20/core/engines.html#sqlalchemy.create_engine\n"
                  },
                  "label": {
                    "en_US": "DB Config Options",
                    "zh_Hans": "数据库连接配置选项"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "config_options",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "supply to LLM the context of the database and the user query to get a sql string.",
                  "zh_Hans": "提供数据库上下文和用户的问题，来得到一个 SQL 语句。"
                },
                "llm": "supply to LLM the context of the database and the user query to get a sql string."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "hjlarry",
                "label": {
                  "en_US": "Text to SQL"
                },
                "name": "text2sql"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The user query.",
                    "zh_Hans": "用户的问题。"
                  },
                  "label": {
                    "en_US": "Query string",
                    "zh_Hans": "查询语句"
                  },
                  "llm_description": "The user query.",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Specify which tables to provide to LLM as context. If not specified, all tables will be used. Multi tables use comma to separate.",
                    "zh_Hans": "指定哪些表用于提供给LLM作为上下文，如不指定，则使用所有表。多张表用半角逗号隔开。"
                  },
                  "label": {
                    "en_US": "Tables",
                    "zh_Hans": "表"
                  },
                  "llm_description": "Specify which tables schema do you want to get as model context. Multi tables use comma to separate. Leave it blank if you want to get all tables schema.",
                  "max": null,
                  "min": null,
                  "name": "tables",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Choose the model.",
                    "zh_Hans": "选择模型。"
                  },
                  "label": {
                    "en_US": "Model",
                    "zh_Hans": "模型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": "llm",
                  "template": null,
                  "type": "model-selector"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional, Filling in this field will overwrite the database connection entered during authorization.",
                    "zh_Hans": "选填，填写后将覆盖授权时填写的数据库连接。"
                  },
                  "label": {
                    "en_US": "DB URI"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "db_uri",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Optional. For example {\"connect_args\": {\"ssl\": {\"ca\": \"/path/to/ca.pem\"}}}\nMore connection options can be found at https://docs.sqlalchemy.org/en/20/core/engines.html#sqlalchemy.create_engine\n",
                    "zh_Hans": "选填项。例如 {\"connect_args\": {\"ssl\": {\"ca\": \"/path/to/ca.pem\"}}}\n更多连接选项可参考 https://docs.sqlalchemy.org/en/20/core/engines.html#sqlalchemy.create_engine\n"
                  },
                  "label": {
                    "en_US": "DB Config Options",
                    "zh_Hans": "数据库连接配置选项"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "config_options",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "get the table schema from the database.",
                  "zh_Hans": "从数据库中获取表结构。"
                },
                "llm": "get the table schema from the database."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "hjlarry",
                "label": {
                  "en_US": "Get Table Schema"
                },
                "name": "table_schema"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Specify which tables schema you want to get. If not specified, all tables will be used. Multi tables use comma to separate.",
                    "zh_Hans": "指定想要哪些表的结构，如不指定，则使用所有表。多张表用半角逗号隔开。"
                  },
                  "label": {
                    "en_US": "Tables",
                    "zh_Hans": "表"
                  },
                  "llm_description": "Specify which tables schema you want to get. If not specified, all tables will be used. Multi tables use comma to separate.",
                  "max": null,
                  "min": null,
                  "name": "tables",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional, Filling in this field will overwrite the database connection entered during authorization.",
                    "zh_Hans": "选填，填写后将覆盖授权时填写的数据库连接。"
                  },
                  "label": {
                    "en_US": "DB URI"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "db_uri",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Optional. For example {\"connect_args\": {\"ssl\": {\"ca\": \"/path/to/ca.pem\"}}}\nMore connection options can be found at https://docs.sqlalchemy.org/en/20/core/engines.html#sqlalchemy.create_engine\n",
                    "zh_Hans": "选填项。例如 {\"connect_args\": {\"ssl\": {\"ca\": \"/path/to/ca.pem\"}}}\n更多连接选项可参考 https://docs.sqlalchemy.org/en/20/core/engines.html#sqlalchemy.create_engine\n"
                  },
                  "label": {
                    "en_US": "DB Config Options",
                    "zh_Hans": "数据库连接配置选项"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "config_options",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "run sql query on csv file.",
                  "zh_Hans": "运行在 CSV 文件上的 SQL 查询。"
                },
                "llm": "run sql query on csv file."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "hjlarry",
                "label": {
                  "en_US": "CSV Query"
                },
                "name": "csv_query"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The sql query. The table name is `csv`.",
                    "zh_Hans": "SQL 查询语句。 表名为 `csv`。"
                  },
                  "label": {
                    "en_US": "Query string",
                    "zh_Hans": "查询语句"
                  },
                  "llm_description": "The sql query. The table name is `csv`.",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The csv file.",
                    "zh_Hans": "csv 文件。"
                  },
                  "label": {
                    "en_US": "csv file",
                    "zh_Hans": "csv 文件"
                  },
                  "llm_description": "The csv file.",
                  "max": null,
                  "min": null,
                  "name": "file",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "file"
                },
                {
                  "auto_generate": null,
                  "default": "md",
                  "form": "form",
                  "human_description": {
                    "en_US": "Choose the output format.",
                    "zh_Hans": "选择输出格式。"
                  },
                  "label": {
                    "en_US": "Output format",
                    "zh_Hans": "输出格式"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "format",
                  "options": [
                    {
                      "label": {
                        "en_US": "JSON",
                        "zh_Hans": "JSON"
                      },
                      "value": "json"
                    },
                    {
                      "label": {
                        "en_US": "Markdown",
                        "zh_Hans": "Markdown"
                      },
                      "value": "md"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-15T12:23:59Z",
        "version_updated_at": "2025-04-15T12:23:59Z"
      },
      {
        "agent_strategy": {
          "identity": {
            "author": "hjlarry",
            "description": {
              "en_US": "The agent with MCP tool calls and common function calls.",
              "zh_Hans": "支持 MCP 工具调用和 function call 的 Agent。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "MCP Agent",
              "pt_BR": "MCP Agent",
              "zh_Hans": "MCP Agent"
            },
            "name": "mcp_agent",
            "tags": []
          },
          "strategies": [
            {
              "description": {
                "en_US": "Function Calling is a basic strategy for agent, model will use the tools provided to perform the task.",
                "pt_BR": "Function Calling is a basic strategy for agent, model will use the tools provided to perform the task.",
                "zh_Hans": "Function Calling 是一个基本的 Agent 策略，模型将使用提供的工具来执行任务。"
              },
              "identity": {
                "author": "Dify",
                "label": {
                  "en_US": "MCP FunctionCalling"
                },
                "name": "function_calling"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "label": {
                    "en_US": "Model",
                    "pt_BR": "Model",
                    "zh_Hans": "模型"
                  },
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": "tool-call&llm",
                  "template": null,
                  "type": "model-selector"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "label": {
                    "en_US": "Tools list",
                    "pt_BR": "Tools list",
                    "zh_Hans": "工具列表"
                  },
                  "max": null,
                  "min": null,
                  "name": "tools",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "array[tools]"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "label": {
                    "en_US": "MCP Server URL",
                    "zh_Hans": "MCP 服务器地址"
                  },
                  "max": null,
                  "min": null,
                  "name": "mcp_server",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": {
                    "type": "prompt_instruction"
                  },
                  "default": null,
                  "label": {
                    "en_US": "Instruction",
                    "pt_BR": "Instruction",
                    "zh_Hans": "指令"
                  },
                  "max": null,
                  "min": null,
                  "name": "instruction",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": {
                    "enabled": true
                  },
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "label": {
                    "en_US": "Query",
                    "pt_BR": "Query",
                    "zh_Hans": "查询"
                  },
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 3,
                  "label": {
                    "en_US": "Maxium Iterations",
                    "pt_BR": "Maxium Iterations",
                    "zh_Hans": "最大迭代次数"
                  },
                  "max": 30,
                  "min": 1,
                  "name": "maximum_iterations",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            }
          ]
        },
        "badges": [],
        "brief": {
          "en_US": "An agent strategy with MCP tool calls and common function calls.",
          "zh_Hans": "支持 MCP 工具调用和 function call 的 Agent 策略。"
        },
        "category": "agent-strategy",
        "created_at": "2025-03-14T11:45:09Z",
        "endpoint": {},
        "icon": "hjlarry/packages/agent/_assets/icon.svg",
        "index_id": "hjlarry___agent",
        "install_count": 12215,
        "introduction": "# MCP Agent Strategy\n\n[![Version](https://img.shields.io/badge/version-0.0.1-blue.svg)](https://github.com/hjlarry/dify-plugin-mcp_agent)\n[![Repo](https://img.shields.io/badge/repo-github-green.svg)](https://github.com/hjlarry/dify-plugin-mcp_agent)\n\nA Dify Agent strategy plugin that integrates MCP tool calls and common function calls capabilities.\n\n## Features\n\n- Full compatibility with official function call agent strategy\n- Seamless integration with MCP tool calls\n- Flexible MCP server connection options\n\n## Getting Started\n\n![agent](./_assets/agent.png)\n\n### Basic Configuration\n\nFor single MCP server setup, simply provide the server URL:\n\n```shell\nhttp://localhost:8000/sse\n```\n\n### Advanced Configuration\n\nFor multiple MCP servers with detailed connection parameters:\n```json\n{\n  \"server_name1\": {\n    \"url\": \"http://127.0.0.1:8000/sse\",\n    \"headers\": {},\n    \"timeout\": 5,\n    \"sse_read_timeout\": 300\n  },\n  \"server_name2\": {\n    \"url\": \"http://127.0.0.1:8001/sse\"\n  }\n}\n```\n\n\n## How to change MCP server from `stdio` to `sse` ?\n\n### Option 1: source code modification\n```python\nif __name__ == \"__main__\":\n    mcp.run(transport='sse')\n```\n\n### Option 2: using the [mcp-proxy](https://github.com/sparfenyuk/mcp-proxy)\n```shell\nuv tool install mcp-proxy\nmcp-proxy --sse-host=0.0.0.0 --sse-port=8080 uvx your-server\n```",
        "label": {
          "en_US": "MCP Agent Strategy",
          "zh_Hans": "MCP Agent 策略"
        },
        "latest_package_identifier": "hjlarry/agent:0.0.1@f42a5a80b1c77fd0655c755b70ad08da47ceb1acc3638cf13a0eb9ed42b3a128",
        "latest_version": "0.0.1",
        "model": {},
        "name": "agent",
        "org": "hjlarry",
        "plugin_id": "hjlarry/agent",
        "plugins": {
          "agent_strategies": [
            "provider/mcp_agent.yaml"
          ],
          "endpoints": null,
          "models": null,
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "agent"
          }
        ],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-03-14T11:45:15Z",
        "version_updated_at": "2025-03-14T11:45:15Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Fetch and call tools by MCP protocol through HTTP with SSE or Streamable HTTP transport.",
          "zh_Hans": "通过 HTTP with SSE 或 Streamable HTTP 传输方式使用 MCP 协议来发现和调用工具。"
        },
        "category": "tool",
        "created_at": "2025-03-14T11:47:34Z",
        "endpoint": {},
        "icon": "junjiem/packages/mcp_sse/_assets/icon.png",
        "index_id": "junjiem___mcp_sse",
        "install_count": 12026,
        "introduction": "## Dify 1.0 Plugin MCP HTTP with SSE or Streamable HTTP transport Tools\n\n\n**Author:** [Junjie.M](https://github.com/junjiem)  \n**Type:** tool  \n**Github Repo:** [https://github.com/junjiem/dify-plugin-tools-mcp_sse](https://github.com/junjiem/dify-plugin-tools-mcp_sse)  \n**Github Issues:** [issues](https://github.com/junjiem/dify-plugin-tools-mcp_sse/issues)\n\n\n---\n\n\n### Description\n\nFetch and call tools by MCP protocol through `HTTP with SSE` or `Streamable HTTP` transport.\n\n通过 `HTTP with SSE` 或 `Streamable HTTP` 传输方式使用 MCP 协议来发现和调用工具。\n\n![mcp_sse_plugin](_assets/mcp_sse_plugin.png)\n\n![mcp_sse_plugin_set_authorization](_assets/mcp_sse_plugin_set_authorization.png)\n\nMCP Servers config, support multiple MCP services. The following example:\n\nMCP服务配置，支持多个MCP服务。 如下示例：\n\n```json\n{\n  \"server_name1\": {\n    \"transport\": \"sse\",\n    \"url\": \"http://127.0.0.1:8000/sse\",\n    \"headers\": {},\n    \"timeout\": 60,\n    \"sse_read_timeout\": 300\n  },\n  \"server_name2\": {\n    \"transport\": \"sse\",\n    \"url\": \"http://127.0.0.1:8001/sse\"\n  },\n  \"server_name3\": {\n    \"transport\": \"streamable_http\",\n    \"url\": \"http://127.0.0.1:8002/mcp\",\n    \"headers\": {},\n    \"timeout\": 60\n  },\n  \"server_name4\": {\n    \"transport\": \"streamable_http\",\n    \"url\": \"http://127.0.0.1:8003/mcp\"\n  }\n}\n```\nOR\n```json\n{\n  \"mcpServers\": {\n      \"server_name1\": {\n        \"transport\": \"sse\",\n        \"url\": \"http://127.0.0.1:8000/sse\",\n        \"headers\": {},\n        \"timeout\": 60,\n        \"sse_read_timeout\": 300\n      },\n      \"server_name2\": {\n        \"transport\": \"sse\",\n        \"url\": \"http://127.0.0.1:8001/sse\"\n      },\n      \"server_name3\": {\n        \"transport\": \"streamable_http\",\n        \"url\": \"http://127.0.0.1:8002/mcp\",\n        \"headers\": {},\n        \"timeout\": 60\n      },\n      \"server_name4\": {\n        \"transport\": \"streamable_http\",\n        \"url\": \"http://127.0.0.1:8003/mcp\"\n      }\n    }\n}\n```\n\n> **Note:** \"transport\" parameter as `sse` or `streamable_http`, default `sse`.\n\n> **注：**  \"transport\" 参数为 `sse` 或 `streamable_http` ，默认为 `sse`。\n\n\n![agent_add_mcp_see_tools](_assets/agent_add_mcp_see_tools.png)\n\n\n\n---\n\n\n\n### Managed MCP Servers 托管的MCP服务器\n\nIf you want to try MCP but don't know how to deploy SSE transport's MCP Server, can you try connect to Managed MCP Servers.\n\n如果你想尝试 MCP，但是不知道如何部署 SSE 传输的 MCP Server，可以尝试连接托管的 MCP 服务器。\n\n#### Example 1  示例1\n\n[Composio Managed MCP Servers](https://mcp.composio.dev)\n\n[Composio 托管的 MCP 服务器](https://mcp.composio.dev)\n\n![composio_mcp_list](_assets/composio_mcp_list.png)\n\nReference Cursor Settings, shown below:\n\n参考 Cursor 设置，如下图：\n\n![composio_mcp_cursor](_assets/composio_mcp_cursor.png)\n![composio_mcp_cursor2](_assets/composio_mcp_cursor2.png)\n\nMCP Servers config, shown below:\n\nMCP 服务配置，如下示例：\n\n```json\n{\n  \"tavily\": {\n    \"url\": \"https://mcp.composio.dev/tavily/xxxx-xxxx-xxxx-xxxx\"\n  }\n}\n```\n\n\n\n#### Example 2  示例2\n\n[Zapier Managed MCP Servers](https://actions.zapier.com/settings/mcp)\n\n[Zapier 托管的 MCP 服务器](https://actions.zapier.com/settings/mcp)\n\nCopy the MCP Server URL for use in the Dify plug-in configuration.\n\n复制 MCP Server URL，在 Dify 插件配置中使用。\n\n![zapier_mcp_servers](_assets/zapier_mcp_servers.png)\n\nMCP Servers config, shown below:\n\nMCP 服务配置，如下示例：\n\n```json\n{\n  \"zapier-mcp\": {\n    \"url\": \"https://actions.zapier.com/mcp/sk-xxxxxxxxxx/sse\"\n  }\n}\n```\n\nClick \"Edit MCP Actions\" to go to the page for adding tools and actions.\n\n点击 “Edit MCP Actions” ，进入工具和操作的添加页面。\n\n![zapier_mcp_edit_actions](_assets/zapier_mcp_edit_actions.png)\n\nClick \"Add a new action\" to add the required MCP service instance.\n\n点击 “Add a new action”，添加需要的MCP服务实例。\n\n![zapier_mcp_add_actions](_assets/zapier_mcp_add_actions.png)\n\nYou can also continue to add different actions to enrich the tool set available to the Agent.\n\n你还可以继续添加不同的 Action，丰富 Agent 可用的工具集。\n\n\n\n#### Example 3  示例3\n\n[MCP.so Managed MCP Servers](https://mcp.so/playground)\n\n[MCP.so 托管的 MCP 服务器](https://mcp.so/playground)\n\n##### `Streamable HTTP`\n\n![mcpso_mcp_servers_streamable_http](_assets/mcpso_mcp_servers_streamable_http.png)\n\nMCP Servers config, shown below:\n\nMCP 服务配置，如下示例：\n\n```json\n{\n  \"tavily-mcp\": {\n    \"transport\": \"streamable_http\",\n    \"url\": \"https://router.mcp.so/mcp/xxxxxxxxxxx\"\n  }\n}\n```\n\n##### `SSE` \n\n![mcpso_mcp_servers_sse](_assets/mcpso_mcp_servers_sse.png)\n\nMCP Servers config, shown below:\n\nMCP 服务配置，如下示例：\n\n```json\n{\n  \"tavily-mcp\": {\n    \"url\": \"https://router.mcp.so/sse/xxxxxxxxxxx\"\n  }\n}\n```\n\n\n\n---\n\n\n\n### Installing Plugins via GitHub  通过 GitHub 安装插件\n\nCan install the plugin using the GitHub repository address. Visit the Dify platform's plugin management page, choose to install via GitHub, enter the repository address, select version number and package file to complete installation.\n\n可以通过 GitHub 仓库地址安装该插件。访问 Dify 平台的插件管理页，选择通过 GitHub 安装插件，输入仓库地址后，选择版本号和包文件完成安装。\n\n![install_plugin_via_github](_assets/install_plugin_via_github.png)\n\n![install_plugin_via_github](_assets/install_plugin_via_github_successfully.png)\n\n\n\n---\n\n\n\n### FAQ\n\n#### 1. How to Handle Errors When Installing Plugins? 安装插件时遇到异常应如何处理？\n\n**Issue**: If you encounter the error message: plugin verification has been enabled, and the plugin you want to install has a bad signature, how to handle the issue?\n\n**Solution**: Add the following line to the end of your .env configuration file: FORCE_VERIFYING_SIGNATURE=false\nOnce this field is added, the Dify platform will allow the installation of all plugins that are not listed (and thus not verified) in the Dify Marketplace.\n\n**问题描述**：安装插件时遇到异常信息：plugin verification has been enabled, and the plugin you want to install has a bad signature，应该如何处理？\n\n**解决办法**：在 .env 配置文件的末尾添加 FORCE_VERIFYING_SIGNATURE=false 字段即可解决该问题。\n添加该字段后，Dify 平台将允许安装所有未在 Dify Marketplace 上架（审核）的插件，可能存在安全隐患。\n\n\n#### 2. How to install the offline version 如何安装离线版本\n\nScripting tool for downloading Dify plugin package from Dify Marketplace and Github and repackaging [true] offline package (contains dependencies, no need to be connected to the Internet).\n\n从Dify市场和Github下载Dify插件包并重新打【真】离线包（包含依赖，不需要再联网）的脚本工具。\n\nGithub Repo: https://github.com/junjiem/dify-plugin-repackaging\n\n",
        "label": {
          "en_US": "MCP SSE / StreamableHTTP",
          "zh_Hans": "MCP SSE / StreamableHTTP"
        },
        "latest_package_identifier": "junjiem/mcp_sse:0.1.0@5a75f28f62f193346cd692bcb4621b4029fd05f9c33848c46b73199aaac5c17a",
        "latest_version": "0.1.0",
        "model": {},
        "name": "mcp_sse",
        "org": "junjiem",
        "plugin_id": "junjiem/mcp_sse",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/mcp_tool.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {}
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": "{\n  \"server_name\": {\n    \"url\": \"http://127.0.0.1:8000/sse\",\n    \"headers\": {},\n \"timeout\": 60,\n    \"sse_read_timeout\": 300\n  }\n}",
              "help": {
                "en_US": "MCP Servers config, support multiple MCP services.",
                "zh_Hans": "MCP服务配置，支持多个MCP服务。"
              },
              "label": {
                "en_US": "MCP Servers config",
                "zh_Hans": "MCP 服务配置"
              },
              "name": "servers_config",
              "options": null,
              "placeholder": null,
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            }
          ],
          "identity": {
            "author": "junjiem",
            "description": {
              "en_US": "Fetch and call tools by MCP protocol.",
              "zh_Hans": "使用 MCP 协议发现和调用工具。"
            },
            "icon": "icon.png",
            "label": {
              "en_US": "MCP tools",
              "zh_Hans": "发现和调用 MCP 工具"
            },
            "name": "mcp_sse",
            "tags": [
              "utilities"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Fetch MCP Server tools list.",
                  "zh_Hans": "获取 MCP 服务端的工具列表。"
                },
                "llm": "Fetch MCP Server tools list (Gets a list of MCP tools in addition to existing tools)."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "junjiem",
                "label": {
                  "en_US": "Fetch MCP Tools",
                  "zh_Hans": "获取 MCP 工具列表"
                },
                "name": "mcp_sse_list_tools"
              },
              "output_schema": null,
              "parameters": null
            },
            {
              "description": {
                "human": {
                  "en_US": "Call MCP Server tool.",
                  "zh_Hans": "调用 MCP 服务端工具。"
                },
                "llm": "Call MCP Server tool."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "junjiem",
                "label": {
                  "en_US": "Call MCP Tool",
                  "zh_Hans": "调用 MCP 工具"
                },
                "name": "mcp_sse_call_tool"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Name of the tool to execute.",
                    "zh_Hans": "要执行的工具的名称。"
                  },
                  "label": {
                    "en_US": "Tool Name",
                    "zh_Hans": "工具名称"
                  },
                  "llm_description": "Name of the tool to execute.",
                  "max": null,
                  "min": null,
                  "name": "tool_name",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Tool arguments (JSON string in the python dict[str, Any] format).",
                    "zh_Hans": "工具的参数。"
                  },
                  "label": {
                    "en_US": "Arguments",
                    "zh_Hans": "参数"
                  },
                  "llm_description": "Tool arguments (JSON string in the python dict[str, Any] format).",
                  "max": null,
                  "min": null,
                  "name": "arguments",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-21T20:51:35Z",
        "version_updated_at": "2025-04-21T20:51:35Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Wikipedia is a free online encyclopedia, created and edited by volunteers around the world.",
          "pt_BR": "Wikipedia is a free online encyclopedia, created and edited by volunteers around the world.",
          "zh_Hans": "维基百科是一个由全世界的志愿者创建和编辑的免费在线百科全书。"
        },
        "category": "tool",
        "created_at": "2024-12-04T04:52:01Z",
        "endpoint": {},
        "icon": "langgenius/packages/wikipedia/_assets/icon.svg",
        "index_id": "langgenius___wikipedia",
        "install_count": 11677,
        "introduction": "# Wikipedia Tool\n\n## Overview\n\nWikipedia is a free, open-source online encyclopedia that provides a vast repository of information. It offers a powerful search functionality that enables users to find articles on various topics. Wikipedia tool also allows for programmatic access, facilitating the extraction of article snippets and entire webpages.\n\n## Configuration\n\n### 1. Get Wikipedia tools from Plugin Marketplace\nThe Wikipedia tools could be found at the Plugin Marketplace, please install it first.\n\n![](./_assets/wikipedia_1.png)\n\n### 2. Use the tool\nYou can use the Wikipedia tool in the following application types.\n\n![](./_assets/wikipedia_2.png)\n\n#### Chatflow / Workflow applications\n\nBoth Chatflow and Workflow applications support adding Wikipedia tool nodes.\n\n#### Agent applications\n\nAdd the Wikipedia tool in the Agent application, then enter the online search command to call this tool.",
        "label": {
          "en_US": "Wikipedia",
          "pt_BR": "Wikipedia",
          "zh_Hans": "维基百科"
        },
        "latest_package_identifier": "langgenius/wikipedia:0.0.3@c15c50172ae5abf681847180509a8df32d5944c3be3c91066d61c931b82b3470",
        "latest_version": "0.0.3",
        "model": {},
        "name": "wikipedia",
        "org": "langgenius",
        "plugin_id": "langgenius/wikipedia",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/wikipedia.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "social"
          }
        ],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "langgenius",
            "description": {
              "en_US": "Wikipedia is a free online encyclopedia, created and edited by volunteers around the world.",
              "pt_BR": "Wikipedia is a free online encyclopedia, created and edited by volunteers around the world.",
              "zh_Hans": "维基百科是一个由全世界的志愿者创建和编辑的免费在线百科全书。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Wikipedia",
              "pt_BR": "Wikipedia",
              "zh_Hans": "维基百科"
            },
            "name": "wikipedia",
            "tags": [
              "social"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool for performing a Wikipedia search and extracting snippets and webpages.",
                  "pt_BR": "A tool for performing a Wikipedia search and extracting snippets and webpages.",
                  "zh_Hans": "一个用于执行维基百科搜索并提取片段和网页的工具。"
                },
                "llm": "A tool for performing a Wikipedia search and extracting snippets and webpages. Input should be a search query."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "WikipediaSearch",
                  "pt_BR": "WikipediaSearch",
                  "zh_Hans": "维基百科搜索"
                },
                "name": "wikipedia_search"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "key words for searching",
                    "pt_BR": "key words for searching",
                    "zh_Hans": "查询关键词"
                  },
                  "label": {
                    "en_US": "Query string",
                    "pt_BR": "Query string",
                    "zh_Hans": "查询语句"
                  },
                  "llm_description": "key words for searching, this should be in the language of \"language\" parameter",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The language of the Wikipedia to be searched",
                    "zh_Hans": "要搜索的维基百科语言"
                  },
                  "label": {
                    "en_US": "Language",
                    "zh_Hans": "语言"
                  },
                  "llm_description": "language of the wikipedia to be searched, only \"de\" for German, \"en\" for English, \"fr\" for French, \"hi\" for Hindi, \"ja\" for Japanese, \"ko\" for Korean, \"pl\" for Polish, \"pt\" for Portuguese, \"ro\" for Romanian, \"uk\" for Ukrainian, \"vi\" for Vietnamese, and \"zh\" for Chinese are supported",
                  "max": null,
                  "min": null,
                  "name": "language",
                  "options": [
                    {
                      "label": {
                        "en_US": "German",
                        "zh_Hans": "德语"
                      },
                      "value": "de"
                    },
                    {
                      "label": {
                        "en_US": "English",
                        "zh_Hans": "英语"
                      },
                      "value": "en"
                    },
                    {
                      "label": {
                        "en_US": "French",
                        "zh_Hans": "法语"
                      },
                      "value": "fr"
                    },
                    {
                      "label": {
                        "en_US": "Hindi",
                        "zh_Hans": "印地语"
                      },
                      "value": "hi"
                    },
                    {
                      "label": {
                        "en_US": "Japanese",
                        "zh_Hans": "日语"
                      },
                      "value": "ja"
                    },
                    {
                      "label": {
                        "en_US": "Korean",
                        "zh_Hans": "韩语"
                      },
                      "value": "ko"
                    },
                    {
                      "label": {
                        "en_US": "Polish",
                        "zh_Hans": "波兰语"
                      },
                      "value": "pl"
                    },
                    {
                      "label": {
                        "en_US": "Portuguese",
                        "zh_Hans": "葡萄牙语"
                      },
                      "value": "pt"
                    },
                    {
                      "label": {
                        "en_US": "Romanian",
                        "zh_Hans": "罗马尼亚语"
                      },
                      "value": "ro"
                    },
                    {
                      "label": {
                        "en_US": "Ukrainian",
                        "zh_Hans": "乌克兰语"
                      },
                      "value": "uk"
                    },
                    {
                      "label": {
                        "en_US": "Vietnamese",
                        "zh_Hans": "越南语"
                      },
                      "value": "vi"
                    },
                    {
                      "label": {
                        "en_US": "Chinese",
                        "zh_Hans": "中文"
                      },
                      "value": "zh"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:04:27Z",
        "version_updated_at": "2025-02-17T07:04:27Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "A privacy-focused search engine.",
          "zh_Hans": "一个注重隐私的搜索引擎。"
        },
        "category": "tool",
        "created_at": "2024-12-04T08:32:02Z",
        "endpoint": {},
        "icon": "langgenius/packages/duckduckgo/_assets/icon.svg",
        "index_id": "langgenius___duckduckgo",
        "install_count": 11097,
        "introduction": "# Duckduckgo\n\n## Overview\n\nDuckDuckGo is a search engine focused on privacy. It offers search capabilities for web pages, images, and provides translation services. DuckDuckGo also features a private AI chat interface, providing users with an AI assistant that prioritizes data protection.\n\n## Configuration\n\n### 1. Get DuckDuckGo tools from Plugin Marketplace\n\nThe DuckDuckGo tools could be found at the Plugin Marketplace, please install it first.\n\n![](./_assets/duckduckgo_1.PNG)\n\n### 2. Use the tool\n\nYou can use the DuckDuckGo tool in the following application types.\n\n![](./_assets/duckduckgo_2.PNG)\n\n#### - Chatflow / Workflow applications\n\nBoth Chatflow and Workflow applications support adding DuckDuckGo tool nodes, it provides four tools: ai chatbox, image search, simple search, and translation.\n\n#### - Agent applications\n\nAdd the DuckDuckGo tool in the Agent application, then enter the search command to call this tool.",
        "label": {
          "en_US": "DuckDuckGo"
        },
        "latest_package_identifier": "langgenius/duckduckgo:0.0.5@dcefef02ee5bffdc6587b519e92b0247bed871881f05a756277f24a516f136f4",
        "latest_version": "0.0.5",
        "model": {},
        "name": "duckduckgo",
        "org": "langgenius",
        "plugin_id": "langgenius/duckduckgo",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/duckduckgo.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "yash_parmar",
            "description": {
              "en_US": "A privacy-focused search engine.",
              "zh_Hans": "一个注重隐私的搜索引擎。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "DuckDuckGo",
              "zh_Hans": "DuckDuckGo"
            },
            "name": "duckduckgo",
            "tags": [
              "search"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Use the anonymous private chat provided by DuckDuckGo.",
                  "zh_Hans": "使用DuckDuckGo提供的匿名私密聊天。"
                },
                "llm": "Use the anonymous private chat provided by DuckDuckGo."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "hjlarry",
                "label": {
                  "en_US": "DuckDuckGo AI Chat",
                  "zh_Hans": "DuckDuckGo AI聊天"
                },
                "name": "ddgo_ai"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The chat content.",
                    "zh_Hans": "要聊天的内容。"
                  },
                  "label": {
                    "en_US": "Chat Content",
                    "zh_Hans": "聊天内容"
                  },
                  "llm_description": "Key words for chat",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "gpt-3.5",
                  "form": "form",
                  "human_description": {
                    "en_US": "used to select the model for AI chat.",
                    "zh_Hans": "用于选择使用AI聊天的模型"
                  },
                  "label": {
                    "en_US": "Choose Model",
                    "zh_Hans": "选择模型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": [
                    {
                      "label": {
                        "en_US": "GPT-4o-mini"
                      },
                      "value": "gpt-4o-mini"
                    },
                    {
                      "label": {
                        "en_US": "Claude 3"
                      },
                      "value": "claude-3-haiku"
                    },
                    {
                      "label": {
                        "en_US": "Llama 3"
                      },
                      "value": "llama-3-70b"
                    },
                    {
                      "label": {
                        "en_US": "Mixtral"
                      },
                      "value": "mixtral-8x7b"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Supports http/https/socks proxies. Example: http://user:pass@example.com:3128.",
                    "zh_Hans": "支持 http/https/socks 代理。示例：http://user:pass@example.com:3128。"
                  },
                  "label": {
                    "en_US": "Proxy server",
                    "zh_Hans": "代理服务器"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "proxy_server",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Perform image searches on DuckDuckGo and get results.",
                  "zh_Hans": "在 DuckDuckGo 上进行图片搜索并获取结果。"
                },
                "llm": "Perform image searches on DuckDuckGo and get results."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "hjlarry",
                "label": {
                  "en_US": "DuckDuckGo Image Search",
                  "zh_Hans": "DuckDuckGo 图片搜索"
                },
                "name": "ddgo_img"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The search query.",
                    "zh_Hans": "搜索查询语句。"
                  },
                  "label": {
                    "en_US": "Query string",
                    "zh_Hans": "查询语句"
                  },
                  "llm_description": "Key words for searching",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 3,
                  "form": "form",
                  "human_description": {
                    "en_US": "The max results.",
                    "zh_Hans": "最大结果数量"
                  },
                  "label": {
                    "en_US": "Max results",
                    "zh_Hans": "最大结果数量"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "max_results",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Use when querying results within a specific time range only.",
                    "zh_Hans": "只查询一定时间范围内的结果时使用"
                  },
                  "label": {
                    "en_US": "Result time limit",
                    "zh_Hans": "结果时间限制"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "timelimit",
                  "options": [
                    {
                      "label": {
                        "en_US": "current day",
                        "zh_Hans": "当天"
                      },
                      "value": "Day"
                    },
                    {
                      "label": {
                        "en_US": "current week",
                        "zh_Hans": "本周"
                      },
                      "value": "Week"
                    },
                    {
                      "label": {
                        "en_US": "current month",
                        "zh_Hans": "当月"
                      },
                      "value": "Month"
                    },
                    {
                      "label": {
                        "en_US": "current year",
                        "zh_Hans": "今年"
                      },
                      "value": "Year"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The size of the image to be searched.",
                    "zh_Hans": "要搜索的图片的大小"
                  },
                  "label": {
                    "en_US": "image size",
                    "zh_Hans": "图片大小"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "size",
                  "options": [
                    {
                      "label": {
                        "en_US": "small",
                        "zh_Hans": "小"
                      },
                      "value": "Small"
                    },
                    {
                      "label": {
                        "en_US": "medium",
                        "zh_Hans": "中"
                      },
                      "value": "Medium"
                    },
                    {
                      "label": {
                        "en_US": "large",
                        "zh_Hans": "大"
                      },
                      "value": "Large"
                    },
                    {
                      "label": {
                        "en_US": "xl",
                        "zh_Hans": "超大"
                      },
                      "value": "Wallpaper"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Supports http/https/socks proxies. Example: http://user:pass@example.com:3128.",
                    "zh_Hans": "支持 http/https/socks 代理。示例：http://user:pass@example.com:3128。"
                  },
                  "label": {
                    "en_US": "Proxy server",
                    "zh_Hans": "代理服务器"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "proxy_server",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Perform searches on DuckDuckGo and get results.",
                  "zh_Hans": "在 DuckDuckGo 上进行搜索并获取结果。"
                },
                "llm": "Perform searches on DuckDuckGo and get results."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "yash_parmar",
                "label": {
                  "en_US": "DuckDuckGo Search",
                  "zh_Hans": "DuckDuckGo 搜索"
                },
                "name": "ddgo_search"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The search query.",
                    "zh_Hans": "搜索查询语句。"
                  },
                  "label": {
                    "en_US": "Query string",
                    "zh_Hans": "查询语句"
                  },
                  "llm_description": "Key words for searching",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 5,
                  "form": "form",
                  "human_description": {
                    "en_US": "The maximum number of results to return.",
                    "zh_Hans": "最大结果数量"
                  },
                  "label": {
                    "en_US": "Max results",
                    "zh_Hans": "最大结果数量"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "max_results",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to pass the search results to llm for summarization.",
                    "zh_Hans": "是否需要将搜索结果传给大模型总结"
                  },
                  "label": {
                    "en_US": "Require Summary",
                    "zh_Hans": "是否总结"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "require_summary",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Supports http/https/socks proxies. Example: http://user:pass@example.com:3128.",
                    "zh_Hans": "支持 http/https/socks 代理。示例：http://user:pass@example.com:3128。"
                  },
                  "label": {
                    "en_US": "Proxy server",
                    "zh_Hans": "代理服务器"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "proxy_server",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Use DuckDuckGo's translation feature.",
                  "zh_Hans": "使用DuckDuckGo的翻译功能。"
                },
                "llm": "Use DuckDuckGo's translation feature."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "hjlarry",
                "label": {
                  "en_US": "DuckDuckGo Translate",
                  "zh_Hans": "DuckDuckGo 翻译"
                },
                "name": "ddgo_translate"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The translate content.",
                    "zh_Hans": "要翻译的内容。"
                  },
                  "label": {
                    "en_US": "Translate Content",
                    "zh_Hans": "翻译内容"
                  },
                  "llm_description": "Key words for translate",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "en",
                  "form": "form",
                  "human_description": {
                    "en_US": "select the language to translate.",
                    "zh_Hans": "选择要翻译的语言"
                  },
                  "label": {
                    "en_US": "Choose Language",
                    "zh_Hans": "选择语言"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "translate_to",
                  "options": [
                    {
                      "label": {
                        "en_US": "English",
                        "zh_Hans": "英语"
                      },
                      "value": "en"
                    },
                    {
                      "label": {
                        "en_US": "Simplified Chinese",
                        "zh_Hans": "简体中文"
                      },
                      "value": "zh-Hans"
                    },
                    {
                      "label": {
                        "en_US": "Traditional Chinese",
                        "zh_Hans": "繁体中文"
                      },
                      "value": "zh-Hant"
                    },
                    {
                      "label": {
                        "en_US": "Japanese",
                        "zh_Hans": "日语"
                      },
                      "value": "ja"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Supports http/https/socks proxies. Example: http://user:pass@example.com:3128.",
                    "zh_Hans": "支持 http/https/socks 代理。示例：http://user:pass@example.com:3128。"
                  },
                  "label": {
                    "en_US": "Proxy server",
                    "zh_Hans": "代理服务器"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "proxy_server",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-30T05:38:45Z",
        "version_updated_at": "2025-03-30T05:38:45Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Wecom group bot",
          "pt_BR": "Wecom group bot",
          "zh_Hans": "企业微信群机器人"
        },
        "category": "tool",
        "created_at": "2024-11-29T09:25:19Z",
        "endpoint": {},
        "icon": "langgenius/packages/wecom/_assets/icon.png",
        "index_id": "langgenius___wecom",
        "install_count": 10596,
        "introduction": "# WeCom\n\n## Overview\n\nWeCom (formerly WeChat Work) is a communication and collaboration platform designed for businesses. It provides features like instant messaging, group chats (including the ability to send group messages), video conferencing, and work calendars.\n\n## Configuration\n\n### 1. Create a WeCom Group Robot and get Webhook Key\n\n1. Login to WeCom and click the \"Group Tools\" from the upper right corner from one group chat page.\n\n2. Click the \"Add Group Robot\" button.\n\n3. Enter the robot's name, and click \"Add Robot\" from the pop-up box.\n\n4. Copy the Webhook URL\n\n### 2. Get WeCom tools from Plugin Marketplace\nThe WeCom tools could be found at the Plugin Marketplace, please install it.\n\n![](./_assets/wecom_1.png)\n\n### 3. Using the tool\nYou can use the WeCom tool in the following application types.\n\n#### Chatflow / Workflow applications\nBoth Chatflow and Workflow applications support adding a WeCom tool node and fill in the Webhook Key.\n\n#### Agent applications\nAdd the WeCom tool in the Agent application, then enter the Webhook Key, and send the group message to call the tool.",
        "label": {
          "en_US": "Wecom",
          "pt_BR": "Wecom",
          "zh_Hans": "企业微信"
        },
        "latest_package_identifier": "langgenius/wecom:0.0.2@13392834d29569db50915818a9bc93dae67260b29a98885945ecc35dc0e8aab4",
        "latest_version": "0.0.2",
        "model": {},
        "name": "wecom",
        "org": "langgenius",
        "plugin_id": "langgenius/wecom",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/wecom.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "social"
          }
        ],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "Bowen Liang",
            "description": {
              "en_US": "Wecom group bot",
              "pt_BR": "Wecom group bot",
              "zh_Hans": "企业微信群机器人"
            },
            "icon": "icon.png",
            "label": {
              "en_US": "Wecom",
              "pt_BR": "Wecom",
              "zh_Hans": "企业微信"
            },
            "name": "wecom",
            "tags": [
              "social"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Sending a group message on Wecom via the webhook of group bot",
                  "pt_BR": "Sending a group message on Wecom via the webhook of group bot",
                  "zh_Hans": "通过企业微信的群机器人webhook发送群消息"
                },
                "llm": "A tool for sending messages to a chat group on Wecom(企业微信) ."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Bowen Liang",
                "label": {
                  "en_US": "Send Group Message",
                  "pt_BR": "Send Group Message",
                  "zh_Hans": "发送群消息"
                },
                "name": "wecom_group_bot"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Wecom Group bot webhook key",
                    "pt_BR": "Wecom Group bot webhook key",
                    "zh_Hans": "群机器人webhook的key"
                  },
                  "label": {
                    "en_US": "Wecom Group bot webhook key",
                    "pt_BR": "Wecom Group bot webhook key",
                    "zh_Hans": "群机器人webhook的key"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "hook_key",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Content to sent to the group.",
                    "pt_BR": "Content to sent to the group.",
                    "zh_Hans": "群消息文本"
                  },
                  "label": {
                    "en_US": "content",
                    "pt_BR": "content",
                    "zh_Hans": "消息内容"
                  },
                  "llm_description": "Content of the message",
                  "max": null,
                  "min": null,
                  "name": "content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "text",
                  "form": "form",
                  "human_description": {
                    "en_US": "Wecom Group bot message type",
                    "pt_BR": "Wecom Group bot message type",
                    "zh_Hans": "群机器人webhook的消息类型"
                  },
                  "label": {
                    "en_US": "Wecom Group bot message type",
                    "pt_BR": "Wecom Group bot message type",
                    "zh_Hans": "群机器人webhook的消息类型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "message_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "Text",
                        "pt_BR": "Text",
                        "zh_Hans": "文本"
                      },
                      "value": "text"
                    },
                    {
                      "label": {
                        "en_US": "Markdown",
                        "pt_BR": "Markdown",
                        "zh_Hans": "Markdown"
                      },
                      "value": "markdown"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:09:06Z",
        "version_updated_at": "2025-02-17T07:09:06Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Export Markdown to DOCX, PPTX, XLSX, PDF, HTML, MD, CSV, JSON, XML, LaTex files, and extract code blocks to Python, Bash, JS and etc files.",
          "ja_JP": "MarkdownをDOCX、PPTX、XLSX、PDF、HTML、MD、CSV、JSON、XML、LaTexファイルとしてエクスポートし、さらにコードブロックを各種スクリプトファイルとしてエクスポートします",
          "zh_Hans": "导出 Markdown 为 DOCX, PPTX, XLSX, PDF, HTML, MD, CSV, JSON, XML, LaTex 文件, 并将代码块导出为各类脚本文件(Python, JS, Bash等)。"
        },
        "category": "tool",
        "created_at": "2025-03-04T14:20:23Z",
        "endpoint": {},
        "icon": "bowenliang123/packages/md_exporter/_assets/icon.svg",
        "index_id": "bowenliang123___md_exporter",
        "install_count": 10525,
        "introduction": "# Markdown Exporter - Generate files from Mardown\n\n**Author:** [bowenliang123](https://github.com/bowenliang123)\n\n**Github Repository:** https://github.com/bowenliang123/md_exporter\n\n**Dify Marketplace:** https://marketplace.dify.ai/plugins/bowenliang123/md_exporter\n\n## Description\n\nThis Dify plugin `md_exporter` provides tools to export Markdown text to DOCX, PPTX, XLSX, PDF, HTML, MD, CSV, JSON, XML, LaTex, RST files, and extract code blocks to snippet files as `.py`, `.sh` , `.js`, `.xml` file, and etc.\n\n<table>\n  <tr>\n    <th>Tool</th>\n    <th>\n    \tInput\n    \t<p>(Syntax)</p>\n    </th>\n    <th>Output</th>\n  </tr>\n  <tr>\n    <td><code>md_to_docx</code></td>\n    <td rowspan=\"6\">\n      <a href=\"https://daringfireball.net/projects/markdown/syntax\">Markdown text</a>\n    </td>\n    <td>Word file (.docx)</td>\n  </tr>\n  <tr>\n    <td><code>md_to_html</code></td>\n    <td>HTML file (.html)</td>\n  </tr>\n  <tr>\n    <td><code>md_to_pdf</code></td>\n    <td>PDF file (.pdf)</td>\n  </tr>\n  <tr>\n    <td><code>md_to_md</code></td>\n    <td>Markdown file (.md)</td>\n  </tr>\n  <tr>\n    <td><code>md_to_xml</code></td>\n    <td>XML file (.xml)</td>\n  </tr>\n  <tr>\n    <td><code>md_to_rst</code></td>\n    <td>\n      <p>reStructuredText file (.rst)</p>\n      [with basic syntax support]\n    </td>\n  </tr>\n  <tr>\n    <td><code>md_to_pptx</code></td>\n    <td>\n      <div>\n        Markdown slides\n      </a>\n      </div>\n      <div>\n      with <a href=\"https://github.com/MartinPacker/md2pptx/blob/master/docs/user-guide.md#creating-slides\"> md2pptx </a> style\n      </div>\n    </td>\n    <td>PowerPoint file (.pptx)</td>\n  </tr>\n  <tr>\n    <td><code>md_to_codeblock</code></td>\n    <td>\n      <div>\n      <a href=\"https://www.markdownguide.org/extended-syntax/#fenced-code-blocks\">\n        Code Blocks\n      </a>\n      </div>\n      <div>\n         in Markdown text\n      </div>\n    </td>\n    <td>\n      Generating files by language:\n      <ul>\n          <li>python → .py file</li>\n          <li>javascript → .js file</li>\n          <li>html → .html file</li>\n          <li>bash → .sh file</li>\n          <li>json → .json file</li>\n          <li>xml → .xml file</li>\n          <li>svg → .svg file</li>\n          <li>css → .css file</li>\n          <li>yaml → .yaml file</li>\n          <li>ruby → .rb file</li>\n          <li>java → .java file</li>\n          <li>php → .php file</li>\n          <li>markdown → .md file</li>\n      </ul>\n      <div>\n      Or a ZIP file of codeblock files.\n      </div>\n    </td>\n  </tr>\n  <tr>\n    <td><code>md_to_linked_image</code></td>\n    <td>\n      <div>\n      <a href=\"https://www.markdownguide.org/basic-syntax/#linking-images\">\n        Linked images\n      </a>\n      </div>\n      <div>\n         in Markdown text\n      </div>\n    </td>\n    <td>\n      <div>\n      Images files from the linked image URLs.\n      </div>\n      <div>\n      Only http or https URLs are supported.\n      </div>\n    </td>\n  </tr>\n  <tr>\n    <td><code>md_to_xlsx</code></td>\n    <td><a href=\"https://www.markdownguide.org/extended-syntax/#tables\">Markdown tables</a></td>\n    <td>Excel file (.xlsx)</td>\n  </tr>\n  <tr>\n    <td><code>md_to_csv</code></td>\n    <td rowspan=\"4\">\n      <a href=\"https://www.markdownguide.org/extended-syntax/#tables\">Single Markdown table</a>\n  </td>\n    <td>CSV file (.csv)</td>\n  </tr>\n  <tr>\n    <td><code>md_to_json</code></td>\n    <td>JSON file (.json)</td>\n  </tr>\n  <tr>\n    <td><code>md_to_latex</code></td>\n    <td>LaTeX file (.tex)</td>\n  </tr>\n</table>\n\n## Usage\n![](_assets/usage_md_to_docx.png)\n\n\n## Tools\n\n### Markdown → DOCX\n![](_assets/md_to_docx_1.png)\n\n---\n\n### Markdown → XLSX\n\nInput Markdown text:\n\n```\n| Name    | Age | City        |\n|---------|-----|-------------|\n| Alice   | 30  | New York    |\n| Bowen   | 25  | Guangzhou   |\n| Charlie | 35  | Tokyo       |\n| David   | 40  | Miami       |\n```\n\n\noutput XLSX file:\n\n![](_assets/md_to_xlsx_1.png)\n\n---\n\n### Markdown → PPTX\nThe input Markdown text of slides must follows the syle rules of [md2pptx's  syntax](https://github.com/MartinPacker/md2pptx/blob/master/docs/user-guide.md#creating-slides).\n\n<details>\n\n```\n# This Is A Presentation Title Page\n\n## This Is A Presentation Section Page\n\n### This Is A Bulleted List Page\n\n* One\n    * One A\n    * One B\n* Two\n```\n</details>\n\n\n![](_assets/md_to_pptx_1.png)\n\n---\n\n### Markdown → HTML\n\n![](_assets/md_to_html_1.png)\n\n---\n\n### Markdown → PDF\n\n![](_assets/md_to_pdf_1.png)\n\n---\n\n### Markdown → Code Blocks files (.py/.sh/.html/.css, etc.)\n\n  Multiple generated files in formats by language type of the extracted code blocks:\n  <ul>\n      <li>python → .py file</li>\n      <li>javascript → .js file</li>\n      <li>html → .html file</li>\n      <li>bash → .sh file</li>\n      <li>json → .json file</li>\n      <li>xml → .xml file</li>\n      <li>svg → .svg file</li>\n      <li>css → .css file</li>\n      <li>yaml → .yaml file</li>\n      <li>ruby → .rb file</li>\n      <li>java → .java file</li>\n      <li>php → .php file</li>\n      <li>markdown → .md file</li>\n  </ul>\n\n![](_assets/usage_md_to_codeblock_2.png)\n\nIf compression is enabled, all the code blocks will be generated into a single ZIP file.\n![](_assets/usage_md_to_codeblock_3.png)\n![](_assets/usage_md_to_codeblock_4.png)\n\n---\n\n### Markdown → Linked Image files\n\n![](_assets/usage_md_to_linked_image_1.png)\n\n---\n\n### Markdown → RST (reStructedText)\n\nConverted .rst file by using mistune's RST render with basic reStructedText syntax support.\n\n![](_assets/md_to_rst_1.png)\n\n---\n\n### Markdown → CSV\n\n\n![](_assets/md_to_csv_1.png)\n\n\n---\n\n### Markdown → JSON\n\n![](_assets/md_to_json_1.png)\n\n---\n\n### Markdown → XML\n\n![](_assets/md_to_xml_1.png)\n\n---\n\n### Markdown → LaTeX\n\noutput LaTeX file:\n\n![](_assets/md_to_latex_1.png)\n\nviewed as PDF:\n\n![](_assets/md_to_latex_2.png)\n\n---\n\n### Markdown → Markdown\n\nOutput `.md` file with orginal input Markdown text.\n\n\n\n---\n\n## Changelog\n- 0.5.0:\n    -  Introducing `md_to_linked_image` tool, support extracting image files in links in Markdown text\n\n- 0.4.3:\n    - improve the display of Chinese characters in text paragraph in `md_to_docx` tool, by setting global font to Song if content contains Chinese     - improve the display of Chinese characters in text paragraph in `md_to_docx` tool, by setting global font to Song if content contains Chinese charactor\n\n- 0.4.2:\n    - support Java, PHP and Ruby file exporting in `md_to_codeblocks` tool\n\n- 0.4.1:\n    - support YAML file exporting in `md_to_codeblocks` tool\n\n- 0.4.0:\n    - support exporting Markdown codeblocks in to single zip file in `md_to_codeblocks` tool\n\n- 0.3.0:\n    - Fixed the error in importing libraries of `md_to_pptx` tool when running on self-hosted Dify plugin-daemon service\n\n- 0.2.0:\n    - Introducing `md_to_codeblock` tool, support extracting code blocks in Markdown to Python, JSON, JS, BASH, SVG, HTML, XML, MARKDOWN files. \n    - Introducing `md_to_rst` tool, support reStructuredText `.rst` file format as destination file format\n\n- 0.1.x:\n    - Introducing `md_to_pptx` tool, support PowerPoint `.pptx` file format as destination file format\n\n- 0.0.x:\n    - Published to Dify Marketplace\n    - support exporting Markdown to DOCX, PPTX, XLSX, PDF, HTML, MD, CSV, JSON, XML, LaTex files\n\n## Used Open sourced projects\n\nThis Dify plugin uses the following open sourced projects:\n\n- [html2docx](https://github.com/erezlife/html2docx), MIT License\n- [md2pptx](https://github.com/MartinPacker/md2pptx) , MIT License\n- [mistune](https://github.com/lepture/mistune), BSD 3-Clause License\n- [pandas](https://github.com/pandas-dev/pandas), BSD 3-Clause License\n- [python-pptx](https://github.com/scanny/python-pptx), MIT License\n- [xhtml2pdf](https://github.com/xhtml2pdf/xhtml2pdf), Apache License 2.0\n\n## License\n- Apache License 2.0\n\n\n## Privacy\n\nThis plugin collects no data.\n\nAll the file transformations are completed locally. NO data is transmitted to third-party services.\n",
        "label": {
          "en_US": "Markdown Exporter",
          "ja_JP": "Markdownエクスポーター",
          "zh_Hans": "Markdown 转换器"
        },
        "latest_package_identifier": "bowenliang123/md_exporter:0.5.0@7e9d1dd9aaac0e3206d44a90f5b1f993f27f0e6c4e6c61f0d937d28e386616a7",
        "latest_version": "0.5.0",
        "model": {},
        "name": "md_exporter",
        "org": "bowenliang123",
        "plugin_id": "bowenliang123/md_exporter",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/md_exporter.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 536870912,
          "permission": {
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "bowenliang123",
            "description": {
              "en_US": "Export Markdown to DOCX, PPTX, XLSX, PDF, HTML, MD, CSV, JSON, XML, LaTex files, and extract code blocks to Python, Bash, JS and etc files.",
              "ja_JP": "MarkdownをDOCX、PPTX、XLSX、PDF、HTML、MD、CSV、JSON、XML、LaTexファイルとしてエクスポートし、さらにコードブロックを各種スクリプトファイルとしてエクスポートします",
              "zh_Hans": "导出 Markdown 为 DOCX, PPTX, XLSX, PDF, HTML, MD, CSV, JSON, XML, LaTex 文件, 并将代码块导出为各类脚本文件(Python, JS, Bash等)。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Markdown Exporter",
              "ja_JP": "Markdownエクスポーター",
              "zh_Hans": "Markdown 转换器"
            },
            "name": "md_exporter",
            "tags": [
              "utilities"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool for generating DOCX file from Markdown text",
                  "zh_Hans": "一个用于将Markdown转换为DOCX文件的工具"
                },
                "llm": "A tool for generating DOCX file from Markdown text"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Bowen Liang",
                "label": {
                  "en_US": "Markdown to DOCX file",
                  "zh_Hans": "Markdown转Docx文件"
                },
                "name": "md_to_docx"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Markdown text",
                    "zh_Hans": "Markdown格式文本"
                  },
                  "label": {
                    "en_US": "Markdown text",
                    "zh_Hans": "Markdown格式文本"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "md_text",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for generating HTML file from Markdown.",
                  "zh_Hans": "一个用于将Markdown转换为HTML文件的工具"
                },
                "llm": "A tool for generating HTML file from Markdown text"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Bowen Liang",
                "label": {
                  "en_US": "Markdown to HTML file",
                  "zh_Hans": "Markdown转HTML文件"
                },
                "name": "md_to_html"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Markdown text",
                    "zh_Hans": "Markdown格式文本"
                  },
                  "label": {
                    "en_US": "Markdown text",
                    "zh_Hans": "Markdown格式文本"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "md_text",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for generating PDF file from Markdown text",
                  "zh_Hans": "一个用于将Markdown转换为PDF文件的工具"
                },
                "llm": "A tool for generating PDF file from Markdown text"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Bowen Liang",
                "label": {
                  "en_US": "Markdown to PDF file",
                  "zh_Hans": "Markdown转PDF文件"
                },
                "name": "md_to_pdf"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Markdown text",
                    "zh_Hans": "Markdown格式文本"
                  },
                  "label": {
                    "en_US": "Markdown text",
                    "zh_Hans": "Markdown格式文本"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "md_text",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for generating .md file from Markdown text",
                  "zh_Hans": "一个用于将Markdown转换为.md文件的工具"
                },
                "llm": "A tool for generating .md file from Markdown text"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Bowen Liang",
                "label": {
                  "en_US": "Markdown to md file",
                  "zh_Hans": "Markdown转md文件"
                },
                "name": "md_to_md"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Markdown text",
                    "zh_Hans": "Markdown格式文本"
                  },
                  "label": {
                    "en_US": "Markdown text",
                    "zh_Hans": "Markdown格式文本"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "md_text",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for generating XLSX file from Markdown text",
                  "zh_Hans": "一个用于将Markdown转换为XLSX文件的工具"
                },
                "llm": "A tool for generating XLSX file from Markdown text"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Bowen Liang",
                "label": {
                  "en_US": "Markdown to XLSX file",
                  "zh_Hans": "Markdown转XLSX文件"
                },
                "name": "md_to_xlsx"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Markdown table text",
                    "zh_Hans": "Markdown格式文本，必须为Markdown表格格式，可包含多个表格"
                  },
                  "label": {
                    "en_US": "Markdown text",
                    "zh_Hans": "Markdown格式文本"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "md_text",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for generating CSV file from Markdown text",
                  "zh_Hans": "一个用于将Markdown转换为CSV文件的工具"
                },
                "llm": "A tool for generating CSV file from Markdown text"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Bowen Liang",
                "label": {
                  "en_US": "Markdown to CSV file",
                  "zh_Hans": "Markdown转CSV文件"
                },
                "name": "md_to_csv"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Markdown text",
                    "zh_Hans": "Markdown格式文本，必须为Markdown表格格式"
                  },
                  "label": {
                    "en_US": "Markdown text",
                    "zh_Hans": "Markdown格式文本"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "md_text",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for generating JSON file from Markdown text",
                  "zh_Hans": "一个用于将Markdown转换为JSON文件的工具"
                },
                "llm": "A tool for generating JSON file from Markdown text"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Bowen Liang",
                "label": {
                  "en_US": "Markdown to JSON file",
                  "zh_Hans": "Markdown转JSON文件"
                },
                "name": "md_to_json"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Markdown table text",
                    "zh_Hans": "Markdown格式文本，必须为Markdown表格格式"
                  },
                  "label": {
                    "en_US": "Markdown text",
                    "zh_Hans": "Markdown格式文本"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "md_text",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for generating XML file from Markdown text",
                  "zh_Hans": "一个用于将Markdown转换为XML文件的工具"
                },
                "llm": "A tool for generating XML file from Markdown text"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Bowen Liang",
                "label": {
                  "en_US": "Markdown to XML file",
                  "zh_Hans": "Markdown转XML文件"
                },
                "name": "md_to_xml"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Markdown table text",
                    "zh_Hans": "Markdown格式文本，必须为Markdown表格格式"
                  },
                  "label": {
                    "en_US": "Markdown text",
                    "zh_Hans": "Markdown格式文本"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "md_text",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for generating LaTeX file from Markdown text",
                  "zh_Hans": "一个用于将Markdown转换为LaTeX文件的工具"
                },
                "llm": "A tool for generating LaTeX file from Markdown text"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Bowen Liang",
                "label": {
                  "en_US": "Markdown to LaTeX file",
                  "zh_Hans": "Markdown转LaTeX文件"
                },
                "name": "md_to_latex"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Markdown table text",
                    "zh_Hans": "Markdown格式文本，必须为Markdown表格格式"
                  },
                  "label": {
                    "en_US": "Markdown text",
                    "zh_Hans": "Markdown格式文本"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "md_text",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for generating PPTX file from Markdown text",
                  "zh_Hans": "一个用于将Markdown转换为PPTX文件的工具"
                },
                "llm": "A tool for generating PPTX file from Markdown text"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Bowen Liang",
                "label": {
                  "en_US": "Markdown to PPTX file",
                  "zh_Hans": "Markdown转PPTX文件"
                },
                "name": "md_to_pptx"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Markdown text，style docs：https://github.com/MartinPacker/md2pptx/blob/master/docs/user-guide.md#creating-slides",
                    "zh_Hans": "Markdown格式文本，样式文档： https://github.com/MartinPacker/md2pptx/blob/master/docs/user-guide.md#creating-slides"
                  },
                  "label": {
                    "en_US": "Markdown text",
                    "zh_Hans": "Markdown格式文本"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "md_text",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for generating RST file from Markdown text",
                  "zh_Hans": "一个用于将Markdown转换为RST文件的工具"
                },
                "llm": "A tool for generating RST file from Markdown text"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Bowen Liang",
                "label": {
                  "en_US": "Markdown to RST file",
                  "zh_Hans": "Markdown转RST文件"
                },
                "name": "md_to_rst"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Markdown text",
                    "zh_Hans": "Markdown格式文本"
                  },
                  "label": {
                    "en_US": "Markdown text",
                    "zh_Hans": "Markdown格式文本"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "md_text",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for generating files from code blocks from Markdown text",
                  "zh_Hans": "一个用于将Markdown中代码块转换为文件的工具"
                },
                "llm": "A tool for generating files from code blocks from Markdown text"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Bowen Liang",
                "label": {
                  "en_US": "Codeblocks to files",
                  "zh_Hans": "提取Codeblock为文件"
                },
                "name": "md_to_codeblock"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Markdown text",
                    "zh_Hans": "Markdown格式文本"
                  },
                  "label": {
                    "en_US": "Markdown text",
                    "zh_Hans": "Markdown格式文本"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "md_text",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "false",
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to generate into ZIP file",
                    "zh_Hans": "是否压缩为ZIP文件"
                  },
                  "label": {
                    "en_US": "Generate into ZIP file",
                    "zh_Hans": "是否压缩为ZIP文件"
                  },
                  "llm_description": "Whether to generate into ZIP file, default to \"false\"",
                  "max": null,
                  "min": null,
                  "name": "is_compress",
                  "options": [
                    {
                      "label": {
                        "en_US": "Yes",
                        "zh_Hans": "是"
                      },
                      "value": "true"
                    },
                    {
                      "label": {
                        "en_US": "No",
                        "zh_Hans": "否"
                      },
                      "value": "false"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for generating files from code blocks from Markdown text",
                  "zh_Hans": "一个用于将Markdown中代码块转换为文件的工具"
                },
                "llm": "A tool for generating files from code blocks from Markdown text"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Bowen Liang",
                "label": {
                  "en_US": "Image files extraction",
                  "zh_Hans": "提取图片链接为文件"
                },
                "name": "md_to_linked_image"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Markdown text",
                    "zh_Hans": "Markdown格式文本"
                  },
                  "label": {
                    "en_US": "Markdown text",
                    "zh_Hans": "Markdown格式文本"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "md_text",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-21T20:58:40Z",
        "version_updated_at": "2025-04-21T20:58:40Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "ZHIPU AI",
          "zh_Hans": "智谱 AI"
        },
        "category": "model",
        "created_at": "2024-12-03T09:14:42Z",
        "endpoint": {},
        "icon": "langgenius/packages/zhipuai/_assets/icon_s_en.svg",
        "index_id": "langgenius___zhipuai",
        "install_count": 10198,
        "introduction": "# Overview\nZhipu AI's ChatGLM is a series of advanced LLMs developed by Zhipu AI, designed to facilitate natural language understanding and generation. The ChatGLM models are particularly notable for their bilingual capabilities, excelling in both Chinese and English, and are optimized for various applications, including conversational agents, academic research, and business solutions.\n\n# Configure\nAfter installation, you need to get API keys from [Zhipu AI](https://open.bigmodel.cn/usercenter/apikeys) and setup in Settings -> Model Provider.\n\n![](_assets/zhipuai.png)",
        "label": {
          "en_US": "Zhipuai",
          "ja_JP": "Zhipuai",
          "pt_BR": "Zhipuai",
          "zh_Hans": "Zhipuai"
        },
        "latest_package_identifier": "langgenius/zhipuai:0.0.8@6ada678a71e64c072d5645ea6549e7abce6ef6693d3e5a7485214d669dddc1f1",
        "latest_version": "0.0.8",
        "model": {
          "background": "#EFF1FE",
          "configurate_methods": [
            "predefined-model"
          ],
          "description": {
            "en_US": "ZHIPU AI",
            "zh_Hans": "智谱 AI"
          },
          "help": {
            "title": {
              "en_US": "Get your API key from ZHIPU AI",
              "zh_Hans": "从智谱 AI 获取 API Key"
            },
            "url": {
              "en_US": "https://open.bigmodel.cn/usercenter/apikeys"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.svg",
            "zh_Hans": "icon_l_zh.svg"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "ZHIPU AI",
            "zh_Hans": "智谱 AI"
          },
          "model_credential_schema": null,
          "models": [
            {
              "deprecated": true,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "chatglm_lite"
              },
              "model": "chatglm_lite",
              "model_properties": {
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.9,
                  "help": {
                    "en_US": "Sampling temperature, controls the randomness of the output, must be a positive number. The value range is (0.0,1.0], which cannot be equal to 0. The default value is 0.95. The larger the value, the more random and creative the output will be; the smaller the value, The output will be more stable or certain. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "采样温度，控制输出的随机性，必须为正数取值范围是：(0.0,1.0]，不能等于 0,默认值为 0.95 值越大，会使输出更随机，更具创造性；值越小，输出会更加稳定或确定建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Another method of temperature sampling is called kernel sampling. The value range is (0.0, 1.0) open interval, which cannot be equal to 0 or 1. The default value is 0.7. The model considers the results with top_p probability mass tokens. For example 0.1 means The model decoder only considers tokens from the candidate set with the top 10% probability. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "用温度取样的另一种方法，称为核取样取值范围是：(0.0, 1.0) 开区间，不能等于 0 或 1，默认值为 0.7 模型考虑具有 top_p 概率质量tokens的结果例如：0.1 意味着模型解码器只考虑从前 10% 的概率的候选集中取 tokens 建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": true,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "chatglm_lite_32k"
              },
              "model": "chatglm_lite_32k",
              "model_properties": {
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.9,
                  "help": {
                    "en_US": "Sampling temperature, controls the randomness of the output, must be a positive number. The value range is (0.0,1.0], which cannot be equal to 0. The default value is 0.95. The larger the value, the more random and creative the output will be; the smaller the value, The output will be more stable or certain. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "采样温度，控制输出的随机性，必须为正数取值范围是：(0.0,1.0]，不能等于 0,默认值为 0.95 值越大，会使输出更随机，更具创造性；值越小，输出会更加稳定或确定建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Another method of temperature sampling is called kernel sampling. The value range is (0.0, 1.0) open interval, which cannot be equal to 0 or 1. The default value is 0.7. The model considers the results with top_p probability mass tokens. For example 0.1 means The model decoder only considers tokens from the candidate set with the top 10% probability. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "用温度取样的另一种方法，称为核取样取值范围是：(0.0, 1.0) 开区间，不能等于 0 或 1，默认值为 0.7 模型考虑具有 top_p 概率质量tokens的结果例如：0.1 意味着模型解码器只考虑从前 10% 的概率的候选集中取 tokens 建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": true,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "chatglm_pro"
              },
              "model": "chatglm_pro",
              "model_properties": {
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.9,
                  "help": {
                    "en_US": "Sampling temperature, controls the randomness of the output, must be a positive number. The value range is (0.0,1.0], which cannot be equal to 0. The default value is 0.95. The larger the value, the more random and creative the output will be; the smaller the value, The output will be more stable or certain. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "采样温度，控制输出的随机性，必须为正数取值范围是：(0.0,1.0]，不能等于 0,默认值为 0.95 值越大，会使输出更随机，更具创造性；值越小，输出会更加稳定或确定建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Another method of temperature sampling is called kernel sampling. The value range is (0.0, 1.0) open interval, which cannot be equal to 0 or 1. The default value is 0.7. The model considers the results with top_p probability mass tokens. For example 0.1 means The model decoder only considers tokens from the candidate set with the top 10% probability. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "用温度取样的另一种方法，称为核取样取值范围是：(0.0, 1.0) 开区间，不能等于 0 或 1，默认值为 0.7 模型考虑具有 top_p 概率质量tokens的结果例如：0.1 意味着模型解码器只考虑从前 10% 的概率的候选集中取 tokens 建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": true,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "chatglm_std"
              },
              "model": "chatglm_std",
              "model_properties": {
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.9,
                  "help": {
                    "en_US": "Sampling temperature, controls the randomness of the output, must be a positive number. The value range is (0.0,1.0], which cannot be equal to 0. The default value is 0.95. The larger the value, the more random and creative the output will be; the smaller the value, The output will be more stable or certain. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "采样温度，控制输出的随机性，必须为正数取值范围是：(0.0,1.0]，不能等于 0,默认值为 0.95 值越大，会使输出更随机，更具创造性；值越小，输出会更加稳定或确定建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Another method of temperature sampling is called kernel sampling. The value range is (0.0, 1.0) open interval, which cannot be equal to 0 or 1. The default value is 0.7. The model considers the results with top_p probability mass tokens. For example 0.1 means The model decoder only considers tokens from the candidate set with the top 10% probability. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "用温度取样的另一种方法，称为核取样取值范围是：(0.0, 1.0) 开区间，不能等于 0 或 1，默认值为 0.7 模型考虑具有 top_p 概率质量tokens的结果例如：0.1 意味着模型解码器只考虑从前 10% 的概率的候选集中取 tokens 建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": true,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "chatglm_turbo"
              },
              "model": "chatglm_turbo",
              "model_properties": {
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Sampling temperature, controls the randomness of the output, must be a positive number. The value range is (0.0,1.0], which cannot be equal to 0. The default value is 0.95. The larger the value, the more random and creative the output will be; the smaller the value, The output will be more stable or certain. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "采样温度，控制输出的随机性，必须为正数取值范围是：(0.0,1.0]，不能等于 0,默认值为 0.95 值越大，会使输出更随机，更具创造性；值越小，输出会更加稳定或确定建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Another method of temperature sampling is called kernel sampling. The value range is (0.0, 1.0) open interval, which cannot be equal to 0 or 1. The default value is 0.7. The model considers the results with top_p probability mass tokens. For example 0.1 means The model decoder only considers tokens from the candidate set with the top 10% probability. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "用温度取样的另一种方法，称为核取样取值范围是：(0.0, 1.0) 开区间，不能等于 0 或 1，默认值为 0.7 模型考虑具有 top_p 概率质量tokens的结果例如：0.1 意味着模型解码器只考虑从前 10% 的概率的候选集中取 tokens 建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "When `do_sample` is set to true, the sampling strategy is enabled. When `do_sample` is set to false, the sampling strategies such as `temperature` and `top_p` will not take effect. The default value is true.",
                    "zh_Hans": "do_sample 为 true 时启用采样策略，do_sample 为 false 时采样策略 temperature、top_p 将不生效。默认值为 true。"
                  },
                  "label": {
                    "en_US": "Sampling strategy",
                    "zh_Hans": "采样策略"
                  },
                  "max": null,
                  "min": null,
                  "name": "do_sample",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Used to control the type of content returned each time. When it is empty or does not have this field, it will be returned as json_string by default. json_string returns a standard JSON string, and text returns the original text content.",
                    "zh_Hans": "用于控制每次返回内容的类型，空或者没有此字段时默认按照 json_string 返回，json_string 返回标准的 JSON 字符串，text 返回原始的文本内容。"
                  },
                  "label": {
                    "en_US": "Return Type",
                    "zh_Hans": "回复类型"
                  },
                  "max": null,
                  "min": null,
                  "name": "return_type",
                  "options": [
                    "text",
                    "json_string"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "glm-4-0520"
              },
              "model": "glm-4-0520",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Sampling temperature, controls the randomness of the output, must be a positive number. The value range is (0.0,1.0], which cannot be equal to 0. The default value is 0.95. The larger the value, the more random and creative the output will be; the smaller the value, The output will be more stable or certain. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "采样温度，控制输出的随机性，必须为正数取值范围是：(0.0,1.0]，不能等于 0,默认值为 0.95 值越大，会使输出更随机，更具创造性；值越小，输出会更加稳定或确定建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Another method of temperature sampling is called kernel sampling. The value range is (0.0, 1.0) open interval, which cannot be equal to 0 or 1. The default value is 0.7. The model considers the results with top_p probability mass tokens. For example 0.1 means The model decoder only considers tokens from the candidate set with the top 10% probability. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "用温度取样的另一种方法，称为核取样取值范围是：(0.0, 1.0) 开区间，不能等于 0 或 1，默认值为 0.7 模型考虑具有 top_p 概率质量tokens的结果例如：0.1 意味着模型解码器只考虑从前 10% 的概率的候选集中取 tokens 建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "When `do_sample` is set to true, the sampling strategy is enabled. When `do_sample` is set to false, the sampling strategies such as `temperature` and `top_p` will not take effect. The default value is true.",
                    "zh_Hans": "do_sample 为 true 时启用采样策略，do_sample 为 false 时采样策略 temperature、top_p 将不生效。默认值为 true。"
                  },
                  "label": {
                    "en_US": "Sampling strategy",
                    "zh_Hans": "采样策略"
                  },
                  "max": null,
                  "min": null,
                  "name": "do_sample",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4095,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "web_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.1",
                "output": "0.1",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "glm-4-air-0111"
              },
              "model": "glm-4-air-0111",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Sampling temperature, controls the randomness of the output, must be a positive number. The value range is (0.0,1.0], which cannot be equal to 0. The default value is 0.95. The larger the value, the more random and creative the output will be; the smaller the value, The output will be more stable or certain. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "采样温度，控制输出的随机性，必须为正数取值范围是：(0.0,1.0]，不能等于 0,默认值为 0.95 值越大，会使输出更随机，更具创造性；值越小，输出会更加稳定或确定建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Another method of temperature sampling is called kernel sampling. The value range is (0.0, 1.0) open interval, which cannot be equal to 0 or 1. The default value is 0.7. The model considers the results with top_p probability mass tokens. For example 0.1 means The model decoder only considers tokens from the candidate set with the top 10% probability. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "用温度取样的另一种方法，称为核取样取值范围是：(0.0, 1.0) 开区间，不能等于 0 或 1，默认值为 0.7 模型考虑具有 top_p 概率质量tokens的结果例如：0.1 意味着模型解码器只考虑从前 10% 的概率的候选集中取 tokens 建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "When `do_sample` is set to true, the sampling strategy is enabled. When `do_sample` is set to false, the sampling strategies such as `temperature` and `top_p` will not take effect. The default value is true.",
                    "zh_Hans": "do_sample 为 true 时启用采样策略，do_sample 为 false 时采样策略 temperature、top_p 将不生效。默认值为 true。"
                  },
                  "label": {
                    "en_US": "Sampling strategy",
                    "zh_Hans": "采样策略"
                  },
                  "max": null,
                  "min": null,
                  "name": "do_sample",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4095,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "web_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.0005",
                "output": "0.0005",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "glm-4-air-250414"
              },
              "model": "glm-4-air-250414",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Sampling temperature, controls the randomness of the output, must be a positive number. The value range is (0.0,1.0], which cannot be equal to 0. The default value is 0.95. The larger the value, the more random and creative the output will be; the smaller the value, The output will be more stable or certain. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "采样温度，控制输出的随机性，必须为正数取值范围是：(0.0,1.0]，不能等于 0,默认值为 0.95 值越大，会使输出更随机，更具创造性；值越小，输出会更加稳定或确定建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Another method of temperature sampling is called kernel sampling. The value range is (0.0, 1.0) open interval, which cannot be equal to 0 or 1. The default value is 0.7. The model considers the results with top_p probability mass tokens. For example 0.1 means The model decoder only considers tokens from the candidate set with the top 10% probability. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "用温度取样的另一种方法，称为核取样取值范围是：(0.0, 1.0) 开区间，不能等于 0 或 1，默认值为 0.7 模型考虑具有 top_p 概率质量tokens的结果例如：0.1 意味着模型解码器只考虑从前 10% 的概率的候选集中取 tokens 建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "When `do_sample` is set to true, the sampling strategy is enabled. When `do_sample` is set to false, the sampling strategies such as `temperature` and `top_p` will not take effect. The default value is true.",
                    "zh_Hans": "do_sample 为 true 时启用采样策略，do_sample 为 false 时采样策略 temperature、top_p 将不生效。默认值为 true。"
                  },
                  "label": {
                    "en_US": "Sampling strategy",
                    "zh_Hans": "采样策略"
                  },
                  "max": null,
                  "min": null,
                  "name": "do_sample",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4095,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "web_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.0005",
                "output": "0.0005",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "glm-4-air"
              },
              "model": "glm-4-air",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Sampling temperature, controls the randomness of the output, must be a positive number. The value range is (0.0,1.0], which cannot be equal to 0. The default value is 0.95. The larger the value, the more random and creative the output will be; the smaller the value, The output will be more stable or certain. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "采样温度，控制输出的随机性，必须为正数取值范围是：(0.0,1.0]，不能等于 0,默认值为 0.95 值越大，会使输出更随机，更具创造性；值越小，输出会更加稳定或确定建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Another method of temperature sampling is called kernel sampling. The value range is (0.0, 1.0) open interval, which cannot be equal to 0 or 1. The default value is 0.7. The model considers the results with top_p probability mass tokens. For example 0.1 means The model decoder only considers tokens from the candidate set with the top 10% probability. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "用温度取样的另一种方法，称为核取样取值范围是：(0.0, 1.0) 开区间，不能等于 0 或 1，默认值为 0.7 模型考虑具有 top_p 概率质量tokens的结果例如：0.1 意味着模型解码器只考虑从前 10% 的概率的候选集中取 tokens 建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "When `do_sample` is set to true, the sampling strategy is enabled. When `do_sample` is set to false, the sampling strategies such as `temperature` and `top_p` will not take effect. The default value is true.",
                    "zh_Hans": "do_sample 为 true 时启用采样策略，do_sample 为 false 时采样策略 temperature、top_p 将不生效。默认值为 true。"
                  },
                  "label": {
                    "en_US": "Sampling strategy",
                    "zh_Hans": "采样策略"
                  },
                  "max": null,
                  "min": null,
                  "name": "do_sample",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4095,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "web_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.001",
                "output": "0.001",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "glm-4-airx"
              },
              "model": "glm-4-airx",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Sampling temperature, controls the randomness of the output, must be a positive number. The value range is (0.0,1.0], which cannot be equal to 0. The default value is 0.95. The larger the value, the more random and creative the output will be; the smaller the value, The output will be more stable or certain. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "采样温度，控制输出的随机性，必须为正数取值范围是：(0.0,1.0]，不能等于 0,默认值为 0.95 值越大，会使输出更随机，更具创造性；值越小，输出会更加稳定或确定建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Another method of temperature sampling is called kernel sampling. The value range is (0.0, 1.0) open interval, which cannot be equal to 0 or 1. The default value is 0.7. The model considers the results with top_p probability mass tokens. For example 0.1 means The model decoder only considers tokens from the candidate set with the top 10% probability. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "用温度取样的另一种方法，称为核取样取值范围是：(0.0, 1.0) 开区间，不能等于 0 或 1，默认值为 0.7 模型考虑具有 top_p 概率质量tokens的结果例如：0.1 意味着模型解码器只考虑从前 10% 的概率的候选集中取 tokens 建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "When `do_sample` is set to true, the sampling strategy is enabled. When `do_sample` is set to false, the sampling strategies such as `temperature` and `top_p` will not take effect. The default value is true.",
                    "zh_Hans": "do_sample 为 true 时启用采样策略，do_sample 为 false 时采样策略 temperature、top_p 将不生效。默认值为 true。"
                  },
                  "label": {
                    "en_US": "Sampling strategy",
                    "zh_Hans": "采样策略"
                  },
                  "max": null,
                  "min": null,
                  "name": "do_sample",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4095,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "web_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.01",
                "output": "0.01",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "glm-4-flash-250414"
              },
              "model": "glm-4-flash-250414",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Sampling temperature, controls the randomness of the output, must be a positive number. The value range is (0.0,1.0], which cannot be equal to 0. The default value is 0.95. The larger the value, the more random and creative the output will be; the smaller the value, The output will be more stable or certain. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "采样温度，控制输出的随机性，必须为正数取值范围是：(0.0,1.0]，不能等于 0,默认值为 0.95 值越大，会使输出更随机，更具创造性；值越小，输出会更加稳定或确定建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Another method of temperature sampling is called kernel sampling. The value range is (0.0, 1.0) open interval, which cannot be equal to 0 or 1. The default value is 0.7. The model considers the results with top_p probability mass tokens. For example 0.1 means The model decoder only considers tokens from the candidate set with the top 10% probability. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "用温度取样的另一种方法，称为核取样取值范围是：(0.0, 1.0) 开区间，不能等于 0 或 1，默认值为 0.7 模型考虑具有 top_p 概率质量tokens的结果例如：0.1 意味着模型解码器只考虑从前 10% 的概率的候选集中取 tokens 建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "When `do_sample` is set to true, the sampling strategy is enabled. When `do_sample` is set to false, the sampling strategies such as `temperature` and `top_p` will not take effect. The default value is true.",
                    "zh_Hans": "do_sample 为 true 时启用采样策略，do_sample 为 false 时采样策略 temperature、top_p 将不生效。默认值为 true。"
                  },
                  "label": {
                    "en_US": "Sampling strategy",
                    "zh_Hans": "采样策略"
                  },
                  "max": null,
                  "min": null,
                  "name": "do_sample",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4095,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "web_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "glm-4-flash"
              },
              "model": "glm-4-flash",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Sampling temperature, controls the randomness of the output, must be a positive number. The value range is (0.0,1.0], which cannot be equal to 0. The default value is 0.95. The larger the value, the more random and creative the output will be; the smaller the value, The output will be more stable or certain. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "采样温度，控制输出的随机性，必须为正数取值范围是：(0.0,1.0]，不能等于 0,默认值为 0.95 值越大，会使输出更随机，更具创造性；值越小，输出会更加稳定或确定建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Another method of temperature sampling is called kernel sampling. The value range is (0.0, 1.0) open interval, which cannot be equal to 0 or 1. The default value is 0.7. The model considers the results with top_p probability mass tokens. For example 0.1 means The model decoder only considers tokens from the candidate set with the top 10% probability. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "用温度取样的另一种方法，称为核取样取值范围是：(0.0, 1.0) 开区间，不能等于 0 或 1，默认值为 0.7 模型考虑具有 top_p 概率质量tokens的结果例如：0.1 意味着模型解码器只考虑从前 10% 的概率的候选集中取 tokens 建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "When `do_sample` is set to true, the sampling strategy is enabled. When `do_sample` is set to false, the sampling strategies such as `temperature` and `top_p` will not take effect. The default value is true.",
                    "zh_Hans": "do_sample 为 true 时启用采样策略，do_sample 为 false 时采样策略 temperature、top_p 将不生效。默认值为 true。"
                  },
                  "label": {
                    "en_US": "Sampling strategy",
                    "zh_Hans": "采样策略"
                  },
                  "max": null,
                  "min": null,
                  "name": "do_sample",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4095,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "web_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "glm-4-flashx-250414"
              },
              "model": "glm-4-flashx-250414",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Sampling temperature, controls the randomness of the output, must be a positive number. The value range is (0.0,1.0], which cannot be equal to 0. The default value is 0.95. The larger the value, the more random and creative the output will be; the smaller the value, The output will be more stable or certain. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "采样温度，控制输出的随机性，必须为正数取值范围是：(0.0,1.0]，不能等于 0,默认值为 0.95 值越大，会使输出更随机，更具创造性；值越小，输出会更加稳定或确定建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Another method of temperature sampling is called kernel sampling. The value range is (0.0, 1.0) open interval, which cannot be equal to 0 or 1. The default value is 0.7. The model considers the results with top_p probability mass tokens. For example 0.1 means The model decoder only considers tokens from the candidate set with the top 10% probability. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "用温度取样的另一种方法，称为核取样取值范围是：(0.0, 1.0) 开区间，不能等于 0 或 1，默认值为 0.7 模型考虑具有 top_p 概率质量tokens的结果例如：0.1 意味着模型解码器只考虑从前 10% 的概率的候选集中取 tokens 建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "When `do_sample` is set to true, the sampling strategy is enabled. When `do_sample` is set to false, the sampling strategies such as `temperature` and `top_p` will not take effect. The default value is true.",
                    "zh_Hans": "do_sample 为 true 时启用采样策略，do_sample 为 false 时采样策略 temperature、top_p 将不生效。默认值为 true。"
                  },
                  "label": {
                    "en_US": "Sampling strategy",
                    "zh_Hans": "采样策略"
                  },
                  "max": null,
                  "min": null,
                  "name": "do_sample",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4095,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "web_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "glm-4-flashx"
              },
              "model": "glm-4-flashx",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Sampling temperature, controls the randomness of the output, must be a positive number. The value range is (0.0,1.0], which cannot be equal to 0. The default value is 0.95. The larger the value, the more random and creative the output will be; the smaller the value, The output will be more stable or certain. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "采样温度，控制输出的随机性，必须为正数取值范围是：(0.0,1.0]，不能等于 0,默认值为 0.95 值越大，会使输出更随机，更具创造性；值越小，输出会更加稳定或确定建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Another method of temperature sampling is called kernel sampling. The value range is (0.0, 1.0) open interval, which cannot be equal to 0 or 1. The default value is 0.7. The model considers the results with top_p probability mass tokens. For example 0.1 means The model decoder only considers tokens from the candidate set with the top 10% probability. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "用温度取样的另一种方法，称为核取样取值范围是：(0.0, 1.0) 开区间，不能等于 0 或 1，默认值为 0.7 模型考虑具有 top_p 概率质量tokens的结果例如：0.1 意味着模型解码器只考虑从前 10% 的概率的候选集中取 tokens 建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "When `do_sample` is set to true, the sampling strategy is enabled. When `do_sample` is set to false, the sampling strategies such as `temperature` and `top_p` will not take effect. The default value is true.",
                    "zh_Hans": "do_sample 为 true 时启用采样策略，do_sample 为 false 时采样策略 temperature、top_p 将不生效。默认值为 true。"
                  },
                  "label": {
                    "en_US": "Sampling strategy",
                    "zh_Hans": "采样策略"
                  },
                  "max": null,
                  "min": null,
                  "name": "do_sample",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4095,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "web_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "glm-4v-flash"
              },
              "model": "glm-4v-flash",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Sampling temperature, controls the randomness of the output, must be a positive number. The value range is (0.0,1.0], which cannot be equal to 0. The default value is 0.95. The larger the value, the more random and creative the output will be; the smaller the value, The output will be more stable or certain. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "采样温度，控制输出的随机性，必须为正数取值范围是：(0.0,1.0]，不能等于 0,默认值为 0.95 值越大，会使输出更随机，更具创造性；值越小，输出会更加稳定或确定建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.6,
                  "help": {
                    "en_US": "Another method of temperature sampling is called kernel sampling. The value range is (0.0, 1.0) open interval, which cannot be equal to 0 or 1. The default value is 0.7. The model considers the results with top_p probability mass tokens. For example 0.1 means The model decoder only considers tokens from the candidate set with the top 10% probability. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "用温度取样的另一种方法，称为核取样取值范围是：(0.0, 1.0) 开区间，不能等于 0 或 1，默认值为 0.7 模型考虑具有 top_p 概率质量tokens的结果例如：0.1 意味着模型解码器只考虑从前 10% 的概率的候选集中取 tokens 建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "When `do_sample` is set to true, the sampling strategy is enabled. When `do_sample` is set to false, the sampling strategies such as `temperature` and `top_p` will not take effect. The default value is true.",
                    "zh_Hans": "do_sample 为 true 时启用采样策略，do_sample 为 false 时采样策略 temperature、top_p 将不生效。默认值为 true。"
                  },
                  "label": {
                    "en_US": "Sampling strategy",
                    "zh_Hans": "采样策略"
                  },
                  "max": null,
                  "min": null,
                  "name": "do_sample",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 1024,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "glm-z1-air"
              },
              "model": "glm-z1-air",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Sampling temperature, controls the randomness of the output, must be a positive number. The value range is (0.0,1.0], which cannot be equal to 0. The default value is 0.95. The larger the value, the more random and creative the output will be; the smaller the value, The output will be more stable or certain. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "采样温度，控制输出的随机性，必须为正数取值范围是：(0.0,1.0]，不能等于 0,默认值为 0.95 值越大，会使输出更随机，更具创造性；值越小，输出会更加稳定或确定建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Another method of temperature sampling is called kernel sampling. The value range is (0.0, 1.0) open interval, which cannot be equal to 0 or 1. The default value is 0.7. The model considers the results with top_p probability mass tokens. For example 0.1 means The model decoder only considers tokens from the candidate set with the top 10% probability. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "用温度取样的另一种方法，称为核取样取值范围是：(0.0, 1.0) 开区间，不能等于 0 或 1，默认值为 0.7 模型考虑具有 top_p 概率质量tokens的结果例如：0.1 意味着模型解码器只考虑从前 10% 的概率的候选集中取 tokens 建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "When `do_sample` is set to true, the sampling strategy is enabled. When `do_sample` is set to false, the sampling strategies such as `temperature` and `top_p` will not take effect. The default value is true.",
                    "zh_Hans": "do_sample 为 true 时启用采样策略，do_sample 为 false 时采样策略 temperature、top_p 将不生效。默认值为 true。"
                  },
                  "label": {
                    "en_US": "Sampling strategy",
                    "zh_Hans": "采样策略"
                  },
                  "max": null,
                  "min": null,
                  "name": "do_sample",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 30720,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.0005",
                "output": "0.0005",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "glm-z1-airx"
              },
              "model": "glm-z1-airx",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Sampling temperature, controls the randomness of the output, must be a positive number. The value range is (0.0,1.0], which cannot be equal to 0. The default value is 0.95. The larger the value, the more random and creative the output will be; the smaller the value, The output will be more stable or certain. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "采样温度，控制输出的随机性，必须为正数取值范围是：(0.0,1.0]，不能等于 0,默认值为 0.95 值越大，会使输出更随机，更具创造性；值越小，输出会更加稳定或确定建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Another method of temperature sampling is called kernel sampling. The value range is (0.0, 1.0) open interval, which cannot be equal to 0 or 1. The default value is 0.7. The model considers the results with top_p probability mass tokens. For example 0.1 means The model decoder only considers tokens from the candidate set with the top 10% probability. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "用温度取样的另一种方法，称为核取样取值范围是：(0.0, 1.0) 开区间，不能等于 0 或 1，默认值为 0.7 模型考虑具有 top_p 概率质量tokens的结果例如：0.1 意味着模型解码器只考虑从前 10% 的概率的候选集中取 tokens 建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "When `do_sample` is set to true, the sampling strategy is enabled. When `do_sample` is set to false, the sampling strategies such as `temperature` and `top_p` will not take effect. The default value is true.",
                    "zh_Hans": "do_sample 为 true 时启用采样策略，do_sample 为 false 时采样策略 temperature、top_p 将不生效。默认值为 true。"
                  },
                  "label": {
                    "en_US": "Sampling strategy",
                    "zh_Hans": "采样策略"
                  },
                  "max": null,
                  "min": null,
                  "name": "do_sample",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 30720,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.005",
                "output": "0.005",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "glm-z1-flash"
              },
              "model": "glm-z1-flash",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Sampling temperature, controls the randomness of the output, must be a positive number. The value range is (0.0,1.0], which cannot be equal to 0. The default value is 0.95. The larger the value, the more random and creative the output will be; the smaller the value, The output will be more stable or certain. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "采样温度，控制输出的随机性，必须为正数取值范围是：(0.0,1.0]，不能等于 0,默认值为 0.95 值越大，会使输出更随机，更具创造性；值越小，输出会更加稳定或确定建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Another method of temperature sampling is called kernel sampling. The value range is (0.0, 1.0) open interval, which cannot be equal to 0 or 1. The default value is 0.7. The model considers the results with top_p probability mass tokens. For example 0.1 means The model decoder only considers tokens from the candidate set with the top 10% probability. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "用温度取样的另一种方法，称为核取样取值范围是：(0.0, 1.0) 开区间，不能等于 0 或 1，默认值为 0.7 模型考虑具有 top_p 概率质量tokens的结果例如：0.1 意味着模型解码器只考虑从前 10% 的概率的候选集中取 tokens 建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "When `do_sample` is set to true, the sampling strategy is enabled. When `do_sample` is set to false, the sampling strategies such as `temperature` and `top_p` will not take effect. The default value is true.",
                    "zh_Hans": "do_sample 为 true 时启用采样策略，do_sample 为 false 时采样策略 temperature、top_p 将不生效。默认值为 true。"
                  },
                  "label": {
                    "en_US": "Sampling strategy",
                    "zh_Hans": "采样策略"
                  },
                  "max": null,
                  "min": null,
                  "name": "do_sample",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 30720,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "glm-z1-flashx"
              },
              "model": "glm-z1-flashx",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Sampling temperature, controls the randomness of the output, must be a positive number. The value range is (0.0,1.0], which cannot be equal to 0. The default value is 0.95. The larger the value, the more random and creative the output will be; the smaller the value, The output will be more stable or certain. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "采样温度，控制输出的随机性，必须为正数取值范围是：(0.0,1.0]，不能等于 0,默认值为 0.95 值越大，会使输出更随机，更具创造性；值越小，输出会更加稳定或确定建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Another method of temperature sampling is called kernel sampling. The value range is (0.0, 1.0) open interval, which cannot be equal to 0 or 1. The default value is 0.7. The model considers the results with top_p probability mass tokens. For example 0.1 means The model decoder only considers tokens from the candidate set with the top 10% probability. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "用温度取样的另一种方法，称为核取样取值范围是：(0.0, 1.0) 开区间，不能等于 0 或 1，默认值为 0.7 模型考虑具有 top_p 概率质量tokens的结果例如：0.1 意味着模型解码器只考虑从前 10% 的概率的候选集中取 tokens 建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "When `do_sample` is set to true, the sampling strategy is enabled. When `do_sample` is set to false, the sampling strategies such as `temperature` and `top_p` will not take effect. The default value is true.",
                    "zh_Hans": "do_sample 为 true 时启用采样策略，do_sample 为 false 时采样策略 temperature、top_p 将不生效。默认值为 true。"
                  },
                  "label": {
                    "en_US": "Sampling strategy",
                    "zh_Hans": "采样策略"
                  },
                  "max": null,
                  "min": null,
                  "name": "do_sample",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 30720,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "glm-3-turbo"
              },
              "model": "glm-3-turbo",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Sampling temperature, controls the randomness of the output, must be a positive number. The value range is (0.0,1.0], which cannot be equal to 0. The default value is 0.95. The larger the value, the more random and creative the output will be; the smaller the value, The output will be more stable or certain. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "采样温度，控制输出的随机性，必须为正数取值范围是：(0.0,1.0]，不能等于 0,默认值为 0.95 值越大，会使输出更随机，更具创造性；值越小，输出会更加稳定或确定建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Another method of temperature sampling is called kernel sampling. The value range is (0.0, 1.0) open interval, which cannot be equal to 0 or 1. The default value is 0.7. The model considers the results with top_p probability mass tokens. For example 0.1 means The model decoder only considers tokens from the candidate set with the top 10% probability. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "用温度取样的另一种方法，称为核取样取值范围是：(0.0, 1.0) 开区间，不能等于 0 或 1，默认值为 0.7 模型考虑具有 top_p 概率质量tokens的结果例如：0.1 意味着模型解码器只考虑从前 10% 的概率的候选集中取 tokens 建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "When `do_sample` is set to true, the sampling strategy is enabled. When `do_sample` is set to false, the sampling strategies such as `temperature` and `top_p` will not take effect. The default value is true.",
                    "zh_Hans": "do_sample 为 true 时启用采样策略，do_sample 为 false 时采样策略 temperature、top_p 将不生效。默认值为 true。"
                  },
                  "label": {
                    "en_US": "Sampling strategy",
                    "zh_Hans": "采样策略"
                  },
                  "max": null,
                  "min": null,
                  "name": "do_sample",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "web_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.001",
                "output": "0.001",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "glm-4"
              },
              "model": "glm-4",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Sampling temperature, controls the randomness of the output, must be a positive number. The value range is (0.0,1.0], which cannot be equal to 0. The default value is 0.95. The larger the value, the more random and creative the output will be; the smaller the value, The output will be more stable or certain. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "采样温度，控制输出的随机性，必须为正数取值范围是：(0.0,1.0]，不能等于 0,默认值为 0.95 值越大，会使输出更随机，更具创造性；值越小，输出会更加稳定或确定建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Another method of temperature sampling is called kernel sampling. The value range is (0.0, 1.0) open interval, which cannot be equal to 0 or 1. The default value is 0.7. The model considers the results with top_p probability mass tokens. For example 0.1 means The model decoder only considers tokens from the candidate set with the top 10% probability. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "用温度取样的另一种方法，称为核取样取值范围是：(0.0, 1.0) 开区间，不能等于 0 或 1，默认值为 0.7 模型考虑具有 top_p 概率质量tokens的结果例如：0.1 意味着模型解码器只考虑从前 10% 的概率的候选集中取 tokens 建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "When `do_sample` is set to true, the sampling strategy is enabled. When `do_sample` is set to false, the sampling strategies such as `temperature` and `top_p` will not take effect. The default value is true.",
                    "zh_Hans": "do_sample 为 true 时启用采样策略，do_sample 为 false 时采样策略 temperature、top_p 将不生效。默认值为 true。"
                  },
                  "label": {
                    "en_US": "Sampling strategy",
                    "zh_Hans": "采样策略"
                  },
                  "max": null,
                  "min": null,
                  "name": "do_sample",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4095,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "web_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.1",
                "output": "0.1",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "glm-4-long"
              },
              "model": "glm-4-long",
              "model_properties": {
                "context_size": 1048576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Sampling temperature, controls the randomness of the output, must be a positive number. The value range is (0.0,1.0], which cannot be equal to 0. The default value is 0.95. The larger the value, the more random and creative the output will be; the smaller the value, The output will be more stable or certain. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "采样温度，控制输出的随机性，必须为正数取值范围是：(0.0,1.0]，不能等于 0,默认值为 0.95 值越大，会使输出更随机，更具创造性；值越小，输出会更加稳定或确定建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Another method of temperature sampling is called kernel sampling. The value range is (0.0, 1.0) open interval, which cannot be equal to 0 or 1. The default value is 0.7. The model considers the results with top_p probability mass tokens. For example 0.1 means The model decoder only considers tokens from the candidate set with the top 10% probability. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "用温度取样的另一种方法，称为核取样取值范围是：(0.0, 1.0) 开区间，不能等于 0 或 1，默认值为 0.7 模型考虑具有 top_p 概率质量tokens的结果例如：0.1 意味着模型解码器只考虑从前 10% 的概率的候选集中取 tokens 建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "When `do_sample` is set to true, the sampling strategy is enabled. When `do_sample` is set to false, the sampling strategies such as `temperature` and `top_p` will not take effect. The default value is true.",
                    "zh_Hans": "do_sample 为 true 时启用采样策略，do_sample 为 false 时采样策略 temperature、top_p 将不生效。默认值为 true。"
                  },
                  "label": {
                    "en_US": "Sampling strategy",
                    "zh_Hans": "采样策略"
                  },
                  "max": null,
                  "min": null,
                  "name": "do_sample",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4095,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "web_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.001",
                "output": "0.001",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "glm-4-plus"
              },
              "model": "glm-4-plus",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Sampling temperature, controls the randomness of the output, must be a positive number. The value range is (0.0,1.0], which cannot be equal to 0. The default value is 0.95. The larger the value, the more random and creative the output will be; the smaller the value, The output will be more stable or certain. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "采样温度，控制输出的随机性，必须为正数取值范围是：(0.0,1.0]，不能等于 0,默认值为 0.95 值越大，会使输出更随机，更具创造性；值越小，输出会更加稳定或确定建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Another method of temperature sampling is called kernel sampling. The value range is (0.0, 1.0) open interval, which cannot be equal to 0 or 1. The default value is 0.7. The model considers the results with top_p probability mass tokens. For example 0.1 means The model decoder only considers tokens from the candidate set with the top 10% probability. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "用温度取样的另一种方法，称为核取样取值范围是：(0.0, 1.0) 开区间，不能等于 0 或 1，默认值为 0.7 模型考虑具有 top_p 概率质量tokens的结果例如：0.1 意味着模型解码器只考虑从前 10% 的概率的候选集中取 tokens 建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "When `do_sample` is set to true, the sampling strategy is enabled. When `do_sample` is set to false, the sampling strategies such as `temperature` and `top_p` will not take effect. The default value is true.",
                    "zh_Hans": "do_sample 为 true 时启用采样策略，do_sample 为 false 时采样策略 temperature、top_p 将不生效。默认值为 true。"
                  },
                  "label": {
                    "en_US": "Sampling strategy",
                    "zh_Hans": "采样策略"
                  },
                  "max": null,
                  "min": null,
                  "name": "do_sample",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4095,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "web_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.05",
                "output": "0.05",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "glm-4v"
              },
              "model": "glm-4v",
              "model_properties": {
                "context_size": 2048,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Sampling temperature, controls the randomness of the output, must be a positive number. The value range is (0.0,1.0], which cannot be equal to 0. The default value is 0.95. The larger the value, the more random and creative the output will be; the smaller the value, The output will be more stable or certain. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "采样温度，控制输出的随机性，必须为正数取值范围是：(0.0,1.0]，不能等于 0,默认值为 0.95 值越大，会使输出更随机，更具创造性；值越小，输出会更加稳定或确定建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.6,
                  "help": {
                    "en_US": "Another method of temperature sampling is called kernel sampling. The value range is (0.0, 1.0) open interval, which cannot be equal to 0 or 1. The default value is 0.7. The model considers the results with top_p probability mass tokens. For example 0.1 means The model decoder only considers tokens from the candidate set with the top 10% probability. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "用温度取样的另一种方法，称为核取样取值范围是：(0.0, 1.0) 开区间，不能等于 0 或 1，默认值为 0.7 模型考虑具有 top_p 概率质量tokens的结果例如：0.1 意味着模型解码器只考虑从前 10% 的概率的候选集中取 tokens 建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "When `do_sample` is set to true, the sampling strategy is enabled. When `do_sample` is set to false, the sampling strategies such as `temperature` and `top_p` will not take effect. The default value is true.",
                    "zh_Hans": "do_sample 为 true 时启用采样策略，do_sample 为 false 时采样策略 temperature、top_p 将不生效。默认值为 true。"
                  },
                  "label": {
                    "en_US": "Sampling strategy",
                    "zh_Hans": "采样策略"
                  },
                  "max": null,
                  "min": null,
                  "name": "do_sample",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 1024,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "web_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.05",
                "output": "0.05",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "vision",
                "video"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "glm-4v-plus"
              },
              "model": "glm-4v-plus",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Sampling temperature, controls the randomness of the output, must be a positive number. The value range is (0.0,1.0], which cannot be equal to 0. The default value is 0.95. The larger the value, the more random and creative the output will be; the smaller the value, The output will be more stable or certain. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "采样温度，控制输出的随机性，必须为正数取值范围是：(0.0,1.0]，不能等于 0,默认值为 0.95 值越大，会使输出更随机，更具创造性；值越小，输出会更加稳定或确定建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.6,
                  "help": {
                    "en_US": "Another method of temperature sampling is called kernel sampling. The value range is (0.0, 1.0) open interval, which cannot be equal to 0 or 1. The default value is 0.7. The model considers the results with top_p probability mass tokens. For example 0.1 means The model decoder only considers tokens from the candidate set with the top 10% probability. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.",
                    "zh_Hans": "用温度取样的另一种方法，称为核取样取值范围是：(0.0, 1.0) 开区间，不能等于 0 或 1，默认值为 0.7 模型考虑具有 top_p 概率质量tokens的结果例如：0.1 意味着模型解码器只考虑从前 10% 的概率的候选集中取 tokens 建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "When `do_sample` is set to true, the sampling strategy is enabled. When `do_sample` is set to false, the sampling strategies such as `temperature` and `top_p` will not take effect. The default value is true.",
                    "zh_Hans": "do_sample 为 true 时启用采样策略，do_sample 为 false 时采样策略 temperature、top_p 将不生效。默认值为 true。"
                  },
                  "label": {
                    "en_US": "Sampling strategy",
                    "zh_Hans": "采样策略"
                  },
                  "max": null,
                  "min": null,
                  "name": "do_sample",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 1024,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will \"judge\" whether to use Internet search results based on its internal logic.",
                    "zh_Hans": "模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。"
                  },
                  "label": {
                    "en_US": "Web Search",
                    "zh_Hans": "联网搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "web_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.01",
                "output": "0.01",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "embedding-2"
              },
              "model": "embedding-2",
              "model_properties": {
                "context_size": 8192
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "RMB",
                "input": "0.0005",
                "output": null,
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "embedding-3"
              },
              "model": "embedding-3",
              "model_properties": {
                "context_size": 8192
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "RMB",
                "input": "0.0005",
                "output": null,
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "text_embedding"
              },
              "model": "text_embedding",
              "model_properties": {
                "context_size": 512
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": null
            }
          ],
          "position": {
            "llm": [
              "chatglm_lite",
              "chatglm_lite_32k",
              "chatglm_pro",
              "chatglm_std",
              "chatglm_turbo",
              "glm-4-0520",
              "glm-4-air",
              "glm-4-airx",
              "glm-4-flash",
              "glm-4-flashx",
              "glm_3_turbo",
              "glm_4",
              "glm_4_long",
              "glm_4_plus",
              "glm_4v",
              "glm_4v_plus",
              "glm-4-air-0111"
            ],
            "text_embedding": null
          },
          "provider": "zhipuai",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "APIKey"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your APIKey",
                  "zh_Hans": "在此输入您的 APIKey"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              }
            ]
          },
          "supported_model_types": [
            "llm",
            "text-embedding"
          ]
        },
        "name": "zhipuai",
        "org": "langgenius",
        "plugin_id": "langgenius/zhipuai",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/zhipuai.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-17T12:31:32Z",
        "version_updated_at": "2025-04-17T12:31:32Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "A free internet metasearch engine.",
          "zh_Hans": "开源免费的互联网元搜索引擎"
        },
        "category": "tool",
        "created_at": "2024-11-29T10:24:32Z",
        "endpoint": {},
        "icon": "langgenius/packages/searxng/_assets/icon.svg",
        "index_id": "langgenius___searxng",
        "install_count": 9787,
        "introduction": "# Overview\n**SearXNG** is a free and open-source metasearch engine that aggregates results from multiple search services and databases. It prioritizes user privacy by ensuring that no tracking or profiling occurs. SearXNG allows users to perform searches anonymously while retrieving comprehensive results from various sources.\n\nWhen integrated with Dify, SearXNG can be used as a tool to enhance search capabilities within your workflows. This integration enables you to query multiple search engines simultaneously and retrieve aggregated results directly in Dify.\n\n# Configure\n## 1. Prerequisites\nBefore starting, ensure the following:\n- Access to the Dify Community Edition or the ability to configure tools in Dify Cloud.\n- Docker installed on your system for local deployment.\n- The SearXNG service is either self-hosted or accessible via a public instance.\n- Install SearXNG from Dify Marketplace.\n\n## 2. Local Deployment Using Docker\n\n### Step 1: Start the SearXNG Docker Service\n```shell\n$ mkdir my-instance\n$ cd my-instance\n$ export PORT=8081\n$ docker pull searxng/searxng\n$ docker run --rm \\\n             -d -p ${PORT}:8080 \\\n             -v \"${PWD}/searxng:/etc/searxng\" \\\n             -e \"BASE_URL=http://localhost:$PORT/\" \\\n             -e \"INSTANCE_NAME=my-instance\" \\\n             searxng/searxng\n2f998.... # container's ID\n```\n> Note: Use port `8081` instead of `8080` to avoid conflicts with other Docker services.\n\n### Step 2: Modify the SearXNG Configuration\n\nEdit the `my-instance/searxng/settings.yml` file,  make sure the `formats` has `json` format(default is only `html`) and the `limiter` is `false`.\n\nThen restart the SearXNG Docker service.\n```shell\n$ docker restart 2f998\n```\n\n### Step 3: Authenticate in Dify\n1. Go to **Tools > SearXNG > To authorize** in your Dify dashboard.\n2. Enter the base URL for your SearXNG instance, typically:\n`http://host.docker.internal:8081`\n3. Save the configuration to establish a connection between Dify and SearXNG.\n\n\n## 3. Using an Existing SearXNG Instance\nIf you are using an already deployed SearXNG service (e.g., on a public server), follow these steps:\n1. Retrieve the base URL of your SearXNG instance.\n2. Navigate to **Tools > SearXNG > To authorize** in Dify.\n3. Input the base URL and save the configuration.\n",
        "label": {
          "en_US": "SearXNG",
          "zh_Hans": "SearXNG"
        },
        "latest_package_identifier": "langgenius/searxng:0.0.5@4d354290d66892676a9f9dc7ce75cef323aae25dfc1c5057c7f770bd1052441b",
        "latest_version": "0.0.5",
        "model": {},
        "name": "searxng",
        "org": "langgenius",
        "plugin_id": "langgenius/searxng",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/searxng.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "search"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "SearXNG base URL",
                "zh_Hans": "SearXNG base URL"
              },
              "name": "searxng_base_url",
              "options": null,
              "placeholder": {
                "en_US": "Please input your SearXNG base URL",
                "zh_Hans": "请输入您的 SearXNG base URL"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": "https://docs.dify.ai/tutorials/tool-configuration/searxng"
            }
          ],
          "identity": {
            "author": "Junytang",
            "description": {
              "en_US": "A free internet metasearch engine.",
              "zh_Hans": "开源免费的互联网元搜索引擎"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "SearXNG",
              "zh_Hans": "SearXNG"
            },
            "name": "searxng",
            "tags": [
              "search",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "SearXNG is a free internet metasearch engine which aggregates results from more than 70 search services.",
                  "zh_Hans": "SearXNG 是一个免费的互联网元搜索引擎，它从70多个不同的搜索服务中聚合搜索结果。"
                },
                "llm": "Perform searches on SearXNG and get results."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Junytang",
                "label": {
                  "en_US": "SearXNG Search",
                  "zh_Hans": "SearXNG 搜索"
                },
                "name": "searxng_search"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Enter your search query",
                    "zh_Hans": "输入搜索关键词"
                  },
                  "label": {
                    "en_US": "Query string",
                    "zh_Hans": "查询语句"
                  },
                  "llm_description": "Key words for searching",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "general",
                  "form": "form",
                  "human_description": {
                    "en_US": "Search the web using SearXNG, a privacy-respecting metasearch engine",
                    "zh_Hans": "使用注重隐私的元搜索引擎 SearXNG 搜索网页"
                  },
                  "label": {
                    "en_US": "search type",
                    "zh_Hans": "搜索类型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "search_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "General",
                        "zh_Hans": "综合"
                      },
                      "value": "general"
                    },
                    {
                      "label": {
                        "en_US": "Images",
                        "zh_Hans": "图片"
                      },
                      "value": "images"
                    },
                    {
                      "label": {
                        "en_US": "Videos",
                        "zh_Hans": "视频"
                      },
                      "value": "videos"
                    },
                    {
                      "label": {
                        "en_US": "News",
                        "zh_Hans": "新闻"
                      },
                      "value": "news"
                    },
                    {
                      "label": {
                        "en_US": "Map",
                        "zh_Hans": "地图"
                      },
                      "value": "map"
                    },
                    {
                      "label": {
                        "en_US": "Music",
                        "zh_Hans": "音乐"
                      },
                      "value": "music"
                    },
                    {
                      "label": {
                        "en_US": "It",
                        "zh_Hans": "信息技术"
                      },
                      "value": "it"
                    },
                    {
                      "label": {
                        "en_US": "Science",
                        "zh_Hans": "科学"
                      },
                      "value": "science"
                    },
                    {
                      "label": {
                        "en_US": "Files",
                        "zh_Hans": "文件"
                      },
                      "value": "files"
                    },
                    {
                      "label": {
                        "en_US": "Social Media",
                        "zh_Hans": "社交媒体"
                      },
                      "value": "social_media"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "corresponding to the SearXNG API's time_range parameter, also depends on whether the search engine supports it",
                    "zh_Hans": "对应的是 SearXNG API 的 time_range 参数，也取决于搜索引擎是否支持"
                  },
                  "label": {
                    "en_US": "time range",
                    "zh_Hans": "时间范围"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "time_range",
                  "options": [
                    {
                      "label": {
                        "en_US": "In a day",
                        "zh_Hans": "一天内"
                      },
                      "value": "day"
                    },
                    {
                      "label": {
                        "en_US": "In a week",
                        "zh_Hans": "一周内"
                      },
                      "value": "week"
                    },
                    {
                      "label": {
                        "en_US": "In a month",
                        "zh_Hans": "一个月内"
                      },
                      "value": "month"
                    },
                    {
                      "label": {
                        "en_US": "In a year",
                        "zh_Hans": "一年内"
                      },
                      "value": "year"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-17T12:31:22Z",
        "version_updated_at": "2025-04-17T12:31:22Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "ECharts Chart Generator is a tool for generating statistical ECharts charts like bar chart, line chart, pie chart, etc.",
          "zh_Hans": "ECharts图表生成是一个用于生成可视化ECharts图表的工具，你可以通过它来生成柱状图、折线图、饼图等各类图表"
        },
        "category": "tool",
        "created_at": "2025-03-02T03:53:06Z",
        "endpoint": {},
        "icon": "langgenius/packages/echarts/_assets/icon.svg",
        "index_id": "langgenius___echarts",
        "install_count": 9231,
        "introduction": "",
        "label": {
          "en_US": "ECharts Chart Generator",
          "zh_Hans": "ECharts图表生成"
        },
        "latest_package_identifier": "langgenius/echarts:0.0.1@fe95412f101f2735530ea05f479ab5e8fbe1d4f4b2847f09e490e7d1d0125de5",
        "latest_version": "0.0.1",
        "model": {},
        "name": "echarts",
        "org": "langgenius",
        "plugin_id": "langgenius/echarts",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/echarts.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "utilities"
          },
          {
            "name": "design"
          }
        ],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "langgenius",
            "description": {
              "en_US": "ECharts Chart Generator is a tool for generating statistical ECharts charts like bar chart, line chart, pie chart, etc.",
              "zh_Hans": "ECharts图表生成是一个用于生成可视化ECharts图表的工具，你可以通过它来生成柱状图、折线图、饼图等各类图表"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "ECharts Chart Generator",
              "zh_Hans": "ECharts图表生成"
            },
            "name": "echarts",
            "tags": [
              "design",
              "productivity",
              "utilities"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "linear chart",
                  "zh_Hans": "线性图表"
                },
                "llm": "generate a linear chart with input data"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Linear Chart",
                  "zh_Hans": "线性图表"
                },
                "name": "line_chart"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "chart title",
                    "zh_Hans": "图表的标题"
                  },
                  "label": {
                    "en_US": "title",
                    "zh_Hans": "标题"
                  },
                  "llm_description": "chart title",
                  "max": null,
                  "min": null,
                  "name": "title",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "data for generating chart, each number should be separated by \";\"",
                    "zh_Hans": "用于生成线性图表的数据，每个数字之间用 \";\" 分隔"
                  },
                  "label": {
                    "en_US": "data",
                    "zh_Hans": "数据"
                  },
                  "llm_description": "data for generating linear chart, data should be a string contains a list of numbers like \"1;2;3;4;5\"",
                  "max": null,
                  "min": null,
                  "name": "data",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "X axis for chart, each text should be separated by \";\"",
                    "zh_Hans": "线性图表的 x 轴，每个文本之间用 \";\" 分隔"
                  },
                  "label": {
                    "en_US": "X Axis",
                    "zh_Hans": "x 轴"
                  },
                  "llm_description": "x axis for linear chart, x axis should be a string contains a list of texts like \"a;b;c;1;2\" in order to match the data",
                  "max": null,
                  "min": null,
                  "name": "x_axis",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Bar chart",
                  "zh_Hans": "柱状图"
                },
                "llm": "generate a bar chart with input data"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Bar Chart",
                  "zh_Hans": "柱状图"
                },
                "name": "bar_chart"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "chart title",
                    "zh_Hans": "图表的标题"
                  },
                  "label": {
                    "en_US": "title",
                    "zh_Hans": "标题"
                  },
                  "llm_description": "chart title",
                  "max": null,
                  "min": null,
                  "name": "title",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "data for generating chart, each number should be separated by \";\"",
                    "zh_Hans": "用于生成柱状图的数据，每个数字之间用 \";\" 分隔"
                  },
                  "label": {
                    "en_US": "data",
                    "zh_Hans": "数据"
                  },
                  "llm_description": "data for generating bar chart, data should be a string contains a list of numbers like \"1;2;3;4;5\"",
                  "max": null,
                  "min": null,
                  "name": "data",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "X axis for chart, each text should be separated by \";\"",
                    "zh_Hans": "柱状图的 x 轴，每个文本之间用 \";\" 分隔"
                  },
                  "label": {
                    "en_US": "X Axis",
                    "zh_Hans": "x 轴"
                  },
                  "llm_description": "x axis for bar chart, x axis should be a string contains a list of texts like \"a;b;c;1;2\" in order to match the data",
                  "max": null,
                  "min": null,
                  "name": "x_axis",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Pie chart",
                  "zh_Hans": "饼图"
                },
                "llm": "generate a pie chart with input data"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Pie Chart",
                  "zh_Hans": "饼图"
                },
                "name": "pie_chart"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "chart title",
                    "zh_Hans": "图表的标题"
                  },
                  "label": {
                    "en_US": "title",
                    "zh_Hans": "标题"
                  },
                  "llm_description": "chart title",
                  "max": null,
                  "min": null,
                  "name": "title",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "data for generating chart, each number should be separated by \";\"",
                    "zh_Hans": "用于生成饼图的数据，每个数字之间用 \";\" 分隔"
                  },
                  "label": {
                    "en_US": "data",
                    "zh_Hans": "数据"
                  },
                  "llm_description": "data for generating pie chart, data should be a string contains a list of numbers like \"1;2;3;4;5\"",
                  "max": null,
                  "min": null,
                  "name": "data",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Categories for chart, each category should be separated by \";\"",
                    "zh_Hans": "饼图的分类，每个分类之间用 \";\" 分隔"
                  },
                  "label": {
                    "en_US": "Categories",
                    "zh_Hans": "分类"
                  },
                  "llm_description": "categories for pie chart, categories should be a string contains a list of texts like \"a;b;c;1;2\" in order to match the data, each category should be split by \";\"",
                  "max": null,
                  "min": null,
                  "name": "categories",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-02T03:53:10Z",
        "version_updated_at": "2025-03-02T03:53:10Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Database Query Utils.",
          "zh_Hans": "数据库查询工具。"
        },
        "category": "tool",
        "created_at": "2025-03-24T07:37:48Z",
        "endpoint": {},
        "icon": "junjiem/packages/db_query/_assets/icon.svg",
        "index_id": "junjiem___db_query",
        "install_count": 9143,
        "introduction": "## Dify 1.0 Plugin Database Query Tools\r\n\r\n\r\n**Author:** [Junjie.M](https://github.com/junjiem)   \r\n**Type:** tool  \r\n**Github Repo:** [https://github.com/junjiem/dify-plugin-tools-dbquery](https://github.com/junjiem/dify-plugin-tools-dbquery)  \r\n**Github Issues:** [issues](https://github.com/junjiem/dify-plugin-tools-dbquery/issues)\r\n\r\n\r\n---\r\n\r\n\r\n### Demonstration\r\n\r\nDatabase Query Tools\r\n\r\n数据库查询工具\r\n\r\nCurrently supported database types: mysql, oracle, postgresql, or mssql.\r\n\r\n目前支持的数据库类型：mysql、oracle、postgresql、mssql。\r\n\r\n![db_query](_assets/db_query.png)\r\n\r\n![db_query_sql_query](_assets/db_query_sql_query.png)\r\n\r\n![db_query_chatflow](_assets/db_query_chatflow.png)\r\n",
        "label": {
          "en_US": "Database Query",
          "zh_Hans": "数据库查询"
        },
        "latest_package_identifier": "junjiem/db_query:0.0.5@a5ceb4c7cd40240d2a2abd38ecb58112d398ddd29a421c0711f599e0993acca9",
        "latest_version": "0.0.5",
        "model": {},
        "name": "db_query",
        "org": "junjiem",
        "plugin_id": "junjiem/db_query",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/db_query.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "utilities"
          },
          {
            "name": "search"
          }
        ],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "junjiem",
            "description": {
              "en_US": "Database Query Utils.",
              "zh_Hans": "数据库查询工具。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Database Query",
              "zh_Hans": "数据库查询"
            },
            "name": "db_query",
            "tags": [
              "search",
              "utilities"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool for Database SQL query.",
                  "zh_Hans": "数据库SQL查询工具。"
                },
                "llm": "A tool for executing SQL query. Input should be a search query."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "junjiem",
                "label": {
                  "en_US": "SQL Query",
                  "zh_Hans": "SQL查询"
                },
                "name": "sql_query"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": "mysql",
                  "form": "llm",
                  "human_description": {
                    "en_US": "Used for selecting the database type, mysql, oracle, postgresql or mssql.",
                    "zh_Hans": "用于选择数据库类型，mysql、oracle、postgresql或mssql。"
                  },
                  "label": {
                    "en_US": "Database type",
                    "zh_Hans": "数据库类型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "db_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "MySQL",
                        "zh_Hans": "MySQL"
                      },
                      "value": "mysql"
                    },
                    {
                      "label": {
                        "en_US": "Oracle",
                        "zh_Hans": "Oracle"
                      },
                      "value": "oracle"
                    },
                    {
                      "label": {
                        "en_US": "PostgreSQL",
                        "zh_Hans": "PostgreSQL"
                      },
                      "value": "postgresql"
                    },
                    {
                      "label": {
                        "en_US": "Microsoft SQL Server",
                        "zh_Hans": "Microsoft SQL Server"
                      },
                      "value": "mssql"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "localhost",
                  "form": "llm",
                  "human_description": {
                    "en_US": "database hostname or IP address (Original string, not URL-encoded string).",
                    "zh_Hans": "数据库的主机名或IP地址（原始字符串，非URL编码字符串）。"
                  },
                  "label": {
                    "en_US": "Database Host",
                    "zh_Hans": "数据库地址"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "db_host",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "database port.",
                    "zh_Hans": "数据库的端口。"
                  },
                  "label": {
                    "en_US": "Port",
                    "zh_Hans": "端口"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "db_port",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "database username (Original string, not URL-encoded string).",
                    "zh_Hans": "数据库的用户名（原始字符串，非URL编码字符串）。"
                  },
                  "label": {
                    "en_US": "Username",
                    "zh_Hans": "用户名"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "db_username",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "database password (Original string, not URL-encoded string).",
                    "zh_Hans": "数据库的密码（原始字符串，非URL编码字符串）。"
                  },
                  "label": {
                    "en_US": "Password",
                    "zh_Hans": "密码"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "db_password",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "database name (Original string, not URL-encoded string).",
                    "zh_Hans": "数据库的名称（原始字符串，非URL编码字符串）。"
                  },
                  "label": {
                    "en_US": "Database name",
                    "zh_Hans": "库名"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "db_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Database properties, for example: alt_host=host1&alt_host=host2&ssl_cipher=%2Fpath%2Fto%2Fcrt",
                    "zh_Hans": "数据库属性，例如：alt_host=host1&alt_host=host2&ssl_cipher=%2Fpath%2Fto%2Fcrt"
                  },
                  "label": {
                    "en_US": "Database properties",
                    "zh_Hans": "数据库属性"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "db_properties",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "SQL query statement, for example: select * from tbl_name",
                    "zh_Hans": "SQL查询语句，例如：select * from tbl_name"
                  },
                  "label": {
                    "en_US": "Query SQL",
                    "zh_Hans": "SQL查询语句"
                  },
                  "llm_description": "SQL query statement, for example: select * from tbl_name",
                  "max": null,
                  "min": null,
                  "name": "query_sql",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-09T09:04:49Z",
        "version_updated_at": "2025-04-09T09:04:49Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Embedding and Rerank Model Supported"
        },
        "category": "model",
        "created_at": "2024-11-29T11:26:04Z",
        "endpoint": {},
        "icon": "langgenius/packages/jina/_assets/icon_s_en.svg",
        "index_id": "langgenius___jina",
        "install_count": 9036,
        "introduction": "## Overview\n\nJina is a cloud-native neural search framework for building scalable, multimodal AI applications. It offers a robust ecosystem for indexing, querying, and retrieving various data types. Jina utilizes modular \"Pods\" for flexible search pipelines and supports diverse backends. Key components include `jina-clip-v2`, a model offering multilingual multimodal embeddings for text and images, and `jina-embeddings-v3`, providing multilingual embeddings with Task LoRA for fine-tuning. Jina enables developers to create sophisticated search, recommendation, and QA systems, streamlining AI development by making advanced functionalities more accessible and scalable.\n\n## Configure\n\nAfter installing the plugin, configure the API key and API base within the Model Provider settings. Obtain your API key from [here](https://jina.ai/). Once saved, you can begin using Jina to build your AI agents and agentic workflows.\n\n![](./_assets/jina_config.PNG)",
        "label": {
          "en_US": "Jina"
        },
        "latest_package_identifier": "langgenius/jina:0.0.6@3ac399c96509b3bfe3124f9cdfa13999cb2f7d7ff00a99cc8d3ac4f4d82ffe6c",
        "latest_version": "0.0.6",
        "model": {
          "background": "#EFFDFD",
          "configurate_methods": [
            "predefined-model",
            "customizable-model"
          ],
          "description": {
            "en_US": "Embedding and Rerank Model Supported"
          },
          "help": {
            "title": {
              "en_US": "Get your API key from Jina AI",
              "zh_Hans": "从 Jina 获取 API Key"
            },
            "url": {
              "en_US": "https://jina.ai/"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.svg"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "Jina"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Base URL",
                  "zh_Hans": "服务器 URL"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Base URL, e.g. https://api.jina.ai/v1",
                  "zh_Hans": "Base URL, e.g. https://api.jina.ai/v1"
                },
                "required": false,
                "show_on": [],
                "type": "text-input",
                "variable": "base_url"
              },
              {
                "default": "8192",
                "label": {
                  "en_US": "Context size",
                  "zh_Hans": "上下文大小"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter context size",
                  "zh_Hans": "输入上下文大小"
                },
                "required": false,
                "show_on": [],
                "type": "text-input",
                "variable": "context_size"
              }
            ],
            "model": {
              "label": {
                "en_US": "Model Name",
                "zh_Hans": "模型名称"
              },
              "placeholder": {
                "en_US": "Enter your model name",
                "zh_Hans": "输入模型名称"
              }
            }
          },
          "models": [
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "jina-colbert-v1-en"
              },
              "model": "jina-colbert-v1-en",
              "model_properties": {
                "context_size": 8192
              },
              "model_type": "rerank",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "jina-reranker-v1-base-en"
              },
              "model": "jina-reranker-v1-base-en",
              "model_properties": {
                "context_size": 8192
              },
              "model_type": "rerank",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "jina-reranker-v1-tiny-en"
              },
              "model": "jina-reranker-v1-tiny-en",
              "model_properties": {
                "context_size": 8192
              },
              "model_type": "rerank",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "jina-reranker-v1-turbo-en"
              },
              "model": "jina-reranker-v1-turbo-en",
              "model_properties": {
                "context_size": 8192
              },
              "model_type": "rerank",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "jina-reranker-v2-base-multilingual"
              },
              "model": "jina-reranker-v2-base-multilingual",
              "model_properties": {
                "context_size": 8192
              },
              "model_type": "rerank",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "jina-clip-v1"
              },
              "model": "jina-clip-v1",
              "model_properties": {
                "context_size": 8192,
                "max_chunks": 2048
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.001",
                "output": null,
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "jina-clip-v2"
              },
              "model": "jina-clip-v2",
              "model_properties": {
                "context_size": 8192,
                "max_chunks": 2048
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.001",
                "output": null,
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "jina-embeddings-v2-base-de"
              },
              "model": "jina-embeddings-v2-base-de",
              "model_properties": {
                "context_size": 8192,
                "max_chunks": 2048
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.001",
                "output": null,
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "jina-embeddings-v2-base-en"
              },
              "model": "jina-embeddings-v2-base-en",
              "model_properties": {
                "context_size": 8192,
                "max_chunks": 2048
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.001",
                "output": null,
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "jina-embeddings-v2-base-zh"
              },
              "model": "jina-embeddings-v2-base-zh",
              "model_properties": {
                "context_size": 8192,
                "max_chunks": 2048
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.001",
                "output": null,
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "jina-embeddings-v2-small-en"
              },
              "model": "jina-embeddings-v2-small-en",
              "model_properties": {
                "context_size": 8192,
                "max_chunks": 2048
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.001",
                "output": null,
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "jina-embeddings-v3"
              },
              "model": "jina-embeddings-v3",
              "model_properties": {
                "context_size": 8192,
                "max_chunks": 2048
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.001",
                "output": null,
                "unit": "0.001"
              }
            }
          ],
          "position": {
            "rerank": [
              "jina-reranker-v2-base-multilingual",
              "jina-reranker-v1-base-en",
              "jina-reranker-v1-turbo-en",
              "jina-colbert-v1-en",
              "jina-reranker-v1-tiny-en"
            ],
            "text_embedding": null
          },
          "provider": "jina",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              }
            ]
          },
          "supported_model_types": [
            "text-embedding",
            "rerank"
          ]
        },
        "name": "jina",
        "org": "langgenius",
        "plugin_id": "langgenius/jina",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/jina.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-03-13T02:54:34Z",
        "version_updated_at": "2025-03-13T02:54:34Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Models provided by Moonshot, such as moonshot-v1-8k, moonshot-v1-32k, and moonshot-v1-128k.",
          "zh_Hans": "Moonshot 提供的模型，例如 moonshot-v1-8k、moonshot-v1-32k 和 moonshot-v1-128k。"
        },
        "category": "model",
        "created_at": "2024-11-29T11:10:49Z",
        "endpoint": {},
        "icon": "langgenius/packages/moonshot/_assets/icon_s_en.png",
        "index_id": "langgenius___moonshot",
        "install_count": 8971,
        "introduction": "## Overview\n\nThis plugin provides access to Moonshot's moonshot-v1 series, offering LLMs with three context lengths for generating diverse text outputs, from short to long. The API supports function calling, enabling developers to connect tools in AI applications.\n\n## Configure\n\nAfter installing the plugin, configure the API key and API base within the Model Provider settings. Obtain your API key from here. Save to use Moonshot.\n\n![](./_assets/moonshot-01.png)\n",
        "label": {
          "en_US": "Moonshot",
          "zh_Hans": "月之暗面"
        },
        "latest_package_identifier": "langgenius/moonshot:0.0.4@684e36cde2a78f7edd6faa0d07e530d8042115677b0d42acfc07fce9407d52e9",
        "latest_version": "0.0.4",
        "model": {
          "background": "#FFFFFF",
          "configurate_methods": [
            "predefined-model",
            "customizable-model"
          ],
          "description": {
            "en_US": "Models provided by Moonshot, such as moonshot-v1-8k, moonshot-v1-32k, and moonshot-v1-128k.",
            "zh_Hans": "Moonshot 提供的模型，例如 moonshot-v1-8k、moonshot-v1-32k 和 moonshot-v1-128k。"
          },
          "help": {
            "title": {
              "en_US": "Get your API Key from Moonshot",
              "zh_Hans": "从 Moonshot 获取 API Key"
            },
            "url": {
              "en_US": "https://platform.moonshot.cn/console/api-keys"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.png"
          },
          "icon_small": {
            "en_US": "icon_s_en.png"
          },
          "label": {
            "en_US": "Moonshot",
            "zh_Hans": "月之暗面"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              },
              {
                "default": "4096",
                "label": {
                  "en_US": "Model context size",
                  "zh_Hans": "模型上下文长度"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Model context size",
                  "zh_Hans": "在此输入您的模型上下文长度"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "context_size"
              },
              {
                "default": "4096",
                "label": {
                  "en_US": "Upper bound for max tokens",
                  "zh_Hans": "最大 token 上限"
                },
                "max_length": 0,
                "options": [],
                "placeholder": null,
                "required": false,
                "show_on": [],
                "type": "text-input",
                "variable": "max_tokens"
              },
              {
                "default": "no_call",
                "label": {
                  "en_US": "Function calling"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Not supported",
                      "zh_Hans": "不支持"
                    },
                    "show_on": [],
                    "value": "no_call"
                  },
                  {
                    "label": {
                      "en_US": "Tool Call",
                      "zh_Hans": "Tool Call"
                    },
                    "show_on": [],
                    "value": "tool_call"
                  }
                ],
                "placeholder": null,
                "required": false,
                "show_on": [],
                "type": "select",
                "variable": "function_calling_type"
              }
            ],
            "model": {
              "label": {
                "en_US": "Model Name",
                "zh_Hans": "模型名称"
              },
              "placeholder": {
                "en_US": "Enter your model name",
                "zh_Hans": "输入模型名称"
              }
            }
          },
          "models": [
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "multi-tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "moonshot-v1-128k",
                "zh_Hans": "moonshot-v1-128k"
              },
              "model": "moonshot-v1-128k",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 128000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.06",
                "output": "0.06",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "multi-tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "moonshot-v1-32k",
                "zh_Hans": "moonshot-v1-32k"
              },
              "model": "moonshot-v1-32k",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 32000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.024",
                "output": "0.024",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "multi-tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "moonshot-v1-8k",
                "zh_Hans": "moonshot-v1-8k"
              },
              "model": "moonshot-v1-8k",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.012",
                "output": "0.012",
                "unit": "0.001"
              }
            }
          ],
          "position": {
            "llm": [
              "moonshot-v1-8k",
              "moonshot-v1-32k",
              "moonshot-v1-128k"
            ]
          },
          "provider": "moonshot",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              },
              {
                "default": null,
                "label": {
                  "en_US": "API Base"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Base URL, e.g. https://api.moonshot.cn/v1",
                  "zh_Hans": "Base URL, 如：https://api.moonshot.cn/v1"
                },
                "required": false,
                "show_on": [],
                "type": "text-input",
                "variable": "endpoint_url"
              }
            ]
          },
          "supported_model_types": [
            "llm"
          ]
        },
        "name": "moonshot",
        "org": "langgenius",
        "plugin_id": "langgenius/moonshot",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/moonshot.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-03-20T10:33:14Z",
        "version_updated_at": "2025-03-20T06:34:11Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "A tool for regex extraction.",
          "pt_BR": "A tool for regex extraction.",
          "zh_Hans": "一个用于正则表达式内容提取的工具。"
        },
        "category": "tool",
        "created_at": "2024-12-04T08:19:17Z",
        "endpoint": {},
        "icon": "langgenius/packages/regex/_assets/icon.svg",
        "index_id": "langgenius___regex",
        "install_count": 8666,
        "introduction": "# Overview\nThe Regex Extract tool is a utility that helps users extract specific patterns of text using regular expressions (regex).\n\n# Configure\n1. Install Regex from Dify Marketplace.\n![](./_assets/regex_install.png)\n2. Fill in Content to be extracted and Regular expression.\n![](./_assets/regex_config.png)\n![](./_assets/regex_test.png)",
        "label": {
          "en_US": "Regex",
          "pt_BR": "Regex",
          "zh_Hans": "正则表达式提取"
        },
        "latest_package_identifier": "langgenius/regex:0.0.3@55439fc9083494e90856405256a1755c4ee47aa395cef50b6fc3614d4f11a479",
        "latest_version": "0.0.3",
        "model": {},
        "name": "regex",
        "org": "langgenius",
        "plugin_id": "langgenius/regex",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/regex.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "utilities"
          }
        ],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "zhuhao",
            "description": {
              "en_US": "A tool for regex extraction.",
              "pt_BR": "A tool for regex extraction.",
              "zh_Hans": "一个用于正则表达式内容提取的工具。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Regex",
              "pt_BR": "Regex",
              "zh_Hans": "正则表达式提取"
            },
            "name": "regex",
            "tags": [
              "utilities",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool for extracting matching content using regular expressions.",
                  "pt_BR": "A tool for extracting matching content using regular expressions.",
                  "zh_Hans": "一个用于利用正则表达式提取匹配内容结果的工具。"
                },
                "llm": "A tool for extracting matching content using regular expressions."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "zhuhao",
                "label": {
                  "en_US": "Regex Extract",
                  "pt_BR": "Regex Extract",
                  "zh_Hans": "正则表达式内容提取"
                },
                "name": "regex_extract"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Content to be extracted",
                    "pt_BR": "Content to be extracted",
                    "zh_Hans": "内容"
                  },
                  "label": {
                    "en_US": "Content to be extracted",
                    "pt_BR": "Content to be extracted",
                    "zh_Hans": "内容"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Regular expression",
                    "pt_BR": "Regular expression",
                    "zh_Hans": "正则表达式"
                  },
                  "label": {
                    "en_US": "Regular expression",
                    "pt_BR": "Regular expression",
                    "zh_Hans": "正则表达式"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "expression",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:11:23Z",
        "version_updated_at": "2025-02-17T07:11:23Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Fetching data from the database using natural language.",
          "ja_JP": "Fetching data from the database using natural language.",
          "pt_BR": "Fetching data from the database using natural language.",
          "zh_Hans": "自然语言查询 MySQL 数据."
        },
        "category": "tool",
        "created_at": "2025-03-19T02:01:54Z",
        "endpoint": {},
        "icon": "jaguarliuu/packages/rookie_text2data/_assets/data-collection.svg",
        "index_id": "jaguarliuu___rookie_text2data",
        "install_count": 8447,
        "introduction": "## rookie_text2data\n\n**Author:** jaguarliuu\n**Version:** 0.3.0\n**Type:** tool\n\n### Description\nA tool that converts natural language into secure and optimized SQL queries, supporting both MySQL and PostgreSQL databases.\n\n\n### 声明\nWe are truly grateful for the overwhelming interest in this experimental project. Your feedback is invaluable for improving this plugin. Join our WeChat group for discussions and collaboration opportunities!\n\n> Contact:\n>  - Wechat： L1763077056\n\n### ✨ Core Features\n\n#### ​Multi-Database Support\n- Native support for MySQL and PostgreSQL syntax differences\n- Automatic SQL syntax adaptation based on database type (e.g., LIMIT vs FETCH FIRST)\n#### ​Security Mechanisms\n- Mandatory result set limits (default LIMIT 100)\n- DML operation prohibition (SELECT statements only)\n- Field whitelist validation (based on database metadata)\n- Least privilege principle for query execution\n\n### Supported Databases\nMySQL\nPostgreSQL\n\n### Supported LLMs\nCompatible with ​all non-deep-thinking models\n- ChatGLM-6B\n- DeepSeek V3\n- Qwen-max\n...\n\n### Quick Start\n#### SQL Generation Component\n1. Import the rookie_text2data plugin\n2. Configure basic parameters:\n\n| Parameter      | Type           | Required | Description                                       | Multilingual Support     |\n|----------------|----------------|----------|---------------------------------------------------|--------------------------|\n| db_type        | select         | Yes      | Database type (MySQL/PostgreSQL)                  | CN/EN/PT                |\n| host           | string         | Yes      | Database host/IP address                          | CN/EN/PT                |\n| port           | number         | Yes      | Database port (1-65535)                           | CN/EN/PT                |\n| db_name        | string         | Yes      | Target database name                              | CN/EN/PT                |\n| table_name     | string         | No       | Comma-separated table names (empty for all tables)| CN (format hints)       |\n| username       | string         | Yes      | Database username                                 | CN/EN/PT                |\n| password       | secret-input   | Yes      | Database password                                 | CN/EN/PT                |\n| model          | model-selector | Yes      | LLM model configuration                           | CN/EN/PT                |\n| query          | string         | Yes      | Natural language query statement                  | CN/EN/PT                |\n\n3. Select Model，We recommend using the Qwen-max model. Other models can be tested but deep-thinking models are unsupported.\n4. Generate SQL queries using natural language\n\n#### SQL Execution Component\n1. Import the rookie_execute_sql plugin\n2. Configure basic parameters:\n\n| Parameter     | Type     | Required | Description                              | Multilingual Support     |\n|---------------|----------|----------|------------------------------------------|--------------------------|\n| db_type       | select   | Yes      | Database type (MySQL/PostgreSQL)         | CN/EN/PT                |\n| host          | string   | Yes      | Database host/IP address                 | CN/EN/PT                |\n| port          | number   | Yes      | Database port (1-65535)                  | CN/EN/PT                |\n| db_name       | string   | Yes      | Target database name                     | CN/EN/PT                |\n| sql           | string   | Yes      | SQL query to execute                     | CN/EN/PT                |\n\n3. Click \"Execute\" to run the SQL statement\n\n### License\n\nThis project is licensed under the Apache License 2.0 - see the [LICENSE](LICENSE) file for details.",
        "label": {
          "en_US": "rookie_text2data",
          "ja_JP": "rookie_text2data",
          "pt_BR": "rookie_text2data",
          "zh_Hans": "rookie_text2data"
        },
        "latest_package_identifier": "jaguarliuu/rookie_text2data:0.3.0@c7fdd3a69ec976a7054fdbb6d159a201060f82ee49881d531c875dc2da0d3d91",
        "latest_version": "0.3.0",
        "model": {},
        "name": "rookie_text2data",
        "org": "jaguarliuu",
        "plugin_id": "jaguarliuu/rookie_text2data",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/rookie_text2data.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "jaguarliuu",
            "description": {
              "en_US": "Fetching data from the database using natural language.",
              "pt_BR": "Fetching data from the database using natural language.",
              "zh_Hans": "使用自然语言获取MySQL数据库数据."
            },
            "icon": "data-collection.svg",
            "label": {
              "en_US": "rookie_text2data",
              "pt_BR": "rookie_text2data",
              "zh_Hans": "rookie_text2data"
            },
            "name": "rookie_text2data",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Fetching data from the database using natural language.",
                  "pt_BR": "Fetching data from the database using natural language.",
                  "zh_Hans": "使用自然语言从MySQL获取数据"
                },
                "llm": "Fetching data from the database using natural language."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "jaguarliuu",
                "label": {
                  "en_US": "rookie_text2data",
                  "pt_BR": "rookie_text2data",
                  "zh_Hans": "rookie_text2data"
                },
                "name": "rookie_text2data"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Database type",
                    "pt_BR": "Database type",
                    "zh_Hans": "数据库类型"
                  },
                  "label": {
                    "en_US": "Database type",
                    "pt_BR": "Database type",
                    "zh_Hans": "数据库类型"
                  },
                  "llm_description": "Database type",
                  "max": null,
                  "min": null,
                  "name": "db_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "MySQL"
                      },
                      "value": "mysql"
                    },
                    {
                      "label": {
                        "en_US": "PostgreSQL"
                      },
                      "value": "postgresql"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "limit",
                    "pt_BR": "limit",
                    "zh_Hans": "SQL返回数据量限制"
                  },
                  "label": {
                    "en_US": "limit",
                    "pt_BR": "limit",
                    "zh_Hans": "SQL返回数据量限制"
                  },
                  "llm_description": "limit",
                  "max": 1000,
                  "min": 1,
                  "name": "limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "json",
                  "form": "form",
                  "human_description": {
                    "en_US": "result_format",
                    "pt_BR": "result_format",
                    "zh_Hans": "返回数据格式"
                  },
                  "label": {
                    "en_US": "result_format",
                    "pt_BR": "result_format",
                    "zh_Hans": "返回数据格式"
                  },
                  "llm_description": "result_format",
                  "max": null,
                  "min": null,
                  "name": "result_format",
                  "options": [
                    {
                      "label": {
                        "en_US": "JSON",
                        "zh_Hans": "JSON"
                      },
                      "value": "json"
                    },
                    {
                      "label": {
                        "en_US": "TEXT",
                        "zh_Hans": "TEXT"
                      },
                      "value": "text"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Database ip/host",
                    "pt_BR": "Database ip/host",
                    "zh_Hans": "数据库IP/域名"
                  },
                  "label": {
                    "en_US": "Database ip/host",
                    "pt_BR": "Database ip/host",
                    "zh_Hans": "数据库IP/域名"
                  },
                  "llm_description": "Database ip/host",
                  "max": null,
                  "min": null,
                  "name": "host",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Database port",
                    "pt_BR": "Database port",
                    "zh_Hans": "数据库端口"
                  },
                  "label": {
                    "en_US": "Database port",
                    "pt_BR": "Database port",
                    "zh_Hans": "数据库端口"
                  },
                  "llm_description": "Database port",
                  "max": 65535,
                  "min": 1,
                  "name": "port",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Database name",
                    "pt_BR": "Database name",
                    "zh_Hans": "数据库名称"
                  },
                  "label": {
                    "en_US": "Database name",
                    "pt_BR": "Database name",
                    "zh_Hans": "数据库名称"
                  },
                  "llm_description": "Database name",
                  "max": null,
                  "min": null,
                  "name": "db_name",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "table_names",
                    "pt_BR": "table_names",
                    "zh_Hans": "数据表名称"
                  },
                  "label": {
                    "en_US": "table_names",
                    "pt_BR": "table_names",
                    "zh_Hans": "数据表名称"
                  },
                  "llm_description": "table_names",
                  "max": null,
                  "min": null,
                  "name": "table_names",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Schema name",
                    "pt_BR": "Schema name",
                    "zh_Hans": "数据库Schema PGSQL用户选填，默认为public"
                  },
                  "label": {
                    "en_US": "Schema name",
                    "pt_BR": "Schema name",
                    "zh_Hans": "数据库Schema PGSQL用户选填，默认为public"
                  },
                  "llm_description": "Schema name",
                  "max": null,
                  "min": null,
                  "name": "schema_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Username",
                    "pt_BR": "Username",
                    "zh_Hans": "用户名"
                  },
                  "label": {
                    "en_US": "Username",
                    "pt_BR": "Username",
                    "zh_Hans": "用户名"
                  },
                  "llm_description": "Username",
                  "max": null,
                  "min": null,
                  "name": "username",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Password",
                    "pt_BR": "Password",
                    "zh_Hans": "密码"
                  },
                  "label": {
                    "en_US": "Password",
                    "pt_BR": "Password",
                    "zh_Hans": "密码"
                  },
                  "llm_description": "Password",
                  "max": null,
                  "min": null,
                  "name": "password",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "LLM model for text2data.",
                    "pt_BR": "LLM model for text2data.",
                    "zh_Hans": "LLM model for text2data."
                  },
                  "label": {
                    "en_US": "Model",
                    "pt_BR": "Model",
                    "zh_Hans": "模型"
                  },
                  "llm_description": "LLM model for text2data.",
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": "llm",
                  "template": null,
                  "type": "model-selector"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Fetching data from the database using natural language.",
                    "pt_BR": "Fetching data from the database using natural language.",
                    "zh_Hans": "Fetching data from the database using natural language."
                  },
                  "label": {
                    "en_US": "Query string",
                    "pt_BR": "Query string",
                    "zh_Hans": "查询语句"
                  },
                  "llm_description": "Fetching data from the database using natural language.",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "custom_prompt",
                    "pt_BR": "custom_prompt",
                    "zh_Hans": "自定义提示"
                  },
                  "label": {
                    "en_US": "custom_prompt",
                    "pt_BR": "custom_prompt",
                    "zh_Hans": "自定义提示"
                  },
                  "llm_description": "custom_prompt",
                  "max": null,
                  "min": null,
                  "name": "custom_prompt",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "with_comment",
                    "pt_BR": "with_comment",
                    "zh_Hans": "是否包含注释"
                  },
                  "label": {
                    "en_US": "with_comment",
                    "pt_BR": "with_comment",
                    "zh_Hans": "是否包含注释"
                  },
                  "llm_description": "with_comment",
                  "max": null,
                  "min": null,
                  "name": "with_comment",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "excute sql",
                  "pt_BR": "excute sql",
                  "zh_Hans": "sql 执行器"
                },
                "llm": "excute sql"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "jaguarliuu",
                "label": {
                  "en_US": "rookie_excute_sql",
                  "pt_BR": "rookie_excute_sql",
                  "zh_Hans": "rookie_excute_sql"
                },
                "name": "rookie_excute_sql"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Database type",
                    "pt_BR": "Database type",
                    "zh_Hans": "数据库类型"
                  },
                  "label": {
                    "en_US": "Database type",
                    "pt_BR": "Database type",
                    "zh_Hans": "数据库类型"
                  },
                  "llm_description": "Database type",
                  "max": null,
                  "min": null,
                  "name": "db_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "MySQL"
                      },
                      "value": "mysql"
                    },
                    {
                      "label": {
                        "en_US": "PostgreSQL"
                      },
                      "value": "postgresql"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Database ip/host",
                    "pt_BR": "Database ip/host",
                    "zh_Hans": "数据库IP/域名"
                  },
                  "label": {
                    "en_US": "Database ip/host",
                    "pt_BR": "Database ip/host",
                    "zh_Hans": "数据库IP/域名"
                  },
                  "llm_description": "Database ip/host",
                  "max": null,
                  "min": null,
                  "name": "host",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Database port",
                    "pt_BR": "Database port",
                    "zh_Hans": "数据库端口"
                  },
                  "label": {
                    "en_US": "Database port",
                    "pt_BR": "Database port",
                    "zh_Hans": "数据库端口"
                  },
                  "llm_description": "Database port",
                  "max": 65535,
                  "min": 1,
                  "name": "port",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Database name",
                    "pt_BR": "Database name",
                    "zh_Hans": "数据库名称"
                  },
                  "label": {
                    "en_US": "Database name",
                    "pt_BR": "Database name",
                    "zh_Hans": "数据库名称"
                  },
                  "llm_description": "Database name",
                  "max": null,
                  "min": null,
                  "name": "db_name",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Username",
                    "pt_BR": "Username",
                    "zh_Hans": "用户名"
                  },
                  "label": {
                    "en_US": "Username",
                    "pt_BR": "Username",
                    "zh_Hans": "用户名"
                  },
                  "llm_description": "Username",
                  "max": null,
                  "min": null,
                  "name": "username",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Password",
                    "pt_BR": "Password",
                    "zh_Hans": "密码"
                  },
                  "label": {
                    "en_US": "Password",
                    "pt_BR": "Password",
                    "zh_Hans": "密码"
                  },
                  "llm_description": "Password",
                  "max": null,
                  "min": null,
                  "name": "password",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Schema name",
                    "pt_BR": "Schema name",
                    "zh_Hans": "数据库Schema PGSQL用户选填，默认为public"
                  },
                  "label": {
                    "en_US": "Schema name",
                    "pt_BR": "Schema name",
                    "zh_Hans": "数据库Schema PGSQL用户选填，默认为public"
                  },
                  "llm_description": "Schema name",
                  "max": null,
                  "min": null,
                  "name": "schema",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Fetching data from the database using natural language.",
                    "pt_BR": "Fetching data from the database using natural language.",
                    "zh_Hans": "Fetching data from the database using natural language."
                  },
                  "label": {
                    "en_US": "SQL string",
                    "pt_BR": "SQL string",
                    "zh_Hans": "待执行的 SQL 语句"
                  },
                  "llm_description": "Fetching data from the database using natural language.",
                  "max": null,
                  "min": null,
                  "name": "sql",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "json",
                  "form": "form",
                  "human_description": {
                    "en_US": "result_format",
                    "pt_BR": "result_format",
                    "zh_Hans": "返回数据格式"
                  },
                  "label": {
                    "en_US": "result_format",
                    "pt_BR": "result_format",
                    "zh_Hans": "返回数据格式"
                  },
                  "llm_description": "result_format",
                  "max": null,
                  "min": null,
                  "name": "result_format",
                  "options": [
                    {
                      "label": {
                        "en_US": "JSON",
                        "zh_Hans": "JSON"
                      },
                      "value": "json"
                    },
                    {
                      "label": {
                        "en_US": "TEXT",
                        "zh_Hans": "TEXT"
                      },
                      "value": "text"
                    },
                    {
                      "label": {
                        "en_US": "CSV",
                        "zh_Hans": "CSV"
                      },
                      "value": "csv"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-15T01:33:28Z",
        "version_updated_at": "2025-04-15T01:33:28Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Hugging Face Model"
        },
        "category": "model",
        "created_at": "2025-01-02T05:33:07Z",
        "endpoint": {},
        "icon": "langgenius/packages/huggingface_hub/_assets/icon_s_en.svg",
        "index_id": "langgenius___huggingface_hub",
        "install_count": 8344,
        "introduction": "## Overview\n\nHugging Face is a leading open-source platform and community dedicated to advancing artificial intelligence (AI) and machine learning (ML), particularly in the field of natural language processing (NLP). Founded in 2016, the company initially aimed to create an interactive chatbot but quickly pivoted to focus on providing powerful tools and resources for AI development. Today, it is widely recognized as a central hub for researchers, developers, and enthusiasts to collaborate on machine learning projects.\n\n## Configuration\n\nDify supports Text-Generation and Embeddings for Hugging Face. Below are the corresponding Hugging Face model types:\n\n* Text-Generation：[text-generation](https://huggingface.co/models?pipeline_tag=text-generation&sort=trending)，[text2text-generation](https://huggingface.co/models?pipeline_tag=text2text-generation&sort=trending)\n* Embeddings：[feature-extraction](https://huggingface.co/models?pipeline_tag=feature-extraction&sort=trending)\n\nThe specific steps are as follows:\n\n1. You need a Hugging Face account ([registered address](https://huggingface.co/join)).\n2. Set the API key of Hugging Face ([obtain address](https://huggingface.co/settings/tokens)).\n3. Select a model to enter the [Hugging Face model list page](https://huggingface.co/models?pipeline_tag=text-generation&sort=trending).\n\n![](./_assets/huggingface_hub-01.png)\n\nDify supports accessing models on Hugging Face in two ways:\n\n1. Hosted Inference API. This method uses the model officially deployed by Hugging Face. No fee is required. But the downside is that only a small number of models support this approach.\n2. Inference Endpoint. This method uses resources such as AWS accessed by the Hugging Face to deploy the model and requires payment.\n\n## Models that access the Hosted Inference API\n\n### 1. Select a model\n\nHosted inference API is supported only when there is an area containing Hosted inference API on the right side of the model details page. As shown in the figure below:\n\n![](./_assets/huggingface_hub-02.png)\n\nOn the model details page, you can get the name of the model.\n\n![](./_assets/huggingface_hub-03.png)\n\n### 2. Using access models in Dify\n\nSelect Hosted Inference API for Endpoint Type in `Settings > Model Provider > Hugging Face > Model Type`. As shown below:\n\n![](./_assets/huggingface_hub-04.png)\n\nAPI Token is the API Key set at the beginning of the article. The model name is the model name obtained in the previous step.\n\n## Method 2: Inference Endpoint\n\n### 1. Select the model to deploy\n\nInference Endpoint is only supported for models with the Inference Endpoints option under the Deploy button on the right side of the model details page. As shown below:\n\n![](./_assets/huggingface_hub-05.png)\n\n### 2. Deployment model\n\nClick the Deploy button for the model and select the Inference Endpoint option. If you have not bound a bank card before, you will need to bind the card. Just follow the process. After binding the card, the following interface will appear: modify the configuration according to the requirements, and click Create Endpoint in the lower left corner to create an Inference Endpoint.\n\n![](./_assets/huggingface_hub-06.png)\n\nAfter the model is deployed, you can see the Endpoint URL.\n\n![](./_assets/huggingface_hub-07.png)\n\n### 3. Using access models in Dify\n\nSelect Inference Endpoints for Endpoint Type in `Settings > Model Provider > Hugging face > Model Type`. As shown below:\n\n![](./_assets/huggingface_hub-08.png)\n\nThe API Token is the API Key set at the beginning of the article. The name of the Text-Generation model can be arbitrary, but the name of the Embeddings model needs to be consistent with Hugging Face. The Endpoint URL is the Endpoint URL obtained after the successful deployment of the model in the previous step.\n\n![](./_assets/huggingface_hub-09.png)\n\n> Note: The \"User name / Organization Name\" for Embeddings needs to be filled in according to your deployment method on Hugging Face's [Inference Endpoints](https://huggingface.co/docs/inference-endpoints/guides/access), with either the ''[User name](https://huggingface.co/settings/account)'' or the \"[Organization Name](https://ui.endpoints.huggingface.co/)\".\n",
        "label": {
          "en_US": "Hugging Face Hub"
        },
        "latest_package_identifier": "langgenius/huggingface_hub:0.0.4@f40c1ead2e81acf196a1fbc6602e4ace795e569315059ec3a645ede30db3bca2",
        "latest_version": "0.0.4",
        "model": {
          "background": "#FFF8DC",
          "configurate_methods": [
            "customizable-model"
          ],
          "description": {
            "en_US": "Hugging Face Model"
          },
          "help": {
            "title": {
              "en_US": "Get your API key from Hugging Face Hub",
              "zh_Hans": "从 Hugging Face Hub 获取 API Key"
            },
            "url": {
              "en_US": "https://huggingface.co/settings/tokens"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.svg"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "Hugging Face Model"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": "hosted_inference_api",
                "label": {
                  "en_US": "Endpoint Type",
                  "zh_Hans": "端点类型"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Hosted Inference API"
                    },
                    "show_on": [],
                    "value": "hosted_inference_api"
                  },
                  {
                    "label": {
                      "en_US": "Inference Endpoints"
                    },
                    "show_on": [],
                    "value": "inference_endpoints"
                  }
                ],
                "placeholder": null,
                "required": true,
                "show_on": [],
                "type": "radio",
                "variable": "huggingfacehub_api_type"
              },
              {
                "default": null,
                "label": {
                  "en_US": "API Token",
                  "zh_Hans": "API Token"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Hugging Face Hub API Token here",
                  "zh_Hans": "在此输入您的 Hugging Face Hub API Token"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "huggingfacehub_api_token"
              },
              {
                "default": null,
                "label": {
                  "en_US": "User Name / Organization Name",
                  "zh_Hans": "用户名 / 组织名称"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your User Name / Organization Name here",
                  "zh_Hans": "在此输入您的用户名 / 组织名称"
                },
                "required": true,
                "show_on": [
                  {
                    "value": "text-embedding",
                    "variable": "__model_type"
                  },
                  {
                    "value": "inference_endpoints",
                    "variable": "huggingfacehub_api_type"
                  }
                ],
                "type": "text-input",
                "variable": "huggingface_namespace"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Endpoint URL",
                  "zh_Hans": "端点 URL"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Endpoint URL here",
                  "zh_Hans": "在此输入您的端点 URL"
                },
                "required": true,
                "show_on": [
                  {
                    "value": "inference_endpoints",
                    "variable": "huggingfacehub_api_type"
                  }
                ],
                "type": "text-input",
                "variable": "huggingfacehub_endpoint_url"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Task",
                  "zh_Hans": "Task"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Text-to-Text Generation"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "text2text-generation"
                  },
                  {
                    "label": {
                      "en_US": "Text Generation",
                      "zh_Hans": "文本生成"
                    },
                    "show_on": [
                      {
                        "value": "llm",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "text-generation"
                  },
                  {
                    "label": {
                      "en_US": "Feature Extraction"
                    },
                    "show_on": [
                      {
                        "value": "text-embedding",
                        "variable": "__model_type"
                      }
                    ],
                    "value": "feature-extraction"
                  }
                ],
                "placeholder": null,
                "required": false,
                "show_on": [
                  {
                    "value": "inference_endpoints",
                    "variable": "huggingfacehub_api_type"
                  }
                ],
                "type": "select",
                "variable": "task_type"
              }
            ],
            "model": {
              "label": {
                "en_US": "Model Name",
                "zh_Hans": "模型名称"
              },
              "placeholder": null
            }
          },
          "models": [],
          "position": {},
          "provider": "huggingface_hub",
          "provider_credential_schema": null,
          "supported_model_types": [
            "llm",
            "text-embedding"
          ]
        },
        "name": "huggingface_hub",
        "org": "langgenius",
        "plugin_id": "langgenius/huggingface_hub",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/huggingface_hub.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": false,
              "llm": false,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": false
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-22T07:03:42Z",
        "version_updated_at": "2025-04-22T07:03:42Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "GitHub is an online software source code hosting service.",
          "pt_BR": "GitHub é uma plataforma online para serviços de hospedagem de código fonte de software.",
          "zh_Hans": "GitHub是一个在线软件源代码托管服务平台。"
        },
        "category": "tool",
        "created_at": "2024-11-29T06:16:42Z",
        "endpoint": {},
        "icon": "langgenius/packages/github/_assets/icon.svg",
        "index_id": "langgenius___github",
        "install_count": 8139,
        "introduction": "# GitHub\n\n## Overview\n\nGitHub is a web-based platform for version control and collaboration, primarily used for software development. As a tool in Dify, it provides users the ability to search repositories by keywords.\n\n## Configuration\n\n### 1. Apply for API Key and Version\n\nPlease apply for an [API Key](https://github.com/settings/personal-access-tokens) and the [API version](https://docs.github.com/en/rest/about-the-rest-api/api-versions?apiVersion=2022-11-28).\n\n### 2. Get GitHub tools from Plugin Marketplace\n\nThe GitHub tools can be found in the Plugin Marketplace. Please install it first.\n\n### 3. Fill in the configuration in Dify\n\nOn the Dify navigation page, click `Tools > GitHub > Authorize` and fill in the API Key.\n\n![](./_assets/github_1.PNG)\n\n### 4. Using the tool\n\nYou can use the GitHub tool in the following application types:\n\n#### Chatflow / Workflow applications\n\nBoth Chatflow and Workflow applications support adding a GitHub tool node.\n\n![](./_assets/github_2.PNG)\n\n#### Agent applications\n\nAdd the GitHub tool in the Agent application, then enter repository search instructions to call this tool.\n\n![](./_assets/github_3.PNG)",
        "label": {
          "en_US": "GitHub",
          "pt_BR": "GitHub",
          "zh_Hans": "GitHub"
        },
        "latest_package_identifier": "langgenius/github:0.0.5@431d6d7751f88622e508b913f604edc8c1765e9a6d90d6fa15aea92b627e7676",
        "latest_version": "0.0.5",
        "model": {},
        "name": "github",
        "org": "langgenius",
        "plugin_id": "langgenius/github",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/github.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "utilities"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Get your Access Tokens from GitHub",
                "pt_BR": "Obtenha sua chave da API do Google no Google",
                "zh_Hans": "从 GitHub 获取您的 Access Tokens"
              },
              "label": {
                "en_US": "Access Tokens",
                "pt_BR": "Tokens de acesso",
                "zh_Hans": "Access Tokens"
              },
              "name": "access_tokens",
              "options": null,
              "placeholder": {
                "en_US": "Please input your GitHub Access Tokens",
                "pt_BR": "Insira seus Tokens de Acesso do GitHub",
                "zh_Hans": "请输入你的 GitHub Access Tokens"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://github.com/settings/tokens?type=beta"
            },
            {
              "default": "2022-11-28",
              "help": {
                "en_US": "Get your API Version from GitHub",
                "pt_BR": "Obtenha sua versão da API do GitHub",
                "zh_Hans": "从 GitHub 获取您的 API Version"
              },
              "label": {
                "en_US": "API Version",
                "pt_BR": "Versão da API",
                "zh_Hans": "API Version"
              },
              "name": "api_version",
              "options": null,
              "placeholder": {
                "en_US": "Please input your GitHub API Version",
                "pt_BR": "Insira sua versão da API do GitHub",
                "zh_Hans": "请输入你的 GitHub API Version"
              },
              "required": false,
              "scope": null,
              "type": "text-input",
              "url": "https://docs.github.com/en/rest/about-the-rest-api/api-versions?apiVersion=2022-11-28"
            }
          ],
          "identity": {
            "author": "CharlieWei",
            "description": {
              "en_US": "GitHub is an online software source code hosting service.",
              "pt_BR": "GitHub é uma plataforma online para serviços de hospedagem de código fonte de software.",
              "zh_Hans": "GitHub 是一个在线软件源代码托管服务平台。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "GitHub",
              "pt_BR": "GitHub",
              "zh_Hans": "GitHub"
            },
            "name": "github",
            "tags": [
              "utilities"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Search the GitHub repository to retrieve the open source projects you need",
                  "pt_BR": "Pesquise o repositório do GitHub para recuperar os projetos de código aberto necessários.",
                  "zh_Hans": "搜索GitHub仓库，检索你需要的开源项目。"
                },
                "llm": "A tool when you wants to search for popular warehouses or open source projects for any keyword. format query condition like \"keywords+language:js\", language can be other dev languages."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "CharlieWei",
                "label": {
                  "en_US": "Search Repositories",
                  "pt_BR": "Pesquisar Repositórios",
                  "zh_Hans": "仓库搜索"
                },
                "name": "github_repositories"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "You want to find the project development language, keywords, For example. Find 10 Python developed PDF document parsing projects.",
                    "pt_BR": "Você deseja encontrar a linguagem de desenvolvimento do projeto, palavras-chave, Por exemplo. Encontre 10 projetos de análise de documentos PDF desenvolvidos em Python.",
                    "zh_Hans": "你想要找的项目开发语言、关键字，如：找10个Python开发的PDF文档解析项目。"
                  },
                  "label": {
                    "en_US": "query",
                    "pt_BR": "consulta",
                    "zh_Hans": "关键字"
                  },
                  "llm_description": "The query of you want to search, format query condition like \"keywords+language:js\", language can be other dev languages.",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 5,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Number of records returned by sorting based on stars. 5 is returned by default.",
                    "pt_BR": "Número de registros retornados por classificação com base em estrelas. 5 é retornado por padrão.",
                    "zh_Hans": "基于stars排序返回的记录数, 默认返回5条。"
                  },
                  "label": {
                    "en_US": "Top N",
                    "pt_BR": "Topo N",
                    "zh_Hans": "Top N"
                  },
                  "llm_description": "Extract the first N records from the returned result.",
                  "max": null,
                  "min": null,
                  "name": "top_n",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Gets the README from a repository directory.",
                  "pt_BR": "Obter o README de um diretório do repositório.",
                  "zh_Hans": "从存储库某个目录中获取README"
                },
                "llm": "A tool when you wants to gets the README content from a repository directory."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "itning",
                "label": {
                  "en_US": "Get README content",
                  "pt_BR": "Obter conteúdo do README",
                  "zh_Hans": "获取README内容"
                },
                "name": "github_repository_readme"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The account owner of the repository. The name is not case sensitive.",
                    "pt_BR": "Proprietário da conta do repositório. O nome não diferencia maiúsculas de minúsculas.",
                    "zh_Hans": "仓库的账户所有者。名称不区分大小写。"
                  },
                  "label": {
                    "en_US": "owner",
                    "pt_BR": "owner",
                    "zh_Hans": "owner"
                  },
                  "llm_description": "The account owner of the repository. The name is not case sensitive.",
                  "max": null,
                  "min": null,
                  "name": "owner",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The name of the repository without the .git extension. The name is not case sensitive.",
                    "pt_BR": "O nome do repositório sem a extensão .git. O nome não diferencia maiúsculas de minúsculas.",
                    "zh_Hans": "仓库名称不带.git扩展名。名称不区分大小写。"
                  },
                  "label": {
                    "en_US": "repo",
                    "pt_BR": "repo",
                    "zh_Hans": "repo"
                  },
                  "llm_description": "The name of the repository without the .git extension. The name is not case sensitive.",
                  "max": null,
                  "min": null,
                  "name": "repo",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The name of the commit/branch/tag. Default: the repository’s default branch.",
                    "pt_BR": "O nome do commit/branch/tag. Valor padrão: a branch padrão do repositório.",
                    "zh_Hans": "commit/branch/tag的名称。默认值：仓库的默认分支。"
                  },
                  "label": {
                    "en_US": "ref",
                    "pt_BR": "ref",
                    "zh_Hans": "ref"
                  },
                  "llm_description": "The name of the commit/branch/tag. Default: the repository’s default branch.",
                  "max": null,
                  "min": null,
                  "name": "ref",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The alternate path to look for a README file",
                    "pt_BR": "O caminho alternativo para encontrar o arquivo README",
                    "zh_Hans": "查找README文件的备用路径。"
                  },
                  "label": {
                    "en_US": "dir",
                    "pt_BR": "dir",
                    "zh_Hans": "dir"
                  },
                  "llm_description": "The alternate path to look for a README file",
                  "max": null,
                  "min": null,
                  "name": "dir",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-01T09:15:37Z",
        "version_updated_at": "2025-04-01T09:15:37Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "ComfyUI is a tool for generating images which can be deployed locally.",
          "zh_Hans": "ComfyUI 是一个可以在本地部署的图片生成的工具。"
        },
        "category": "tool",
        "created_at": "2025-01-02T06:32:13Z",
        "endpoint": {},
        "icon": "langgenius/packages/comfyui/_assets/icon.png",
        "index_id": "langgenius___comfyui",
        "install_count": 7991,
        "introduction": "# ComfyUI\n\n## Overview\n\n[ComfyUI](https://www.comfy.org/) is the most powerful and modular diffusion model GUI, API and backend with a graph/nodes interface. Now you can use it in Dify, input the prompt or images, and get the generated image.\n\n## Configuration\n\n### 1. Ensure that the ComfyUI workflow is running normally\n\nPlease refer to its [official documentation](https://docs.comfy.org/get_started/gettingstarted) to ensure that ComfyUI can run normally and generate images.\n\n### 2. Prompt setting\n\nIf you don't need Dify to pass in the prompt, you can skip this step. If your prompt node is connected to the only `KSampler` node in ComfyUI, you can skip this step.\n\nOtherwise, use the string `{positive_prompt}` to replace the positive prompt content, and `{negative_prompt}` to replace the negative prompt content.\n\n![](./_assets/comfyui_1.PNG)\n\n### 3. Export the API file of the workflow\n\n![](./_assets/comfyui_2.PNG)\n\nAs shown in the figure, select `Save(API Format)`. If there is no such selection, you need to enable `Dev Mode` in the settings.\n\n### 4. Get ComfyUI tools from Plugin Marketplace\n\nThe ComfyUI tools could be found at the Plugin Marketplace, please install it first.\n\n### 5. Integrate ComfyUI in Dify\n\nOn the Dify navigation page, click `Tools > ComfyUI > To Authentication` and fill in the URL of ComfyUI Server.\n\n![](./_assets/comfyui_3.PNG)\n\n### 6. Use ComfyUI in Dify\n\nYou can use the ComfyUI tool in the following application types:\n\n![](./_assets/comfyui_4.PNG)\n\n#### Chatflow / Workflow applications\n\nBoth Chatflow and Workflow applications support the `ComfyUI` tool node. After adding it, you need to fill in the \"Input Variables → Prompt\" in the node with variables to reference the user's input prompt or the content generated by the previous node. Finally, use the variable to reference the image output by `ComfyUI` in the \"End\" node.\n\n#### Agent applications\n\nAdd the `ComfyUI` tool in the Agent application, then send a picture description in the dialog box to call the tool to generate an AI image.\n\n### 7. Image input\n\nSome ComfyUI workflows require multiple images inputs. In Dify, it will find every `LoadImage` node in the `WORKFLOW JSON` and fill in the image files input by the user in order. When you want to change this order, you can adjust it by filling in the `Image node ID list`. For example, if your workflow needs to input images into the 35th, 69th, and 87th nodes, then input `69,35,87` will pass the first image to the 69th node.",
        "label": {
          "en_US": "ComfyUI",
          "zh_Hans": "ComfyUI"
        },
        "latest_package_identifier": "langgenius/comfyui:0.0.6@e14cdc219aa7470c269f0df056884147bbcbc0a5bf5ed40f0079d99afbb4b08d",
        "latest_version": "0.0.6",
        "model": {},
        "name": "comfyui",
        "org": "langgenius",
        "plugin_id": "langgenius/comfyui",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/comfyui.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "image"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "The URL of ComfyUI Server",
                "zh_Hans": "ComfyUI服务器的URL"
              },
              "name": "base_url",
              "options": null,
              "placeholder": {
                "en_US": "Please input your ComfyUI server's Base URL",
                "zh_Hans": "请输入你的 ComfyUI 服务器的 Base URL"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": "https://docs.dify.ai/guides/tools/tool-configuration/comfyui"
            }
          ],
          "identity": {
            "author": "Qun",
            "description": {
              "en_US": "ComfyUI is a tool for generating images which can be deployed locally.",
              "zh_Hans": "ComfyUI 是一个可以在本地部署的图片生成的工具。"
            },
            "icon": "icon.png",
            "label": {
              "en_US": "ComfyUI",
              "zh_Hans": "ComfyUI"
            },
            "name": "comfyui",
            "tags": [
              "image"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Run ComfyUI workflow.",
                  "zh_Hans": "运行ComfyUI工作流。"
                },
                "llm": "Run ComfyUI workflow."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "hjlarry",
                "label": {
                  "en_US": "workflow",
                  "zh_Hans": "工作流"
                },
                "name": "workflow"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Image prompt, you can check the official documentation of Stable Diffusion or FLUX",
                    "zh_Hans": "图像提示词，您可以查看 Stable Diffusion 或者 FLUX 的官方文档"
                  },
                  "label": {
                    "en_US": "Prompt",
                    "zh_Hans": "提示词"
                  },
                  "llm_description": "Image prompt, you should describe the image you want to generate as a list of words as possible as detailed, the prompt must be written in English.",
                  "max": null,
                  "min": null,
                  "name": "positive_prompt",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Negative prompt, you can check the official documentation of Stable Diffusion or FLUX",
                    "zh_Hans": "负面提示词，您可以查看 Stable Diffusion 或者 FLUX 的官方文档"
                  },
                  "label": {
                    "en_US": "Negative Prompt",
                    "zh_Hans": "负面提示词"
                  },
                  "llm_description": "Negative prompt, you should describe the image you don't want to generate as a list of words as possible as detailed, the prompt must be written in English.",
                  "max": null,
                  "min": null,
                  "name": "negative_prompt",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The input images",
                    "zh_Hans": "输入的图片"
                  },
                  "label": {
                    "en_US": "Input Images",
                    "zh_Hans": "输入的图片"
                  },
                  "llm_description": "The input images, used to transfer to the comfyui workflow to generate another image.",
                  "max": null,
                  "min": null,
                  "name": "images",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "files"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "exported from ComfyUI workflow",
                    "zh_Hans": "从ComfyUI的工作流中导出"
                  },
                  "label": {
                    "en_US": "Workflow JSON"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "workflow_json",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "When the workflow has multiple image nodes, enter the ID list of these nodes, and the images will be passed to ComfyUI in the order of the list.",
                    "zh_Hans": "当工作流有多个图片节点时，输入这些节点的ID列表，图片将按列表顺序传给ComfyUI"
                  },
                  "label": {
                    "en_US": "Image Node ID List",
                    "zh_Hans": "图片节点ID列表"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "image_ids",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "If you need to generate different images each time, you need to enter the ID of the seed node.",
                    "zh_Hans": "如果需要每次生成时使用不同的种子，需要输入包含种子的节点的ID"
                  },
                  "label": {
                    "en_US": "Seed Node Id",
                    "zh_Hans": "种子节点ID"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "seed_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "a pre-defined comfyui workflow that can use one model and up to 3 loras to generate images. Support SD1.5, SDXL, SD3 and FLUX which contain text encoders/clip, but does not support models that requires a triple clip loader.",
                  "pt_BR": "a pre-defined comfyui workflow that can use one model and up to 3 loras to generate images. Support SD1.5, SDXL, SD3 and FLUX which contain text encoders/clip, but does not support models that requires a triple clip loader.",
                  "zh_Hans": "一个预定义的 ComfyUI 工作流，可以使用一个模型和最多3个loras来生成图像。支持包含文本编码器/clip的SD1.5、SDXL、SD3和FLUX，但不支持需要clip加载器的模型。"
                },
                "llm": "draw the image you want based on your prompt."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Qun",
                "label": {
                  "en_US": "Txt2Img",
                  "pt_BR": "Txt2Img",
                  "zh_Hans": "Txt2Img"
                },
                "name": "txt2img"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Image prompt, you can check the official documentation of Stable Diffusion or FLUX",
                    "pt_BR": "Image prompt, you can check the official documentation of Stable Diffusion or FLUX",
                    "zh_Hans": "图像提示词，您可以查看 Stable Diffusion 或者 FLUX 的官方文档"
                  },
                  "label": {
                    "en_US": "Prompt",
                    "pt_BR": "Prompt",
                    "zh_Hans": "提示词"
                  },
                  "llm_description": "Image prompt of Stable Diffusion, you should describe the image you want to generate as a list of words as possible as detailed, the prompt must be written in English.",
                  "max": null,
                  "min": null,
                  "name": "prompt",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Model Name",
                    "pt_BR": "Model Name",
                    "zh_Hans": "模型名称"
                  },
                  "label": {
                    "en_US": "Model Name",
                    "pt_BR": "Model Name",
                    "zh_Hans": "模型名称"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Model Type",
                    "pt_BR": "Model Type",
                    "zh_Hans": "模型类型"
                  },
                  "label": {
                    "en_US": "Model Type",
                    "pt_BR": "Model Type",
                    "zh_Hans": "模型类型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "model_type",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Lora 1",
                    "pt_BR": "Lora 1",
                    "zh_Hans": "Lora 1"
                  },
                  "label": {
                    "en_US": "Lora 1",
                    "pt_BR": "Lora 1",
                    "zh_Hans": "Lora 1"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "lora_1",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Lora Strength 1",
                    "pt_BR": "Lora Strength 1",
                    "zh_Hans": "Lora模型的权重"
                  },
                  "label": {
                    "en_US": "Lora Strength 1",
                    "pt_BR": "Lora Strength 1",
                    "zh_Hans": "Lora Strength 1"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "lora_strength_1",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 20,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Steps",
                    "pt_BR": "Steps",
                    "zh_Hans": "Steps"
                  },
                  "label": {
                    "en_US": "Steps",
                    "pt_BR": "Steps",
                    "zh_Hans": "Steps"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "steps",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 1024,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Width",
                    "pt_BR": "Width",
                    "zh_Hans": "Width"
                  },
                  "label": {
                    "en_US": "Width",
                    "pt_BR": "Width",
                    "zh_Hans": "Width"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "width",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 1024,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Height",
                    "pt_BR": "Height",
                    "zh_Hans": "Height"
                  },
                  "label": {
                    "en_US": "Height",
                    "pt_BR": "Height",
                    "zh_Hans": "Height"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "height",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "bad art, ugly, deformed, watermark, duplicated, discontinuous lines",
                  "form": "llm",
                  "human_description": {
                    "en_US": "Negative prompt",
                    "pt_BR": "Negative prompt",
                    "zh_Hans": "Negative prompt"
                  },
                  "label": {
                    "en_US": "Negative prompt",
                    "pt_BR": "Negative prompt",
                    "zh_Hans": "Negative prompt"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "negative_prompt",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 7,
                  "form": "llm",
                  "human_description": {
                    "en_US": "CFG Scale",
                    "pt_BR": "CFG Scale",
                    "zh_Hans": "提示词相关性(CFG Scale)"
                  },
                  "label": {
                    "en_US": "CFG Scale",
                    "pt_BR": "CFG Scale",
                    "zh_Hans": "CFG Scale"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "cfg",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Sampling method",
                    "pt_BR": "Sampling method",
                    "zh_Hans": "Sampling method"
                  },
                  "label": {
                    "en_US": "Sampling method",
                    "pt_BR": "Sampling method",
                    "zh_Hans": "Sampling method"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "sampler_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Scheduler",
                    "pt_BR": "Scheduler",
                    "zh_Hans": "Scheduler"
                  },
                  "label": {
                    "en_US": "Scheduler",
                    "pt_BR": "Scheduler",
                    "zh_Hans": "Scheduler"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "scheduler",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Lora 2",
                    "pt_BR": "Lora 2",
                    "zh_Hans": "Lora 2"
                  },
                  "label": {
                    "en_US": "Lora 2",
                    "pt_BR": "Lora 2",
                    "zh_Hans": "Lora 2"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "lora_2",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Lora Strength 2",
                    "pt_BR": "Lora Strength 2",
                    "zh_Hans": "Lora模型的权重"
                  },
                  "label": {
                    "en_US": "Lora Strength 2",
                    "pt_BR": "Lora Strength 2",
                    "zh_Hans": "Lora Strength 2"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "lora_strength_2",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Lora 3",
                    "pt_BR": "Lora 3",
                    "zh_Hans": "Lora 3"
                  },
                  "label": {
                    "en_US": "Lora 3",
                    "pt_BR": "Lora 3",
                    "zh_Hans": "Lora 3"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "lora_3",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Lora Strength 3",
                    "pt_BR": "Lora Strength 3",
                    "zh_Hans": "Lora模型的权重"
                  },
                  "label": {
                    "en_US": "Lora Strength 3",
                    "pt_BR": "Lora Strength 3",
                    "zh_Hans": "Lora Strength 3"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "lora_strength_3",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-21T06:45:13Z",
        "version_updated_at": "2025-04-21T06:45:13Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Models provided by Tencent Hunyuan, such as hunyuan-standard, hunyuan-standard-256k, hunyuan-pro, hunyuan-role, hunyuan-large, hunyuan-large-role, hunyuan-turbo-latest, hunyuan-large-longcontext, hunyuan-turbo, hunyuan-vision, hunyuan-turbo-vision, hunyuan-functioncall and hunyuan-lite.",
          "zh_Hans": "腾讯混元提供的模型，例如 hunyuan-standard、 hunyuan-standard-256k, hunyuan-pro, hunyuan-role, hunyuan-large, hunyuan-large-role, hunyuan-turbo-latest, hunyuan-large-longcontext, hunyuan-turbo, hunyuan-vision, hunyuan-turbo-vision, hunyuan-functioncall 和 hunyuan-lite。"
        },
        "category": "model",
        "created_at": "2025-01-02T08:16:09Z",
        "endpoint": {},
        "icon": "langgenius/packages/hunyuan/_assets/icon_s_en.png",
        "index_id": "langgenius___hunyuan",
        "install_count": 7823,
        "introduction": "",
        "label": {
          "en_US": "Hunyuan",
          "zh_Hans": "腾讯混元"
        },
        "latest_package_identifier": "langgenius/hunyuan:0.0.5@956d1ee1a8e4153aa942ea4c2650f9b15f7d11d890004dc4423733bfc3f583bb",
        "latest_version": "0.0.5",
        "model": {
          "background": "#F6F7F7",
          "configurate_methods": [
            "predefined-model"
          ],
          "description": {
            "en_US": "Models provided by Tencent Hunyuan, such as hunyuan-standard, hunyuan-standard-256k, hunyuan-pro and hunyuan-lite.",
            "zh_Hans": "腾讯混元提供的模型，例如 hunyuan-standard、 hunyuan-standard-256k, hunyuan-pro 和 hunyuan-lite。"
          },
          "help": {
            "title": {
              "en_US": "Get your API Key from Tencent Hunyuan",
              "zh_Hans": "从腾讯混元获取 API Key"
            },
            "url": {
              "en_US": "https://console.cloud.tencent.com/cam/capi"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.png"
          },
          "icon_small": {
            "en_US": "icon_s_en.png"
          },
          "label": {
            "en_US": "Hunyuan",
            "zh_Hans": "腾讯混元"
          },
          "model_credential_schema": null,
          "models": [
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "multi-tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "hunyuan-functioncall",
                "zh_Hans": "hunyuan-functioncall"
              },
              "model": "hunyuan-functioncall",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 32000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "Allow the model to perform external search to enhance the generation results.",
                    "zh_Hans": "功能增强（如搜索）开关，关闭时将直接由主模型生成回复内容，可以降低响应时延（对于流式输出时的首字时延尤为明显）。但在少数场景里，回复效果可能会下降。"
                  },
                  "label": {
                    "en_US": "Enable Enhancement",
                    "zh_Hans": "功能增强"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_enhance",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.004",
                "output": "0.008",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "multi-tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "hunyuan-large-longcontext",
                "zh_Hans": "hunyuan-large-longcontext"
              },
              "model": "hunyuan-large-longcontext",
              "model_properties": {
                "context_size": 134000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 134000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "Allow the model to perform external search to enhance the generation results.",
                    "zh_Hans": "功能增强（如搜索）开关，关闭时将直接由主模型生成回复内容，可以降低响应时延（对于流式输出时的首字时延尤为明显）。但在少数场景里，回复效果可能会下降。"
                  },
                  "label": {
                    "en_US": "Enable Enhancement",
                    "zh_Hans": "功能增强"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_enhance",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.006",
                "output": "0.018",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "multi-tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "hunyuan-large-role",
                "zh_Hans": "hunyuan-large-role"
              },
              "model": "hunyuan-large-role",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 32000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "Allow the model to perform external search to enhance the generation results.",
                    "zh_Hans": "功能增强（如搜索）开关，关闭时将直接由主模型生成回复内容，可以降低响应时延（对于流式输出时的首字时延尤为明显）。但在少数场景里，回复效果可能会下降。"
                  },
                  "label": {
                    "en_US": "Enable Enhancement",
                    "zh_Hans": "功能增强"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_enhance",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.004",
                "output": "0.008",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "multi-tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "hunyuan-large",
                "zh_Hans": "hunyuan-large"
              },
              "model": "hunyuan-large",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 32000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "Allow the model to perform external search to enhance the generation results.",
                    "zh_Hans": "功能增强（如搜索）开关，关闭时将直接由主模型生成回复内容，可以降低响应时延（对于流式输出时的首字时延尤为明显）。但在少数场景里，回复效果可能会下降。"
                  },
                  "label": {
                    "en_US": "Enable Enhancement",
                    "zh_Hans": "功能增强"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_enhance",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.004",
                "output": "0.012",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "multi-tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "hunyuan-lite",
                "zh_Hans": "hunyuan-lite"
              },
              "model": "hunyuan-lite",
              "model_properties": {
                "context_size": 256000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 256000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "multi-tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "hunyuan-pro",
                "zh_Hans": "hunyuan-pro"
              },
              "model": "hunyuan-pro",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 32000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "Allow the model to perform external search to enhance the generation results.",
                    "zh_Hans": "功能增强（如搜索）开关，关闭时将直接由主模型生成回复内容，可以降低响应时延（对于流式输出时的首字时延尤为明显）。但在少数场景里，回复效果可能会下降。"
                  },
                  "label": {
                    "en_US": "Enable Enhancement",
                    "zh_Hans": "功能增强"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_enhance",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.03",
                "output": "0.1",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "multi-tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "hunyuan-role",
                "zh_Hans": "hunyuan-role"
              },
              "model": "hunyuan-role",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 32000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "Allow the model to perform external search to enhance the generation results.",
                    "zh_Hans": "功能增强（如搜索）开关，关闭时将直接由主模型生成回复内容，可以降低响应时延（对于流式输出时的首字时延尤为明显）。但在少数场景里，回复效果可能会下降。"
                  },
                  "label": {
                    "en_US": "Enable Enhancement",
                    "zh_Hans": "功能增强"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_enhance",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.004",
                "output": "0.008",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "multi-tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "hunyuan-standard-256K",
                "zh_Hans": "hunyuan-standard-256K"
              },
              "model": "hunyuan-standard-256K",
              "model_properties": {
                "context_size": 256000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 256000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "Allow the model to perform external search to enhance the generation results.",
                    "zh_Hans": "功能增强（如搜索）开关，关闭时将直接由主模型生成回复内容，可以降低响应时延（对于流式输出时的首字时延尤为明显）。但在少数场景里，回复效果可能会下降。"
                  },
                  "label": {
                    "en_US": "Enable Enhancement",
                    "zh_Hans": "功能增强"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_enhance",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.015",
                "output": "0.06",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "multi-tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "hunyuan-standard",
                "zh_Hans": "hunyuan-standard"
              },
              "model": "hunyuan-standard",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 32000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "Allow the model to perform external search to enhance the generation results.",
                    "zh_Hans": "功能增强（如搜索）开关，关闭时将直接由主模型生成回复内容，可以降低响应时延（对于流式输出时的首字时延尤为明显）。但在少数场景里，回复效果可能会下降。"
                  },
                  "label": {
                    "en_US": "Enable Enhancement",
                    "zh_Hans": "功能增强"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_enhance",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.0045",
                "output": "0.0005",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "multi-tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "hunyuan-turbo-latest",
                "zh_Hans": "hunyuan-turbo-latest"
              },
              "model": "hunyuan-turbo-latest",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 32000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "Allow the model to perform external search to enhance the generation results.",
                    "zh_Hans": "功能增强（如搜索）开关，关闭时将直接由主模型生成回复内容，可以降低响应时延（对于流式输出时的首字时延尤为明显）。但在少数场景里，回复效果可能会下降。"
                  },
                  "label": {
                    "en_US": "Enable Enhancement",
                    "zh_Hans": "功能增强"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_enhance",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.015",
                "output": "0.05",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "multi-tool-call",
                "stream-tool-call",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "hunyuan-turbo-vision",
                "zh_Hans": "hunyuan-turbo-vision"
              },
              "model": "hunyuan-turbo-vision",
              "model_properties": {
                "context_size": 8000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "Allow the model to perform external search to enhance the generation results.",
                    "zh_Hans": "功能增强（如搜索）开关，关闭时将直接由主模型生成回复内容，可以降低响应时延（对于流式输出时的首字时延尤为明显）。但在少数场景里，回复效果可能会下降。"
                  },
                  "label": {
                    "en_US": "Enable Enhancement",
                    "zh_Hans": "功能增强"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_enhance",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.08",
                "output": "0.08",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "multi-tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "hunyuan-turbo",
                "zh_Hans": "hunyuan-turbo"
              },
              "model": "hunyuan-turbo",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 32000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "Allow the model to perform external search to enhance the generation results.",
                    "zh_Hans": "功能增强（如搜索）开关，关闭时将直接由主模型生成回复内容，可以降低响应时延（对于流式输出时的首字时延尤为明显）。但在少数场景里，回复效果可能会下降。"
                  },
                  "label": {
                    "en_US": "Enable Enhancement",
                    "zh_Hans": "功能增强"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_enhance",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.015",
                "output": "0.05",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "multi-tool-call",
                "stream-tool-call",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "hunyuan-vision",
                "zh_Hans": "hunyuan-vision"
              },
              "model": "hunyuan-vision",
              "model_properties": {
                "context_size": 8000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "Allow the model to perform external search to enhance the generation results.",
                    "zh_Hans": "功能增强（如搜索）开关，关闭时将直接由主模型生成回复内容，可以降低响应时延（对于流式输出时的首字时延尤为明显）。但在少数场景里，回复效果可能会下降。"
                  },
                  "label": {
                    "en_US": "Enable Enhancement",
                    "zh_Hans": "功能增强"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_enhance",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.018",
                "output": "0.018",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "lke-text-embedding-v1"
              },
              "model": "lke-text-embedding-v1",
              "model_properties": {
                "context_size": 1024,
                "max_chunks": 1
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": null
            }
          ],
          "position": {
            "llm": [
              "hunyuan-lite",
              "hunyuan-standard",
              "hunyuan-standard-256k",
              "hunyuan-pro",
              "hunyuan-turbo",
              "hunyuan-vision",
              "hunyuan-role",
              "hunyuan-large",
              "hunyuan-large-role",
              "hunyuan-large-longcontext",
              "hunyuan-turbo-latest",
              "hunyuan-turbo-vision",
              "hunyuan-functioncall"
            ]
          },
          "provider": "hunyuan",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "Secret ID"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Secret ID",
                  "zh_Hans": "在此输入您的 Secret ID"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "secret_id"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Secret Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Secret Key",
                  "zh_Hans": "在此输入您的 Secret Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "secret_key"
              }
            ]
          },
          "supported_model_types": [
            "llm",
            "text-embedding"
          ]
        },
        "name": "hunyuan",
        "org": "langgenius",
        "plugin_id": "langgenius/hunyuan",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/hunyuan.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-03-21T12:38:59Z",
        "version_updated_at": "2025-03-21T12:38:59Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "The image generation API provided by SiliconFlow includes Flux and Stable Diffusion models."
        },
        "category": "tool",
        "created_at": "2024-12-06T10:48:28Z",
        "endpoint": {},
        "icon": "langgenius/packages/siliconflow_tool/_assets/icon.svg",
        "index_id": "langgenius___siliconflow_tool",
        "install_count": 7588,
        "introduction": "# SiliconFlow\n\n## Overview\n\nSiliconFlow provides high-quality GenAI services based on excellent open-source foundation models. You can use SiliconFlow in Dify to call image generation models like Flux and Stable Diffusion, and build your own AI image generation application.\n\n## Configuration\n\n### 1. Apply for SiliconCloud API Key\n\nCreate a new API Key on the [SiliconCloud API management](https://cloud.siliconflow.cn/account/ak) page and ensure that you have sufficient balance.\n\n### 2. Get SiliconFlow tools from Plugin Marketplace\n\nThe SiliconFlow tools could be found at the Plugin Marketplace, please install it first.\n\n### 3. Fill in the configuration in Dify\n\nOn the Dify navigation page, click `Tools > SiliconFlow > To Authorize` and fill in the API Key.\n\n![](./_assets/siliconflow_2.PNG)\n\n### 4. Using the tool\n\nYou can use the SiliconFlow tool in the following application types:\n\n![](./_assets/siliconflow_3.png)\n\n#### Chatflow / Workflow applications\n\nBoth Chatflow and Workflow applications support the SiliconFlow tool node. After adding it, you need to fill in the \"Input Variables → Prompt\" in the node with variables to reference the user's input prompt or the content generated by the previous node. Finally, use the variable to reference the image output by SiliconFlow in the \"End\" node.\n\n#### Agent applications\n\nAdd the SiliconFlow tool in the Agent application, then send a picture description in the dialog box to call the tool to generate an AI image.\n\n#### About SiliconFlow\n\nSiliconFlow is committed to building a scalable, standardized, and high-performance AI Infra platform. It offers SiliconCloud (the model cloud service platform), SiliconLLM (the LLM inference engine), and OneDiff (the high-performance text-to-image/video acceleration library). These solutions help enterprises and individual users deploy AI models efficiently and cost-effectively.\n\n[Website](https://siliconflow.cn/) | [SiliconCloud](https://cloud.siliconflow.cn/playground/chat) | [Discord](https://discord.gg/3nAMSVJekY) | [X](https://twitter.com/SiliconFlowAI) \n",
        "label": {
          "en_US": "SiliconFlow"
        },
        "latest_package_identifier": "langgenius/siliconflow_tool:0.0.4@79df250b67a952dbd9c724c6a8b37032bae6c8f83cda88a0309508be9aa80642",
        "latest_version": "0.0.4",
        "model": {},
        "name": "siliconflow_tool",
        "org": "langgenius",
        "plugin_id": "langgenius/siliconflow_tool",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/siliconflow.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "image"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "SiliconFlow API Key"
              },
              "name": "siliconFlow_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your SiliconFlow API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://cloud.siliconflow.cn/account/ak"
            }
          ],
          "identity": {
            "author": "hjlarry, SiliconFlow, Inc.",
            "description": {
              "en_US": "The image generation API provided by SiliconFlow includes Flux and Stable Diffusion models."
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "SiliconFlow"
            },
            "name": "siliconflow",
            "tags": [
              "image"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Generate image via SiliconFlow's flux model."
                },
                "llm": "This tool is used to generate image from prompt via SiliconFlow's flux model."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "hjlarry, SiliconFlow, Inc.",
                "label": {
                  "en_US": "Flux"
                },
                "name": "flux"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The text prompt used to generate the image.",
                    "zh_Hans": "建议用英文的生成图片提示词以获得更好的生成效果。"
                  },
                  "label": {
                    "en_US": "prompt",
                    "zh_Hans": "提示词"
                  },
                  "llm_description": "this prompt text will be used to generate image.",
                  "max": null,
                  "min": null,
                  "name": "prompt",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "schnell",
                  "form": "form",
                  "human_description": {
                    "en_US": "Choose the model version for image generation",
                    "zh_Hans": "选择用于图像生成的模型版本"
                  },
                  "label": {
                    "en_US": "Choose Image Model",
                    "zh_Hans": "选择生成图片的模型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": [
                    {
                      "label": {
                        "en_US": "Flux.1-schnell"
                      },
                      "value": "schnell"
                    },
                    {
                      "label": {
                        "en_US": "Flux.1-dev"
                      },
                      "value": "dev"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "1024x1024",
                  "form": "form",
                  "human_description": {
                    "en_US": "Select the dimensions of the generated image",
                    "zh_Hans": "选择生成图片的尺寸"
                  },
                  "label": {
                    "en_US": "Choose Image Size",
                    "zh_Hans": "选择生成的图片大小"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "image_size",
                  "options": [
                    {
                      "label": {
                        "en_US": "1024x1024"
                      },
                      "value": "1024x1024"
                    },
                    {
                      "label": {
                        "en_US": "768x1024"
                      },
                      "value": "768x1024"
                    },
                    {
                      "label": {
                        "en_US": "576x1024"
                      },
                      "value": "576x1024"
                    },
                    {
                      "label": {
                        "en_US": "512x1024"
                      },
                      "value": "512x1024"
                    },
                    {
                      "label": {
                        "en_US": "1024x576"
                      },
                      "value": "1024x576"
                    },
                    {
                      "label": {
                        "en_US": "768x512"
                      },
                      "value": "768x512"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 20,
                  "form": "form",
                  "human_description": {
                    "en_US": "The number of inference steps to perform. More steps produce higher quality but take longer.",
                    "zh_Hans": "执行的推理步骤数量。更多的步骤可以产生更高质量的结果，但需要更长的时间。"
                  },
                  "label": {
                    "en_US": "Num Inference Steps",
                    "zh_Hans": "生成图片的步数"
                  },
                  "llm_description": "",
                  "max": 100,
                  "min": 1,
                  "name": "num_inference_steps",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The same seed and prompt can produce similar images.",
                    "zh_Hans": "相同的种子和提示可以产生相似的图像。"
                  },
                  "label": {
                    "en_US": "Seed",
                    "zh_Hans": "种子"
                  },
                  "llm_description": "",
                  "max": 9999999999,
                  "min": 0,
                  "name": "seed",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Generate image via SiliconFlow's stable diffusion model."
                },
                "llm": "This tool is used to generate image from prompt via SiliconFlow's stable diffusion model."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "hjlarry, SiliconFlow, Inc.",
                "label": {
                  "en_US": "Stable Diffusion"
                },
                "name": "stable_diffusion"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The text prompt used to generate the image.",
                    "zh_Hans": "用于生成图片的文字提示词"
                  },
                  "label": {
                    "en_US": "prompt",
                    "zh_Hans": "提示词"
                  },
                  "llm_description": "this prompt text will be used to generate image.",
                  "max": null,
                  "min": null,
                  "name": "prompt",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Describe what you don't want included in the image.",
                    "zh_Hans": "描述您不希望包含在图片中的内容。"
                  },
                  "label": {
                    "en_US": "negative prompt",
                    "zh_Hans": "负面提示词"
                  },
                  "llm_description": "Describe what you don't want included in the image.",
                  "max": null,
                  "min": null,
                  "name": "negative_prompt",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "sd_3",
                  "form": "form",
                  "human_description": {
                    "en_US": "Description in English",
                    "zh_Hans": "描述用中文"
                  },
                  "label": {
                    "en_US": "Choose Image Model",
                    "zh_Hans": "选择生成图片的模型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": [
                    {
                      "label": {
                        "en_US": "Stable Diffusion 3"
                      },
                      "value": "sd_3"
                    },
                    {
                      "label": {
                        "en_US": "Stable Diffusion XL"
                      },
                      "value": "sd_xl"
                    },
                    {
                      "label": {
                        "en_US": "Stable Diffusion 3.5 Large"
                      },
                      "value": "sd_3.5_large"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "1024x1024",
                  "form": "form",
                  "human_description": {
                    "en_US": "Choose the dimensions of the generated image",
                    "zh_Hans": "选择生成图片的尺寸"
                  },
                  "label": {
                    "en_US": "Choose Image Size",
                    "zh_Hans": "选择生成图片的大小"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "image_size",
                  "options": [
                    {
                      "label": {
                        "en_US": "1024x1024"
                      },
                      "value": "1024x1024"
                    },
                    {
                      "label": {
                        "en_US": "1024x2048"
                      },
                      "value": "1024x2048"
                    },
                    {
                      "label": {
                        "en_US": "1152x2048"
                      },
                      "value": "1152x2048"
                    },
                    {
                      "label": {
                        "en_US": "1536x1024"
                      },
                      "value": "1536x1024"
                    },
                    {
                      "label": {
                        "en_US": "1536x2048"
                      },
                      "value": "1536x2048"
                    },
                    {
                      "label": {
                        "en_US": "2048x1152"
                      },
                      "value": "2048x1152"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 1,
                  "form": "form",
                  "human_description": {
                    "en_US": "Number of images to generate in a single batch",
                    "zh_Hans": "单次生成图片的数量"
                  },
                  "label": {
                    "en_US": "Number Images",
                    "zh_Hans": "生成图片的数量"
                  },
                  "llm_description": "",
                  "max": 4,
                  "min": 1,
                  "name": "batch_size",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 7.5,
                  "form": "form",
                  "human_description": {
                    "en_US": "Classifier Free Guidance. How close you want the model to stick to your prompt when looking for a related image to show you.",
                    "zh_Hans": "无分类器引导。您希望模型在寻找相关图片向您展示时，与您的提示保持多紧密的关联度。"
                  },
                  "label": {
                    "en_US": "Guidance Scale",
                    "zh_Hans": "与提示词紧密性"
                  },
                  "llm_description": "",
                  "max": 100,
                  "min": 0,
                  "name": "guidance_scale",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 20,
                  "form": "form",
                  "human_description": {
                    "en_US": "The number of inference steps to perform. More steps produce higher quality but take longer.",
                    "zh_Hans": "执行的推理步骤数量。更多的步骤可以产生更高质量的结果，但需要更长的时间。"
                  },
                  "label": {
                    "en_US": "Num Inference Steps",
                    "zh_Hans": "生成图片的步数"
                  },
                  "llm_description": "",
                  "max": 100,
                  "min": 1,
                  "name": "num_inference_steps",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The same seed and prompt can produce similar images.",
                    "zh_Hans": "相同的种子和提示可以产生相似的图像。"
                  },
                  "label": {
                    "en_US": "Seed",
                    "zh_Hans": "种子"
                  },
                  "llm_description": "",
                  "max": 9999999999,
                  "min": 0,
                  "name": "seed",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Generate image via SiliconFlow's deepseek-ai/Janus-Pro-7B model."
                },
                "llm": "This tool is used to generate image from prompt via SiliconFlow's Janus-Pro-7B model."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "SiliconFlow, Inc.",
                "label": {
                  "en_US": "Janus-Pro-7B"
                },
                "name": "Janus-Pro-7B"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The text prompt used to generate the image.",
                    "zh_Hans": "建议用英文的生成图片提示词以获得更好的生成效果。"
                  },
                  "label": {
                    "en_US": "prompt",
                    "zh_Hans": "提示词"
                  },
                  "llm_description": "this prompt text will be used to generate image.",
                  "max": null,
                  "min": null,
                  "name": "prompt",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "Janus-Pro-7B",
                  "form": "form",
                  "human_description": {
                    "en_US": "Choose the model version for image generation",
                    "zh_Hans": "选择用于图像生成的模型版本"
                  },
                  "label": {
                    "en_US": "Choose Image Model",
                    "zh_Hans": "选择生成图片的模型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": [
                    {
                      "label": {
                        "en_US": "Janus-Pro-7B"
                      },
                      "value": "Janus-Pro-7B"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The same seed and prompt can produce similar images.",
                    "zh_Hans": "相同的种子和提示可以产生相似的图像。"
                  },
                  "label": {
                    "en_US": "Seed",
                    "zh_Hans": "种子"
                  },
                  "llm_description": "",
                  "max": 9999999999,
                  "min": 0,
                  "name": "seed",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-27T12:33:47Z",
        "version_updated_at": "2025-02-27T12:33:47Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "A blazing fast inference solution for text embeddings models.",
          "zh_Hans": "用于文本嵌入模型的超快速推理解决方案。"
        },
        "category": "model",
        "created_at": "2025-01-02T05:32:40Z",
        "endpoint": {},
        "icon": "langgenius/packages/huggingface_tei/_assets/icon_s_en.svg",
        "index_id": "langgenius___huggingface_tei",
        "install_count": 7302,
        "introduction": "",
        "label": {
          "en_US": "Text Embedding Inference"
        },
        "latest_package_identifier": "langgenius/huggingface_tei:0.0.3@cbf6225ca0f97b13975f09c8f6a1707dda136fa033300b3a41d7bd9cc8f700d5",
        "latest_version": "0.0.3",
        "model": {
          "background": "#FFF8DC",
          "configurate_methods": [
            "customizable-model"
          ],
          "description": {
            "en_US": "A blazing fast inference solution for text embeddings models.",
            "zh_Hans": "用于文本嵌入模型的超快速推理解决方案。"
          },
          "help": {
            "title": {
              "en_US": "How to deploy Text Embedding Inference",
              "zh_Hans": "如何部署 Text Embedding Inference"
            },
            "url": {
              "en_US": "https://github.com/huggingface/text-embeddings-inference"
            }
          },
          "icon_large": null,
          "icon_small": null,
          "label": {
            "en_US": "Text Embedding Inference"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "Server url",
                  "zh_Hans": "服务器URL"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter the url of your Text Embedding Inference, e.g. http://192.168.1.100:8080",
                  "zh_Hans": "在此输入Text Embedding Inference的服务器地址，如 http://192.168.1.100:8080"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "server_url"
              },
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": false,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              }
            ],
            "model": {
              "label": {
                "en_US": "Model Name",
                "zh_Hans": "模型名称"
              },
              "placeholder": {
                "en_US": "Enter your model name",
                "zh_Hans": "输入模型名称"
              }
            }
          },
          "models": [],
          "position": {},
          "provider": "huggingface_tei",
          "provider_credential_schema": null,
          "supported_model_types": [
            "text-embedding",
            "rerank"
          ]
        },
        "name": "huggingface_tei",
        "org": "langgenius",
        "plugin_id": "langgenius/huggingface_tei",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/huggingface_tei.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": false,
              "llm": false,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": false
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-08T02:05:56Z",
        "version_updated_at": "2025-04-08T02:05:56Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "DingTalk group robot",
          "pt_BR": "DingTalk group robot",
          "zh_Hans": "钉钉群机器人"
        },
        "category": "tool",
        "created_at": "2024-12-04T04:53:06Z",
        "endpoint": {},
        "icon": "langgenius/packages/dingtalk/_assets/icon.svg",
        "index_id": "langgenius___dingtalk",
        "install_count": 7069,
        "introduction": "# DingTalk Tool\n\n## Overview\n\nDingTalk is a communication and collaboration platform designed for workplace environments. It offers features like instant messaging and group chats.\n\n## Configuration\n\n### 1. Apply for DingTalk Account\n\nGet Access Token and ApiSecret from [DingTalk developer platform](https://open-dev.dingtalk.com/?spm=ding_open_doc.document.0.0.66d876e0V8Gchn), for more getting tutorial:\n\n- **Access Token**: \nhttps://open.dingtalk.com/document/orgapp/obtain-user-token\n\n- **ApiSecret**: \nhttps://open.dingtalk.com/document/connector/untitled-document-2\n\n### 2. Get DingTalk tools from Plugin Marketplace\nThe DingTalk tools could be found at the Plugin Marketplace, please install it.\n\n![](./_assets/dingtalk_1.png)\n\n### 3. You can use the DingTalk tool in the following application types.\n\n![](./_assets/dingtalk_2.PNG)\n\n#### Chatflow / Workflow applications\n\nBoth Chatflow and Workflow applications support the DingTalk tool node, and fill up the node with all the information from **Step 1**.",
        "label": {
          "en_US": "DingTalk",
          "pt_BR": "DingTalk",
          "zh_Hans": "钉钉"
        },
        "latest_package_identifier": "langgenius/dingtalk:0.0.4@fe34a564a52c3a295e60ed97280ef47abd459d96310239cf9df5f04a5b1681b3",
        "latest_version": "0.0.4",
        "model": {},
        "name": "dingtalk",
        "org": "langgenius",
        "plugin_id": "langgenius/dingtalk",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/dingtalk.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "social"
          }
        ],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "Bowen Liang & LiuHao",
            "description": {
              "en_US": "DingTalk group robot",
              "pt_BR": "DingTalk group robot",
              "zh_Hans": "钉钉群机器人"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "DingTalk",
              "pt_BR": "DingTalk",
              "zh_Hans": "钉钉"
            },
            "name": "dingtalk",
            "tags": [
              "social",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Sending a group message on DingTalk via the webhook of group bot",
                  "pt_BR": "Sending a group message on DingTalk via the webhook of group bot",
                  "zh_Hans": "通过钉钉的群机器人webhook发送群消息"
                },
                "llm": "A tool for sending messages to a chat group on DingTalk(钉钉) ."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Bowen Liang",
                "label": {
                  "en_US": "Send Group Message",
                  "pt_BR": "Send Group Message",
                  "zh_Hans": "发送群消息"
                },
                "name": "dingtalk_group_bot"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "access_token in the group robot webhook",
                    "pt_BR": "access_token in the group robot webhook",
                    "zh_Hans": "群自定义机器人webhook中access_token字段的值"
                  },
                  "label": {
                    "en_US": "access token",
                    "pt_BR": "access token",
                    "zh_Hans": "access token"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "access_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "secret key for signing",
                    "pt_BR": "secret key for signing",
                    "zh_Hans": "加签秘钥"
                  },
                  "label": {
                    "en_US": "secret key for signing",
                    "pt_BR": "secret key for signing",
                    "zh_Hans": "加签秘钥"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "sign_secret",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Content to sent to the group.",
                    "pt_BR": "Content to sent to the group.",
                    "zh_Hans": "群消息文本"
                  },
                  "label": {
                    "en_US": "content",
                    "pt_BR": "content",
                    "zh_Hans": "消息内容"
                  },
                  "llm_description": "Content of the message",
                  "max": null,
                  "min": null,
                  "name": "content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "text",
                  "form": "form",
                  "human_description": {
                    "en_US": "dingtalk Group bot message type",
                    "pt_BR": "dingtalk Group bot message type",
                    "zh_Hans": "群机器人webhook的消息类型"
                  },
                  "label": {
                    "en_US": "dingtalk Group bot message type",
                    "pt_BR": "dingtalk Group bot message type",
                    "zh_Hans": "群机器人webhook的消息类型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "message_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "Text",
                        "pt_BR": "Text",
                        "zh_Hans": "文本"
                      },
                      "value": "text"
                    },
                    {
                      "label": {
                        "en_US": "Markdown",
                        "pt_BR": "Markdown",
                        "zh_Hans": "Markdown"
                      },
                      "value": "markdown"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-25T08:20:38Z",
        "version_updated_at": "2025-03-25T08:20:38Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "WenXin",
          "zh_Hans": "文心一言"
        },
        "category": "model",
        "created_at": "2024-12-05T07:21:43Z",
        "endpoint": {},
        "icon": "langgenius/packages/wenxin/_assets/icon_s_en.png",
        "index_id": "langgenius___wenxin",
        "install_count": 7064,
        "introduction": "",
        "label": {
          "en_US": "WenXin",
          "zh_Hans": "文心一言"
        },
        "latest_package_identifier": "langgenius/wenxin:0.0.3@01f14a7f686c8c0ac1afd9cf57e645983e1b2a69e8cfbb1329493a2d997307e1",
        "latest_version": "0.0.3",
        "model": {
          "background": "#E8F5FE",
          "configurate_methods": [
            "predefined-model"
          ],
          "description": {
            "en_US": "WenXin",
            "zh_Hans": "文心一言"
          },
          "help": {
            "title": {
              "en_US": "Get your API Key from WenXin",
              "zh_Hans": "从文心一言获取您的 API Key"
            },
            "url": {
              "en_US": "https://cloud.baidu.com/wenxin.html"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.png",
            "zh_Hans": "icon_l_zh.png"
          },
          "icon_small": {
            "en_US": "icon_s_en.png",
            "zh_Hans": "icon_s_en.png"
          },
          "label": {
            "en_US": "WenXin",
            "zh_Hans": "文心一言"
          },
          "model_credential_schema": null,
          "models": [
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Ernie-3.5-128K"
              },
              "model": "ernie-3.5-128k",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0.1,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 4096,
                  "min": 2,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Disable the model to perform external search.",
                    "zh_Hans": "禁用模型自行进行外部搜索。"
                  },
                  "label": {
                    "en_US": "Disable Search",
                    "zh_Hans": "禁用搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "disable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Ernie-3.5-4k-0205"
              },
              "model": "ernie-3.5-4k-0205",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0.1,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 2,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Disable the model to perform external search.",
                    "zh_Hans": "禁用模型自行进行外部搜索。"
                  },
                  "label": {
                    "en_US": "Disable Search",
                    "zh_Hans": "禁用搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "disable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Ernie-3.5-8K-0205"
              },
              "model": "ernie-3.5-8k-0205",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0.1,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 2,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Disable the model to perform external search.",
                    "zh_Hans": "禁用模型自行进行外部搜索。"
                  },
                  "label": {
                    "en_US": "Disable Search",
                    "zh_Hans": "禁用搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "disable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Ernie-3.5-8K-1222"
              },
              "model": "ernie-3.5-8k-1222",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0.1,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 2,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Disable the model to perform external search.",
                    "zh_Hans": "禁用模型自行进行外部搜索。"
                  },
                  "label": {
                    "en_US": "Disable Search",
                    "zh_Hans": "禁用搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "disable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Ernie-3.5-8K"
              },
              "model": "ernie-3.5-8k",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0.1,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 2,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": 1,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Disable the model to perform external search.",
                    "zh_Hans": "禁用模型自行进行外部搜索。"
                  },
                  "label": {
                    "en_US": "Disable Search",
                    "zh_Hans": "禁用搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "disable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Ernie-4.0-8K-Latest"
              },
              "model": "ernie-4.0-8k-latest",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0.1,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 2,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": 1,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Disable the model to perform external search.",
                    "zh_Hans": "禁用模型自行进行外部搜索。"
                  },
                  "label": {
                    "en_US": "Disable Search",
                    "zh_Hans": "禁用搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "disable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Ernie-4.0-8K"
              },
              "model": "ernie-4.0-8k",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0.1,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 2,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": 1,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Disable the model to perform external search.",
                    "zh_Hans": "禁用模型自行进行外部搜索。"
                  },
                  "label": {
                    "en_US": "Disable Search",
                    "zh_Hans": "禁用搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "disable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Ernie-4.0-turbo-128K"
              },
              "model": "ernie-4.0-turbo-128k",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0.1,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 4096,
                  "min": 2,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": 1,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Disable the model to perform external search.",
                    "zh_Hans": "禁用模型自行进行外部搜索。"
                  },
                  "label": {
                    "en_US": "Disable Search",
                    "zh_Hans": "禁用搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "disable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Ernie-4.0-turbo-8k-preview"
              },
              "model": "ernie-4.0-turbo-8k-preview",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0.1,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 2,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": 1,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Disable the model to perform external search.",
                    "zh_Hans": "禁用模型自行进行外部搜索。"
                  },
                  "label": {
                    "en_US": "Disable Search",
                    "zh_Hans": "禁用搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "disable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Ernie-4.0-turbo-8K"
              },
              "model": "ernie-4.0-turbo-8k",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0.1,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 2,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": 1,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Disable the model to perform external search.",
                    "zh_Hans": "禁用模型自行进行外部搜索。"
                  },
                  "label": {
                    "en_US": "Disable Search",
                    "zh_Hans": "禁用搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "disable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Ernie Bot 4"
              },
              "model": "ernie-bot-4",
              "model_properties": {
                "context_size": 4800,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0.1,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 256,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 4800,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Disable the model to perform external search.",
                    "zh_Hans": "禁用模型自行进行外部搜索。"
                  },
                  "label": {
                    "en_US": "Disable Search",
                    "zh_Hans": "禁用搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "disable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Ernie Bot 8k"
              },
              "model": "ernie-bot-8k",
              "model_properties": {
                "context_size": 8000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0.1,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 8000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Disable the model to perform external search.",
                    "zh_Hans": "禁用模型自行进行外部搜索。"
                  },
                  "label": {
                    "en_US": "Disable Search",
                    "zh_Hans": "禁用搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "disable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Ernie Bot Turbo"
              },
              "model": "ernie-bot-turbo",
              "model_properties": {
                "context_size": 11200,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0.1,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 11200,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Ernie Bot"
              },
              "model": "ernie-bot",
              "model_properties": {
                "context_size": 4800,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0.1,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 256,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 4800,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Disable the model to perform external search.",
                    "zh_Hans": "禁用模型自行进行外部搜索。"
                  },
                  "label": {
                    "en_US": "Disable Search",
                    "zh_Hans": "禁用搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "disable_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "ERNIE-Character-8K-0321"
              },
              "model": "ernie-character-8k-0321",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0.1,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 1024,
                  "min": 2,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": 1,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "ERNIE-Character-8K"
              },
              "model": "ernie-character-8k-0321",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0.1,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 1024,
                  "min": 2,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": 1,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "ERNIE-Lite-8K-0308"
              },
              "model": "ernie-lite-8k-0308",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0.1,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 2,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": 1,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "ERNIE-Lite-8K-0922"
              },
              "model": "ernie-lite-8k-0922",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0.1,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 1024,
                  "min": 2,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": 1,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Ernie-Lite-Pro-128K"
              },
              "model": "ernie-lite-pro-128k",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0.1,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 64,
                  "help": {
                    "en_US": "Specifies the lower limit on the length of generated results.",
                    "zh_Hans": "指定模型最小输出token数"
                  },
                  "label": {
                    "en_US": "Min Output Tokens",
                    "zh_Hans": "最小输出Token数"
                  },
                  "max": 2048,
                  "min": 2,
                  "name": "min_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定模型最大输出token数"
                  },
                  "label": {
                    "en_US": "Max Output Tokens",
                    "zh_Hans": "最大输出Token数"
                  },
                  "max": 2048,
                  "min": 2,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "ERNIE-Speed-128K"
              },
              "model": "ernie-speed-128k",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0.1,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 4096,
                  "min": 2,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": 1,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "ERNIE-Speed-8K"
              },
              "model": "ernie-speed-8k",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0.1,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 2,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": 1,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "ERNIE-Speed-AppBuilder"
              },
              "model": "ernie-speed-appbuilder",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0.1,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": 1,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "yi_34b_chat"
              },
              "model": "yi_34b_chat",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0.1,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 4096,
                  "min": 2,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": 1,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "bce-reranker-base_v1"
              },
              "model": "bce-reranker-base_v1",
              "model_properties": {
                "context_size": 4096
              },
              "model_type": "rerank",
              "parameter_rules": [],
              "pricing": {
                "currency": "RMB",
                "input": "0.0005",
                "output": null,
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "bge-large-en"
              },
              "model": "bge-large-en",
              "model_properties": {
                "context_size": 512,
                "max_chunks": 16
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "RMB",
                "input": "0.0005",
                "output": null,
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "bge-large-zh"
              },
              "model": "bge-large-zh",
              "model_properties": {
                "context_size": 512,
                "max_chunks": 16
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "RMB",
                "input": "0.0005",
                "output": null,
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "embedding-v1"
              },
              "model": "embedding-v1",
              "model_properties": {
                "context_size": 384,
                "max_chunks": 16
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "RMB",
                "input": "0.0005",
                "output": null,
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "tao-8k"
              },
              "model": "tao-8k",
              "model_properties": {
                "context_size": 8192,
                "max_chunks": 1
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "RMB",
                "input": "0.0005",
                "output": null,
                "unit": "0.001"
              }
            }
          ],
          "position": {},
          "provider": "wenxin",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Secret Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Secret Key",
                  "zh_Hans": "在此输入您的 Secret Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "secret_key"
              }
            ]
          },
          "supported_model_types": [
            "llm",
            "text-embedding",
            "rerank"
          ]
        },
        "name": "wenxin",
        "org": "langgenius",
        "plugin_id": "langgenius/wenxin",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/wenxin.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {}
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-02-28T10:41:51Z",
        "version_updated_at": "2025-02-28T10:41:51Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "The fastest way to get actionable insights from your database just by asking questions.",
          "zh_Hans": "一个基于大模型和RAG的Text2SQL工具。"
        },
        "category": "tool",
        "created_at": "2024-11-29T10:28:24Z",
        "endpoint": {},
        "icon": "langgenius/packages/vanna/_assets/icon.png",
        "index_id": "langgenius___vanna",
        "install_count": 6496,
        "introduction": "# Overview\nVanna.ai is an innovative AI-driven platform designed to simplify the interaction between users and complex SQL databases. \n\n# Configure\n## Get API Key\n1. Create an account and login to Vanna.ai.\n2. Copy API key from API Keys.\n\n## Configure Vanna.AI tool\n1. Install Vanna.AI from Marketplace. \n![](./_assets/vanna_install.png)\n2. Add Vanna.AI node to your workflow.\n3. Fill in the Vanna.AI API key.\n4. Fill in the database configurations.\n![](./_assets/vanna_configure.png)",
        "label": {
          "en_US": "Vanna.AI",
          "zh_Hans": "Vanna.AI"
        },
        "latest_package_identifier": "langgenius/vanna:0.0.2@fc0b06ce0b108aaa029280050f5127ad82d770c2c2ea438cf39e4333c0bac910",
        "latest_version": "0.0.2",
        "model": {},
        "name": "vanna",
        "org": "langgenius",
        "plugin_id": "langgenius/vanna",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/vanna.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "utilities"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "API key",
                "zh_Hans": "API key"
              },
              "name": "api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your API key",
                "pt_BR": "Please input your API key",
                "zh_Hans": "请输入你的 API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://vanna.ai/account/profile"
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "Vanna.AI Endpoint Base URL"
              },
              "name": "base_url",
              "options": null,
              "placeholder": {
                "en_US": "https://ask.vanna.ai/rpc"
              },
              "required": false,
              "scope": null,
              "type": "text-input",
              "url": null
            }
          ],
          "identity": {
            "author": "qctc",
            "description": {
              "en_US": "The fastest way to get actionable insights from your database just by asking questions.",
              "zh_Hans": "一个基于大模型和RAG的Text2SQL工具。"
            },
            "icon": "icon.png",
            "label": {
              "en_US": "Vanna.AI",
              "zh_Hans": "Vanna.AI"
            },
            "name": "vanna",
            "tags": [
              "utilities",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "The fastest way to get actionable insights from your database just by asking questions.",
                  "zh_Hans": "一个基于大模型和RAG的Text2SQL工具。"
                },
                "llm": "A tool for converting text to SQL."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "QCTC",
                "label": {
                  "en_US": "Vanna.AI",
                  "zh_Hans": "Vanna.AI"
                },
                "name": "vanna"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "used for generating SQL",
                    "zh_Hans": "用于生成SQL"
                  },
                  "label": {
                    "en_US": "Prompt",
                    "pt_BR": "Prompt",
                    "zh_Hans": "提示词"
                  },
                  "llm_description": "key words for generating SQL",
                  "max": null,
                  "min": null,
                  "name": "prompt",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "RAG Model for your database DDL",
                    "zh_Hans": "存储数据库训练数据的RAG模型"
                  },
                  "label": {
                    "en_US": "RAG Model",
                    "zh_Hans": "RAG模型"
                  },
                  "llm_description": "RAG Model for generating SQL",
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "SQLite",
                  "form": "form",
                  "human_description": {
                    "en_US": "Database type.",
                    "zh_Hans": "选择要链接的数据库类型。"
                  },
                  "label": {
                    "en_US": "DB Type",
                    "zh_Hans": "数据库类型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "db_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "SQLite",
                        "zh_Hans": "SQLite"
                      },
                      "value": "SQLite"
                    },
                    {
                      "label": {
                        "en_US": "Postgres",
                        "zh_Hans": "Postgres"
                      },
                      "value": "Postgres"
                    },
                    {
                      "label": {
                        "en_US": "DuckDB",
                        "zh_Hans": "DuckDB"
                      },
                      "value": "DuckDB"
                    },
                    {
                      "label": {
                        "en_US": "Microsoft SQL Server",
                        "zh_Hans": "微软 SQL Server"
                      },
                      "value": "SQLServer"
                    },
                    {
                      "label": {
                        "en_US": "MySQL",
                        "zh_Hans": "MySQL"
                      },
                      "value": "MySQL"
                    },
                    {
                      "label": {
                        "en_US": "Oracle",
                        "zh_Hans": "Oracle"
                      },
                      "value": "Oracle"
                    },
                    {
                      "label": {
                        "en_US": "Hive",
                        "zh_Hans": "Hive"
                      },
                      "value": "Hive"
                    },
                    {
                      "label": {
                        "en_US": "ClickHouse",
                        "zh_Hans": "ClickHouse"
                      },
                      "value": "ClickHouse"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Please input depending on DB type, visit https://vanna.ai/docs/ for more specification",
                    "zh_Hans": "请根据数据库类型，填入对应值，详情参考https://vanna.ai/docs/"
                  },
                  "label": {
                    "en_US": "URL/Host/DSN",
                    "zh_Hans": "URL/Host/DSN"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "url",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Database name",
                    "zh_Hans": "数据库名"
                  },
                  "label": {
                    "en_US": "DB name",
                    "zh_Hans": "数据库名"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "db_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Username",
                    "zh_Hans": "用户名"
                  },
                  "label": {
                    "en_US": "Username",
                    "zh_Hans": "用户名"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "username",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Password",
                    "zh_Hans": "密码"
                  },
                  "label": {
                    "en_US": "Password",
                    "zh_Hans": "密码"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "password",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Port",
                    "zh_Hans": "端口"
                  },
                  "label": {
                    "en_US": "Port",
                    "zh_Hans": "端口"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "port",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "DDL statements for training data",
                    "zh_Hans": "用于训练RAG Model的建表语句"
                  },
                  "label": {
                    "en_US": "Training DDL",
                    "zh_Hans": "训练DDL"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "ddl",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Question-SQL Pairs",
                    "zh_Hans": "Question-SQL中的问题"
                  },
                  "label": {
                    "en_US": "Training Question",
                    "zh_Hans": "训练问题"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "question",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "SQL queries to your training data",
                    "zh_Hans": "用于训练RAG Model的SQL语句"
                  },
                  "label": {
                    "en_US": "Training SQL",
                    "zh_Hans": "训练SQL"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "sql",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sometimes you may want to add documentation about your business terminology or definitions",
                    "zh_Hans": "添加更多关于数据库的业务说明"
                  },
                  "label": {
                    "en_US": "Training Memos",
                    "zh_Hans": "训练说明"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "memos",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "You only need to train once. Do not train again unless you want to add more training data",
                    "zh_Hans": "训练数据无更新时，训练一次即可"
                  },
                  "label": {
                    "en_US": "Training Data",
                    "zh_Hans": "训练数据"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "enable_training",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Remove all training data in the current RAG Model",
                    "zh_Hans": "删除当前RAG Model中的所有训练数据"
                  },
                  "label": {
                    "en_US": "Reset Training Data",
                    "zh_Hans": "重置训练数据"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "reset_training_data",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "If enabled, it will attempt to train on the metadata of that database",
                    "zh_Hans": "是否自动从数据库获取元数据来训练"
                  },
                  "label": {
                    "en_US": "Training Metadata",
                    "zh_Hans": "训练元数据"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "training_metadata",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to allow the LLM to see the data",
                    "zh_Hans": "是否允许LLM查看数据"
                  },
                  "label": {
                    "en_US": "Whether to allow the LLM to see the data",
                    "zh_Hans": "是否允许LLM查看数据"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "allow_llm_to_see_data",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:11:32Z",
        "version_updated_at": "2025-02-17T07:11:32Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "make dify's workflow as a MCP server",
          "ja_JP": "make dify's workflow as a MCP server",
          "pt_BR": "make dify's workflow as a MCP server",
          "zh_Hans": "make dify's workflow as a MCP server"
        },
        "category": "extension",
        "created_at": "2025-03-19T18:51:15Z",
        "endpoint": {
          "endpoints": [
            {
              "hidden": false,
              "method": "GET",
              "path": "/sse"
            },
            {
              "hidden": false,
              "method": "POST",
              "path": "/messages/"
            },
            {
              "hidden": false,
              "method": "GET",
              "path": "/mcp"
            },
            {
              "hidden": false,
              "method": "POST",
              "path": "/mcp"
            }
          ],
          "settings": [
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "App"
              },
              "name": "app",
              "options": null,
              "placeholder": {
                "en_US": "Please select an app",
                "zh_Hans": "请选择一个应用"
              },
              "required": true,
              "scope": "all",
              "type": "app-selector",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "App Type"
              },
              "name": "app-type",
              "options": [
                {
                  "label": {
                    "en_US": "Chat"
                  },
                  "value": "chat"
                },
                {
                  "label": {
                    "en_US": "Workflow"
                  },
                  "value": "workflow"
                }
              ],
              "placeholder": null,
              "required": true,
              "scope": null,
              "type": "select",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "App Input Schema"
              },
              "name": "app-input-schema",
              "options": null,
              "placeholder": {
                "en_US": "the json format of your app input schema",
                "zh_Hans": "请输入应用所需输入的 json 格式"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            }
          ]
        },
        "icon": "hjlarry/packages/mcp-server/_assets/icon.svg",
        "index_id": "hjlarry___mcp-server",
        "install_count": 6298,
        "introduction": "# MCP Server\n\n**Author:** hjlarry  \n**Version:** 0.0.2  \n**Type:** extension   \n**Repo:** [https://github.com/hjlarry/dify-plugin-mcp_server](https://github.com/hjlarry/dify-plugin-mcp_server)  \n**Feature Request:** [issues](https://github.com/hjlarry/dify-plugin-mcp_server/issues)  \n\n\nA Dify endpoint plugin that change a dify app to a mcp server.\n\n**To keep your data secure, use this plugin exclusively within your private network.**\n\n## Get Started\n\n### 1. create a simple workflow app in dify.\n![1](./_assets/1.png)\n\n### 2. add a endpoint and select this app.\n![2](./_assets/2.png)\n\nThe app's input schema must define its input parameters. For a chat dify app, ensure to include a `query` field in the input schema, formatted as follows:\n```json\n{\n    \"name\": \"get_weather\",\n    \"description\": \"Get weather status for a place.\",\n    \"inputSchema\": {\n        \"properties\": {\n            \"place\": {\"title\": \"Place\", \"type\": \"string\"}\n        },\n        \"required\": [\"place\"],\n        \"title\": \"get_weatherArguments\",\n        \"type\": \"object\"\n    }\n}\n```\n\n### 3. copy the endpoint url to your mcp client, like `Cherry Studio`\n\n#### Option 1: Use the newest Streamable HTTP protocol (Recommended)\n![6](./_assets/6.png)\n![7](./_assets/7.png)\n\n#### Option 2: Use the legacy SSE protocol\n![3](./_assets/3.png)\n![4](./_assets/4.png)\n\n### 4. enjoy it!\n![5](./_assets/5.png)\n\n\n## Changelog\n\n### 0.0.2\n- Add a new Streamable HTTP protocol.\n- Update dify-plugin-sdk version.",
        "label": {
          "en_US": "mcp-server",
          "ja_JP": "mcp-server",
          "pt_BR": "mcp-server",
          "zh_Hans": "mcp-server"
        },
        "latest_package_identifier": "hjlarry/mcp-server:0.0.2@bcce460c6b12539bdc5ed39238e649c3124d3a6086222bbbe0a8807bed0e2591",
        "latest_version": "0.0.2",
        "model": {},
        "name": "mcp-server",
        "org": "hjlarry",
        "plugin_id": "hjlarry/mcp-server",
        "plugins": {
          "agent_strategies": null,
          "endpoints": [
            "group/mcp-server.yaml"
          ],
          "models": null,
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-18T19:39:55Z",
        "version_updated_at": "2025-04-18T19:39:55Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "vllm provider for guided support https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html#id5",
          "ja_JP": "vllm provider for guided support https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html#id5",
          "pt_BR": "vllm provider for guided support https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html#id5",
          "zh_Hans": "vllm provider for guided support https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html#id5"
        },
        "category": "model",
        "created_at": "2025-03-19T14:22:54Z",
        "endpoint": {},
        "icon": "yangyaofei/packages/vllm/_assets/vLLM-Logo.svg",
        "index_id": "yangyaofei___vllm",
        "install_count": 5982,
        "introduction": "# vllm-openai dify provider plugin to support guided generate\n\n## **NOTE!!!**\n**This plugin is a extension for official OpenAI-API-compatible,** \n**provide features for [extra parameters in vLLM's OpenAI-Compatible Server](https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html#extra-parameters).**\n**Only extra parameters featured model will be implemented here, Please use official OpenAI-API-compatible you don't have such needs.**\n\n**本插件是在官方 OpenAI-API-compatible 基础上构建, 用于提供[vLLM's OpenAI-Compatible Server 中的 extra parameters](https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html#extra-parameters)**\n**的调用(现主要集中在 CFG 即 Guided Generate 上). 若没有使用上述 extra parameters 中的相关的特性, 请使用官方 OpenAI-API-compatible 插件.**\n\n## Repo\nhttps://github.com/yangyaofei/dify-vllm-provider\n\n## Description\n\nThe vllm [openAI compatible server](https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html) \ncan make CFG(Classifier-Free Guidance) with [outlines](https://github.com/dottxt-ai/outlines) or \n[lm-format-enforcer](https://github.com/noamgat/lm-format-enforcer) with `Extra Parameters` like `guided_json`, `guided_regex`.\nThe openai compatible provider in Dify can not do this, but like gpt-4o can do same thing wit_assets/add_model.pngh json flag.\n\nThis plugin provide a vllm-openai provider upon Dify's openai compatible provider with `guided_json`, `guided_regex`, `guided_grammar`.\n\n### Add model same as openai compatible with vLLM-openai backend\n\n![`add model`](./_assets/add_model.png)\n\n### Config model guided with `json schema`, `regex`, `grammar`\n\n![`use guided`](./_assets/use_guided.png)\n\n\n## Dynamic Request guided\n\nThe guided param may various in same workflow, but Dify doesn't give a extra param in LLM to pass it.\n\nThis comes little hacky, when the prompt has 2nd part and it's assistant, this provider will use the assistant part as guided param.\nIf it can be parsed as json.\n\nThe structure of param can be found in `GuidedParam` class.\n",
        "label": {
          "en_US": "vllm",
          "ja_JP": "vllm",
          "pt_BR": "vllm",
          "zh_Hans": "vllm"
        },
        "latest_package_identifier": "yangyaofei/vllm:0.1.4@b9d34bbf01875405571bb829f9e275faeaf832b869a401f9757be48acfb509e8",
        "latest_version": "0.1.4",
        "model": {
          "background": "#E5E7EB",
          "configurate_methods": [
            "customizable-model"
          ],
          "description": {
            "en_US": "Models provided by vllm with guided inference supported.",
            "zh_Hans": "Vllm openai guided 支持"
          },
          "help": null,
          "icon_large": {
            "en_US": "vLLM-Logo.svg"
          },
          "icon_small": {
            "en_US": "vLLM-Logo.svg"
          },
          "label": {
            "en_US": "Vllm"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": false,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              },
              {
                "default": null,
                "label": {
                  "en_US": "API endpoint URL",
                  "zh_Hans": "API endpoint URL"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Base URL, e.g. https://api.openai.com/v1",
                  "zh_Hans": "Base URL, e.g. https://api.openai.com/v1"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "endpoint_url"
              },
              {
                "default": null,
                "label": {
                  "en_US": "model name for API endpoint",
                  "zh_Hans": "API endpoint中的模型名称"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "endpoint model name, e.g. chatgpt4.0",
                  "zh_Hans": "endpoint model name, e.g. chatgpt4.0"
                },
                "required": false,
                "show_on": [],
                "type": "text-input",
                "variable": "endpoint_model_name"
              },
              {
                "default": "chat",
                "label": {
                  "en_US": "Completion mode"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Completion",
                      "zh_Hans": "补全"
                    },
                    "show_on": [],
                    "value": "completion"
                  },
                  {
                    "label": {
                      "en_US": "Chat",
                      "zh_Hans": "对话"
                    },
                    "show_on": [],
                    "value": "chat"
                  }
                ],
                "placeholder": {
                  "en_US": "Select completion mode",
                  "zh_Hans": "选择对话类型"
                },
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "select",
                "variable": "mode"
              },
              {
                "default": "4096",
                "label": {
                  "en_US": "Model context size",
                  "zh_Hans": "模型上下文长度"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Model context size",
                  "zh_Hans": "在此输入您的模型上下文长度"
                },
                "required": true,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "text-input",
                "variable": "context_size"
              },
              {
                "default": "4096",
                "label": {
                  "en_US": "Upper bound for max tokens",
                  "zh_Hans": "最大 token 上限"
                },
                "max_length": 0,
                "options": [],
                "placeholder": null,
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "text-input",
                "variable": "max_tokens_to_sample"
              },
              {
                "default": "not_supported",
                "label": {
                  "en_US": "Agent Thought"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Support",
                      "zh_Hans": "支持"
                    },
                    "show_on": [],
                    "value": "supported"
                  },
                  {
                    "label": {
                      "en_US": "Not Support",
                      "zh_Hans": "不支持"
                    },
                    "show_on": [],
                    "value": "not_supported"
                  }
                ],
                "placeholder": null,
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "select",
                "variable": "agent_though_support"
              },
              {
                "default": "no_call",
                "label": {
                  "en_US": "Function calling"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Function Call",
                      "zh_Hans": "Function Call"
                    },
                    "show_on": [],
                    "value": "function_call"
                  },
                  {
                    "label": {
                      "en_US": "Tool Call",
                      "zh_Hans": "Tool Call"
                    },
                    "show_on": [],
                    "value": "tool_call"
                  },
                  {
                    "label": {
                      "en_US": "Not Support",
                      "zh_Hans": "不支持"
                    },
                    "show_on": [],
                    "value": "no_call"
                  }
                ],
                "placeholder": null,
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "select",
                "variable": "function_calling_type"
              },
              {
                "default": "not_supported",
                "label": {
                  "en_US": "Stream function calling"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Support",
                      "zh_Hans": "支持"
                    },
                    "show_on": [],
                    "value": "supported"
                  },
                  {
                    "label": {
                      "en_US": "Not Support",
                      "zh_Hans": "不支持"
                    },
                    "show_on": [],
                    "value": "not_supported"
                  }
                ],
                "placeholder": null,
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "select",
                "variable": "stream_function_calling"
              },
              {
                "default": "no_support",
                "label": {
                  "en_US": "Vision Support",
                  "zh_Hans": "Vision 支持"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Support",
                      "zh_Hans": "支持"
                    },
                    "show_on": [],
                    "value": "support"
                  },
                  {
                    "label": {
                      "en_US": "Not Support",
                      "zh_Hans": "不支持"
                    },
                    "show_on": [],
                    "value": "no_support"
                  }
                ],
                "placeholder": null,
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "select",
                "variable": "vision_support"
              },
              {
                "default": "\\n\\n",
                "label": {
                  "en_US": "Delimiter for streaming results",
                  "zh_Hans": "流模式返回结果的分隔符"
                },
                "max_length": 0,
                "options": [],
                "placeholder": null,
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "text-input",
                "variable": "stream_mode_delimiter"
              }
            ],
            "model": {
              "label": {
                "en_US": "Model Name",
                "zh_Hans": "模型名称"
              },
              "placeholder": {
                "en_US": "Enter your model name",
                "zh_Hans": "输入模型名称"
              }
            }
          },
          "models": [],
          "provider": "vllm",
          "provider_credential_schema": null,
          "supported_model_types": [
            "llm"
          ]
        },
        "name": "vllm",
        "org": "yangyaofei",
        "plugin_id": "yangyaofei/vllm",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/vllm.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-15T01:34:19Z",
        "version_updated_at": "2025-04-15T01:34:19Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Cohere",
          "zh_Hans": "Cohere"
        },
        "category": "model",
        "created_at": "2024-12-13T13:53:14Z",
        "endpoint": {},
        "icon": "langgenius/packages/cohere/_assets/icon_s_en.svg",
        "index_id": "langgenius___cohere",
        "install_count": 5800,
        "introduction": "## Overview\nCohere provides a robust suite of AI models—including LLMs, text embedding, and reranking—designed for enterprise applications. To begin building, simply configure the parameters and add models to this plugin.\n\n## Configure\nInstall the Cohere plugin, then configure it in Model Provider settings with the Model Type, Name, Completion mode, API Key, and API Base. Get your API key from [Cohere](https://dashboard.cohere.com/api-keys) and save your settings.\n\n<img src=\"./_assets/cohere-01.png\" width=\"400\" />\n",
        "label": {
          "en_US": "Cohere"
        },
        "latest_package_identifier": "langgenius/cohere:0.0.8@3dcfb5aa3cf8187b5aa1db48cc3e12326d2211d6e707fbde8031f23cc9eb6315",
        "latest_version": "0.0.8",
        "model": {
          "background": "#ECE9E3",
          "configurate_methods": [
            "predefined-model",
            "customizable-model"
          ],
          "description": {
            "en_US": "Cohere",
            "zh_Hans": "Cohere"
          },
          "help": {
            "title": {
              "en_US": "Get your API key from cohere",
              "zh_Hans": "从 cohere 获取 API Key"
            },
            "url": {
              "en_US": "https://dashboard.cohere.com/api-keys"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.svg"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "Cohere",
            "zh_Hans": "Cohere"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": "chat",
                "label": {
                  "en_US": "Completion mode"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Completion",
                      "zh_Hans": "补全"
                    },
                    "show_on": [],
                    "value": "completion"
                  },
                  {
                    "label": {
                      "en_US": "Chat",
                      "zh_Hans": "对话"
                    },
                    "show_on": [],
                    "value": "chat"
                  }
                ],
                "placeholder": {
                  "en_US": "Select completion mode",
                  "zh_Hans": "选择对话类型"
                },
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "select",
                "variable": "mode"
              },
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              },
              {
                "default": null,
                "label": {
                  "en_US": "API Base",
                  "zh_Hans": "API Base"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Base, e.g. https://api.cohere.ai/v1",
                  "zh_Hans": "在此输入您的 API Base，如 https://api.cohere.ai/v1"
                },
                "required": false,
                "show_on": [],
                "type": "text-input",
                "variable": "base_url"
              }
            ],
            "model": {
              "label": {
                "en_US": "Model Name",
                "zh_Hans": "模型名称"
              },
              "placeholder": {
                "en_US": "Enter your model name",
                "zh_Hans": "输入模型名称"
              }
            }
          },
          "models": [
            {
              "deprecated": false,
              "features": [
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "c4ai-aya-expanse-32b"
              },
              "model": "c4ai-aya-expanse-32b",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.75,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "p"
                  },
                  "max": 0.99,
                  "min": 0.01,
                  "name": "p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.5",
                "output": "1.5",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "c4ai-aya-expanse-8b"
              },
              "model": "c4ai-aya-expanse-8b",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.75,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "p"
                  },
                  "max": 0.99,
                  "min": 0.01,
                  "name": "p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.5",
                "output": "1.5",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "command-a-03-2025"
              },
              "model": "command-a-03-2025",
              "model_properties": {
                "context_size": 256000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.75,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "p"
                  },
                  "max": 0.99,
                  "min": 0.01,
                  "name": "p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "2.5",
                "output": "10",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "command-chat",
                "zh_Hans": "command-chat"
              },
              "model": "command-chat",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 5,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.75,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "p"
                  },
                  "max": 0.99,
                  "min": 0.01,
                  "name": "p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "When specified, the default Cohere preamble will be replaced with the provided one.",
                    "zh_Hans": "当指定时，将使用提供的前导文本替换默认的 Cohere 前导文本。"
                  },
                  "label": {
                    "en_US": "Preamble",
                    "zh_Hans": "前导文本"
                  },
                  "max": null,
                  "min": null,
                  "name": "preamble_override",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": "AUTO",
                  "help": {
                    "en_US": "Dictates how the prompt will be constructed. With prompt_truncation set to \"AUTO\", some elements from chat histories will be dropped in an attempt to construct a prompt that fits within the model's context length limit.",
                    "zh_Hans": "指定如何构造 Prompt。当 prompt_truncation 设置为 \"AUTO\" 时，将会丢弃一些来自聊天记录的元素，以尝试构造一个符合模型上下文长度限制的 Prompt。"
                  },
                  "label": {
                    "en_US": "Prompt Truncation",
                    "zh_Hans": "提示截断"
                  },
                  "max": null,
                  "min": null,
                  "name": "prompt_truncation",
                  "options": [
                    "AUTO",
                    "OFF"
                  ],
                  "precision": null,
                  "required": true,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "1",
                "output": "2",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "command-light-chat",
                "zh_Hans": "command-light-chat"
              },
              "model": "command-light-chat",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 5,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.75,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "p"
                  },
                  "max": 0.99,
                  "min": 0.01,
                  "name": "p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "When specified, the default Cohere preamble will be replaced with the provided one.",
                    "zh_Hans": "当指定时，将使用提供的前导文本替换默认的 Cohere 前导文本。"
                  },
                  "label": {
                    "en_US": "Preamble",
                    "zh_Hans": "前导文本"
                  },
                  "max": null,
                  "min": null,
                  "name": "preamble_override",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": "AUTO",
                  "help": {
                    "en_US": "Dictates how the prompt will be constructed. With prompt_truncation set to \"AUTO\", some elements from chat histories will be dropped in an attempt to construct a prompt that fits within the model's context length limit.",
                    "zh_Hans": "指定如何构造 Prompt。当 prompt_truncation 设置为 \"AUTO\" 时，将会丢弃一些来自聊天记录的元素，以尝试构造一个符合模型上下文长度限制的 Prompt。"
                  },
                  "label": {
                    "en_US": "Prompt Truncation",
                    "zh_Hans": "提示截断"
                  },
                  "max": null,
                  "min": null,
                  "name": "prompt_truncation",
                  "options": [
                    "AUTO",
                    "OFF"
                  ],
                  "precision": null,
                  "required": true,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.3",
                "output": "0.6",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "command-light-nightly-chat",
                "zh_Hans": "command-light-nightly-chat"
              },
              "model": "command-light-nightly-chat",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 5,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.75,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "p"
                  },
                  "max": 0.99,
                  "min": 0.01,
                  "name": "p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "When specified, the default Cohere preamble will be replaced with the provided one.",
                    "zh_Hans": "当指定时，将使用提供的前导文本替换默认的 Cohere 前导文本。"
                  },
                  "label": {
                    "en_US": "Preamble",
                    "zh_Hans": "前导文本"
                  },
                  "max": null,
                  "min": null,
                  "name": "preamble_override",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": "AUTO",
                  "help": {
                    "en_US": "Dictates how the prompt will be constructed. With prompt_truncation set to \"AUTO\", some elements from chat histories will be dropped in an attempt to construct a prompt that fits within the model's context length limit.",
                    "zh_Hans": "指定如何构造 Prompt。当 prompt_truncation 设置为 \"AUTO\" 时，将会丢弃一些来自聊天记录的元素，以尝试构造一个符合模型上下文长度限制的 Prompt。"
                  },
                  "label": {
                    "en_US": "Prompt Truncation",
                    "zh_Hans": "提示截断"
                  },
                  "max": null,
                  "min": null,
                  "name": "prompt_truncation",
                  "options": [
                    "AUTO",
                    "OFF"
                  ],
                  "precision": null,
                  "required": true,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.3",
                "output": "0.6",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "command-light-nightly",
                "zh_Hans": "command-light-nightly"
              },
              "model": "command-light-nightly",
              "model_properties": {
                "context_size": 4096,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 5,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.75,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "p"
                  },
                  "max": 0.99,
                  "min": 0.01,
                  "name": "p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.3",
                "output": "0.6",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "command-light",
                "zh_Hans": "command-light"
              },
              "model": "command-light",
              "model_properties": {
                "context_size": 4096,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 5,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.75,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "p"
                  },
                  "max": 0.99,
                  "min": 0.01,
                  "name": "p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.3",
                "output": "0.6",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "command-nightly-chat",
                "zh_Hans": "command-nightly-chat"
              },
              "model": "command-nightly-chat",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.75,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "p"
                  },
                  "max": 0.99,
                  "min": 0.01,
                  "name": "p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "When specified, the default Cohere preamble will be replaced with the provided one.",
                    "zh_Hans": "当指定时，将使用提供的前导文本替换默认的 Cohere 前导文本。"
                  },
                  "label": {
                    "en_US": "Preamble",
                    "zh_Hans": "前导文本"
                  },
                  "max": null,
                  "min": null,
                  "name": "preamble_override",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": "AUTO",
                  "help": {
                    "en_US": "Dictates how the prompt will be constructed. With prompt_truncation set to \"AUTO\", some elements from chat histories will be dropped in an attempt to construct a prompt that fits within the model's context length limit.",
                    "zh_Hans": "指定如何构造 Prompt。当 prompt_truncation 设置为 \"AUTO\" 时，将会丢弃一些来自聊天记录的元素，以尝试构造一个符合模型上下文长度限制的 Prompt。"
                  },
                  "label": {
                    "en_US": "Prompt Truncation",
                    "zh_Hans": "提示截断"
                  },
                  "max": null,
                  "min": null,
                  "name": "prompt_truncation",
                  "options": [
                    "AUTO",
                    "OFF"
                  ],
                  "precision": null,
                  "required": true,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "1",
                "output": "2",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "command-nightly",
                "zh_Hans": "command-nightly"
              },
              "model": "command-nightly",
              "model_properties": {
                "context_size": 4096,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 5,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.75,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "p"
                  },
                  "max": 0.99,
                  "min": 0.01,
                  "name": "p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "1",
                "output": "2",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "command-r-03-2024"
              },
              "model": "command-r-03-2024",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.75,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "p"
                  },
                  "max": 0.99,
                  "min": 0.01,
                  "name": "p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.5",
                "output": "1.5",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "command-r-08-2024"
              },
              "model": "command-r-08-2024",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.75,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "p"
                  },
                  "max": 0.99,
                  "min": 0.01,
                  "name": "p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.15",
                "output": "0.6",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "command-r-plus-04-2024"
              },
              "model": "command-r-plus-04-2024",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.75,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "p"
                  },
                  "max": 0.99,
                  "min": 0.01,
                  "name": "p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "3",
                "output": "15",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "command-r-plus-08-2024"
              },
              "model": "command-r-plus-08-2024",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.75,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "p"
                  },
                  "max": 0.99,
                  "min": 0.01,
                  "name": "p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "2.5",
                "output": "10",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "command-r-plus"
              },
              "model": "command-r-plus",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.75,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "p"
                  },
                  "max": 0.99,
                  "min": 0.01,
                  "name": "p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "3",
                "output": "15",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "command-r"
              },
              "model": "command-r",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.75,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "p"
                  },
                  "max": 0.99,
                  "min": 0.01,
                  "name": "p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.5",
                "output": "1.5",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "command-r7b-12-2024"
              },
              "model": "command-r7b-12-2024",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.75,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "p"
                  },
                  "max": 0.99,
                  "min": 0.01,
                  "name": "p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0375",
                "output": "0.15",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "command-r7b-arabic-02-2025"
              },
              "model": "command-r7b-arabic-02-2025",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.75,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "p"
                  },
                  "max": 0.99,
                  "min": 0.01,
                  "name": "p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.5",
                "output": "1.5",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "command",
                "zh_Hans": "command"
              },
              "model": "command",
              "model_properties": {
                "context_size": 4096,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 5,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.75,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "p"
                  },
                  "max": 0.99,
                  "min": 0.01,
                  "name": "p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "1",
                "output": "2",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "rerank-english-v3.0"
              },
              "model": "rerank-english-v3.0",
              "model_properties": {
                "context_size": 5120
              },
              "model_type": "rerank",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "rerank-multilingual-v3.0"
              },
              "model": "rerank-multilingual-v3.0",
              "model_properties": {
                "context_size": 5120
              },
              "model_type": "rerank",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "rerank-v3.5"
              },
              "model": "rerank-v3.5",
              "model_properties": {
                "context_size": 5120
              },
              "model_type": "rerank",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "embed-english-light-v2.0"
              },
              "model": "embed-english-light-v2.0",
              "model_properties": {
                "context_size": 1024,
                "max_chunks": 48
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.1",
                "output": null,
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "embed-english-light-v3.0"
              },
              "model": "embed-english-light-v3.0",
              "model_properties": {
                "context_size": 384,
                "max_chunks": 48
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.1",
                "output": null,
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "embed-english-v2.0"
              },
              "model": "embed-english-v2.0",
              "model_properties": {
                "context_size": 4096,
                "max_chunks": 48
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.1",
                "output": null,
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "embed-english-v3.0"
              },
              "model": "embed-english-v3.0",
              "model_properties": {
                "context_size": 1024,
                "max_chunks": 48
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.1",
                "output": null,
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "embed-multilingual-light-v3.0"
              },
              "model": "embed-multilingual-light-v3.0",
              "model_properties": {
                "context_size": 384,
                "max_chunks": 48
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.1",
                "output": null,
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "embed-multilingual-v2.0"
              },
              "model": "embed-multilingual-v2.0",
              "model_properties": {
                "context_size": 768,
                "max_chunks": 48
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.1",
                "output": null,
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "embed-multilingual-v3.0"
              },
              "model": "embed-multilingual-v3.0",
              "model_properties": {
                "context_size": 1024,
                "max_chunks": 48
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.1",
                "output": null,
                "unit": "0.000001"
              }
            }
          ],
          "position": {
            "llm": [
              "command-r",
              "command-r-plus",
              "command-chat",
              "command-light-chat",
              "command-nightly-chat",
              "command-light-nightly-chat",
              "command",
              "command-light",
              "command-nightly",
              "command-light-nightly"
            ],
            "rerank": [
              "rerank-english-v3.0",
              "rerank-multilingual-v3.0",
              "rerank-v3.5"
            ],
            "text_embedding": [
              "embed-multilingual-v3.0",
              "embed-multilingual-light-v3.0",
              "embed-english-v3.0",
              "embed-english-light-v3.0",
              "embed-multilingual-v2.0",
              "embed-english-v2.0",
              "embed-english-light-v2.0"
            ]
          },
          "provider": "cohere",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key",
                  "zh_Hans": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              },
              {
                "default": null,
                "label": {
                  "en_US": "API Base",
                  "zh_Hans": "API Base"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Base, e.g. https://api.cohere.ai/v1",
                  "zh_Hans": "在此输入您的 API Base，如 https://api.cohere.ai/v1"
                },
                "required": false,
                "show_on": [],
                "type": "text-input",
                "variable": "base_url"
              }
            ]
          },
          "supported_model_types": [
            "llm",
            "text-embedding",
            "rerank"
          ]
        },
        "name": "cohere",
        "org": "langgenius",
        "plugin_id": "langgenius/cohere",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/cohere.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": false,
              "llm": false,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-03-21T09:19:15Z",
        "version_updated_at": "2025-03-21T09:19:15Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Chart Generator is a tool for generating statistical charts like bar chart, line chart, pie chart, etc.",
          "pt_BR": "O Gerador de gráficos é uma ferramenta para gerar gráficos estatísticos como gráfico de barras, gráfico de linhas, gráfico de pizza, etc.",
          "zh_Hans": "图表生成是一个用于生成可视化图表的工具，你可以通过它来生成柱状图、折线图、饼图等各类图表"
        },
        "category": "tool",
        "created_at": "2024-11-29T10:02:28Z",
        "endpoint": {},
        "icon": "langgenius/packages/chart/_assets/icon.png",
        "index_id": "langgenius___chart",
        "install_count": 5690,
        "introduction": "",
        "label": {
          "en_US": "ChartGenerator",
          "pt_BR": "Gerador de gráficos",
          "zh_Hans": "图表生成"
        },
        "latest_package_identifier": "langgenius/chart:0.0.2@fb391d9f13ca1d76ceb2596650dd5f4b7b4b5e97a0be16cb22ed132d98a07f7f",
        "latest_version": "0.0.2",
        "model": {},
        "name": "chart",
        "org": "langgenius",
        "plugin_id": "langgenius/chart",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/chart.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "utilities"
          },
          {
            "name": "design"
          }
        ],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "langgenius",
            "description": {
              "en_US": "Chart Generator is a tool for generating statistical charts like bar chart, line chart, pie chart, etc.",
              "pt_BR": "O Gerador de gráficos é uma ferramenta para gerar gráficos estatísticos como gráfico de barras, gráfico de linhas, gráfico de pizza, etc.",
              "zh_Hans": "图表生成是一个用于生成可视化图表的工具，你可以通过它来生成柱状图、折线图、饼图等各类图表"
            },
            "icon": "icon.png",
            "label": {
              "en_US": "ChartGenerator",
              "pt_BR": "Gerador de gráficos",
              "zh_Hans": "图表生成"
            },
            "name": "chart",
            "tags": [
              "design",
              "productivity",
              "utilities"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "linear chart",
                  "pt_BR": "Gráfico linear",
                  "zh_Hans": "线性图表"
                },
                "llm": "generate a linear chart with input data"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Linear Chart",
                  "pt_BR": "Gráfico linear",
                  "zh_Hans": "线性图表"
                },
                "name": "line_chart"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "data for generating chart, each number should be separated by \";\"",
                    "pt_BR": "dados para gerar gráfico linear, cada número deve ser separado por \";\"",
                    "zh_Hans": "用于生成线性图表的数据，每个数字之间用 \";\" 分隔"
                  },
                  "label": {
                    "en_US": "data",
                    "pt_BR": "dados",
                    "zh_Hans": "数据"
                  },
                  "llm_description": "data for generating linear chart, data should be a string contains a list of numbers like \"1;2;3;4;5\"",
                  "max": null,
                  "min": null,
                  "name": "data",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "X axis for chart, each text should be separated by \";\"",
                    "pt_BR": "Eixo X para gráfico linear, cada texto deve ser separado por \";\"",
                    "zh_Hans": "线性图表的 x 轴，每个文本之间用 \";\" 分隔"
                  },
                  "label": {
                    "en_US": "X Axis",
                    "pt_BR": "Eixo X",
                    "zh_Hans": "x 轴"
                  },
                  "llm_description": "x axis for linear chart, x axis should be a string contains a list of texts like \"a;b;c;1;2\" in order to match the data",
                  "max": null,
                  "min": null,
                  "name": "x_axis",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Bar chart",
                  "pt_BR": "Gráfico de barras",
                  "zh_Hans": "柱状图"
                },
                "llm": "generate a bar chart with input data"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Bar Chart",
                  "pt_BR": "Gráfico de barras",
                  "zh_Hans": "柱状图"
                },
                "name": "bar_chart"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "data for generating chart, each number should be separated by \";\"",
                    "pt_BR": "dados para gerar gráfico de barras, cada número deve ser separado por \";\"",
                    "zh_Hans": "用于生成柱状图的数据，每个数字之间用 \";\" 分隔"
                  },
                  "label": {
                    "en_US": "data",
                    "pt_BR": "dados",
                    "zh_Hans": "数据"
                  },
                  "llm_description": "data for generating bar chart, data should be a string contains a list of numbers like \"1;2;3;4;5\"",
                  "max": null,
                  "min": null,
                  "name": "data",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "X axis for chart, each text should be separated by \";\"",
                    "pt_BR": "Eixo X para gráfico de barras, cada texto deve ser separado por \";\"",
                    "zh_Hans": "柱状图的 x 轴，每个文本之间用 \";\" 分隔"
                  },
                  "label": {
                    "en_US": "X Axis",
                    "pt_BR": "Eixo X",
                    "zh_Hans": "x 轴"
                  },
                  "llm_description": "x axis for bar chart, x axis should be a string contains a list of texts like \"a;b;c;1;2\" in order to match the data",
                  "max": null,
                  "min": null,
                  "name": "x_axis",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Pie chart",
                  "pt_BR": "Gráfico de pizza",
                  "zh_Hans": "饼图"
                },
                "llm": "generate a pie chart with input data"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Pie Chart",
                  "pt_BR": "Gráfico de pizza",
                  "zh_Hans": "饼图"
                },
                "name": "pie_chart"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "data for generating chart, each number should be separated by \";\"",
                    "pt_BR": "dados para gerar gráfico de pizza, cada número deve ser separado por \";\"",
                    "zh_Hans": "用于生成饼图的数据，每个数字之间用 \";\" 分隔"
                  },
                  "label": {
                    "en_US": "data",
                    "pt_BR": "dados",
                    "zh_Hans": "数据"
                  },
                  "llm_description": "data for generating pie chart, data should be a string contains a list of numbers like \"1;2;3;4;5\"",
                  "max": null,
                  "min": null,
                  "name": "data",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Categories for chart, each category should be separated by \";\"",
                    "pt_BR": "Categorias para gráfico de pizza, cada categoria deve ser separada por \";\"",
                    "zh_Hans": "饼图的分类，每个分类之间用 \";\" 分隔"
                  },
                  "label": {
                    "en_US": "Categories",
                    "pt_BR": "Categorias",
                    "zh_Hans": "分类"
                  },
                  "llm_description": "categories for pie chart, categories should be a string contains a list of texts like \"a;b;c;1;2\" in order to match the data, each category should be split by \";\"",
                  "max": null,
                  "min": null,
                  "name": "categories",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:08:42Z",
        "version_updated_at": "2025-02-17T07:08:42Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Perplexity.AI",
          "zh_Hans": "Perplexity.AI"
        },
        "category": "tool",
        "created_at": "2024-12-04T11:30:35Z",
        "endpoint": {},
        "icon": "langgenius/packages/perplexity/_assets/icon.svg",
        "index_id": "langgenius___perplexity",
        "install_count": 5309,
        "introduction": "# Perplexity\n\n## Overview\n\nPerplexity is an AI-based search engine that can understand complex queries and provide accurate, relevant real-time answers. Here are the steps to configure and use the Perplexity Search tool in Dify.\n\n## Configuration\n\n### 1. Apply for Perplexity API Key\n\nPlease apply for an API Key at [Perplexity](https://www.perplexity.ai/settings/api), and ensure that your account has sufficient Credits.\n\n### 2. Fill in the configuration in Dify\n\nIn the Dify navigation page, click on Tools > Perplexity > Go to authorize to fill in the API Key.\n\n![](./_assets/perplexity_1.png)\n\n### 3. Using the tool\n\nYou can use the Perplexity Search tool in the following application types:\n\n#### Chatflow / Workflow applications\n\n![](./_assets/perplexity_2.png)\n\nBoth Chatflow and Workflow applications support adding `Perplexity Search` tool nodes. Pass the user's input content through variables to the \"Query\" box in the Perplexity tool node, adjust the built-in parameters of the Perplexity tool as needed, and finally select the output content of the Perplexity tool node in the response box of the \"End\" node.\n\n#### Agent applications\n\n![](path_to_agent_application_image.png)\n\nAdd the `Perplexity Search` tool in the Agent application, then enter relevant commands to invoke this tool.",
        "label": {
          "en_US": "Perplexity",
          "zh_Hans": "Perplexity"
        },
        "latest_package_identifier": "langgenius/perplexity:1.0.0@cb662f8a44deefb34239e5e600816f95174f235664fe69a5f0a69e4c8675766c",
        "latest_version": "1.0.0",
        "model": {},
        "name": "perplexity",
        "org": "langgenius",
        "plugin_id": "langgenius/perplexity",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/perplexity.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "search"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Get your Perplexity API key from Perplexity",
                "zh_Hans": "从 Perplexity 获取您的 Perplexity API key"
              },
              "label": {
                "en_US": "Perplexity API key",
                "zh_Hans": "Perplexity API key"
              },
              "name": "perplexity_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Perplexity API key",
                "zh_Hans": "请输入你的 Perplexity API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://www.perplexity.ai/settings/api"
            }
          ],
          "identity": {
            "author": "langgenius",
            "description": {
              "en_US": "Perplexity.AI",
              "zh_Hans": "Perplexity.AI"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Perplexity",
              "zh_Hans": "Perplexity"
            },
            "name": "perplexity",
            "tags": [
              "search"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Search information using Perplexity AI's language models."
                },
                "llm": "This tool is used to search information using Perplexity AI's language models."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Perplexity Search"
                },
                "name": "perplexity"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The text query to be processed by the AI model.",
                    "zh_Hans": "要由 AI 模型处理的文本查询。"
                  },
                  "label": {
                    "en_US": "Query",
                    "zh_Hans": "查询"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "sonar",
                  "form": "form",
                  "human_description": {
                    "en_US": "The Perplexity AI model to use for generating the response.",
                    "zh_Hans": "用于生成响应的 Perplexity AI 模型。"
                  },
                  "label": {
                    "en_US": "Model Name",
                    "zh_Hans": "模型名称"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": [
                    {
                      "label": {
                        "en_US": "sonar",
                        "zh_Hans": "sonar"
                      },
                      "value": "sonar"
                    },
                    {
                      "label": {
                        "en_US": "sonar-pro",
                        "zh_Hans": "sonar-pro"
                      },
                      "value": "sonar-pro"
                    },
                    {
                      "label": {
                        "en_US": "sonar-reasoning",
                        "zh_Hans": "sonar-reasoning"
                      },
                      "value": "sonar-reasoning"
                    },
                    {
                      "label": {
                        "en_US": "sonar-reasoning-pro",
                        "zh_Hans": "sonar-reasoning-pro"
                      },
                      "value": "sonar-reasoning-pro"
                    },
                    {
                      "label": {
                        "en_US": "sonar-deep-research",
                        "zh_Hans": "sonar-deep-research"
                      },
                      "value": "sonar-deep-research"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 4096,
                  "form": "form",
                  "human_description": {
                    "en_US": "The maximum number of tokens to generate in the response.",
                    "pt_BR": "O número máximo de tokens a serem gerados na resposta.",
                    "zh_Hans": "在响应中生成的最大令牌数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "pt_BR": "Máximo de Tokens",
                    "zh_Hans": "最大令牌数"
                  },
                  "llm_description": "",
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 0.7,
                  "form": "form",
                  "human_description": {
                    "en_US": "Controls randomness in the output. Lower values make the output more focused and deterministic.",
                    "zh_Hans": "控制输出的随机性。较低的值使输出更加集中和确定。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "llm_description": "",
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 5,
                  "form": "form",
                  "human_description": {
                    "en_US": "The number of top results to consider for response generation.",
                    "zh_Hans": "用于生成响应的顶部结果数量。"
                  },
                  "label": {
                    "en_US": "Top K",
                    "zh_Hans": "取样数量"
                  },
                  "llm_description": "",
                  "max": 100,
                  "min": 1,
                  "name": "top_k",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 1,
                  "form": "form",
                  "human_description": {
                    "en_US": "Controls diversity via nucleus sampling.",
                    "zh_Hans": "通过核心采样控制多样性。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "llm_description": "",
                  "max": 1,
                  "min": 0.1,
                  "name": "top_p",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 0,
                  "form": "form",
                  "human_description": {
                    "en_US": "Positive values penalize new tokens based on whether they appear in the text so far.",
                    "zh_Hans": "正值会根据新词元是否已经出现在文本中来对其进行惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "zh_Hans": "存在惩罚"
                  },
                  "llm_description": "",
                  "max": 1,
                  "min": -1,
                  "name": "presence_penalty",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 1,
                  "form": "form",
                  "human_description": {
                    "en_US": "Positive values penalize new tokens based on their existing frequency in the text so far.",
                    "zh_Hans": "正值会根据新词元在文本中已经出现的频率来对其进行惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "zh_Hans": "频率惩罚"
                  },
                  "llm_description": "",
                  "max": 1,
                  "min": 0.1,
                  "name": "frequency_penalty",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to return images in the response.",
                    "zh_Hans": "是否在响应中返回图像。"
                  },
                  "label": {
                    "en_US": "Return Images",
                    "zh_Hans": "返回图像"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "return_images",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to return related questions in the response.",
                    "zh_Hans": "是否在响应中返回相关问题。"
                  },
                  "label": {
                    "en_US": "Return Related Questions",
                    "zh_Hans": "返回相关问题"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "return_related_questions",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": "",
                  "form": "form",
                  "human_description": {
                    "en_US": "Domain to filter the search results. Use comma to separate multiple domains. Up to 3 domains are supported.",
                    "zh_Hans": "用于过滤搜索结果的域名。使用逗号分隔多个域名。最多支持3个域名。"
                  },
                  "label": {
                    "en_US": "Search Domain Filter",
                    "zh_Hans": "搜索域过滤器"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "search_domain_filter",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "month",
                  "form": "form",
                  "human_description": {
                    "en_US": "Filter for search results based on recency.",
                    "zh_Hans": "基于时间筛选搜索结果。"
                  },
                  "label": {
                    "en_US": "Search Recency Filter",
                    "zh_Hans": "搜索时间过滤器"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "search_recency_filter",
                  "options": [
                    {
                      "label": {
                        "en_US": "Day",
                        "zh_Hans": "天"
                      },
                      "value": "day"
                    },
                    {
                      "label": {
                        "en_US": "Week",
                        "zh_Hans": "周"
                      },
                      "value": "week"
                    },
                    {
                      "label": {
                        "en_US": "Month",
                        "zh_Hans": "月"
                      },
                      "value": "month"
                    },
                    {
                      "label": {
                        "en_US": "Year",
                        "zh_Hans": "年"
                      },
                      "value": "year"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "low",
                  "form": "form",
                  "human_description": {
                    "en_US": "Determines how much search context is retrieved for the model.",
                    "zh_Hans": "确定模型检索的搜索上下文量。"
                  },
                  "label": {
                    "en_US": "Search Context Size",
                    "zh_Hans": "搜索上下文大小"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "search_context_size",
                  "options": [
                    {
                      "label": {
                        "en_US": "Low",
                        "zh_Hans": "低"
                      },
                      "value": "low"
                    },
                    {
                      "label": {
                        "en_US": "Medium",
                        "zh_Hans": "中等"
                      },
                      "value": "medium"
                    },
                    {
                      "label": {
                        "en_US": "High",
                        "zh_Hans": "高"
                      },
                      "value": "high"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-16T08:02:18Z",
        "version_updated_at": "2025-04-16T08:02:18Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Stable Diffusion is a tool for generating images which can be deployed locally.",
          "pt_BR": "Stable Diffusion is a tool for generating images which can be deployed locally.",
          "zh_Hans": "Stable Diffusion 是一个可以在本地部署的图片生成的工具。"
        },
        "category": "tool",
        "created_at": "2024-12-02T13:12:00Z",
        "endpoint": {},
        "icon": "langgenius/packages/stablediffusion/_assets/icon.png",
        "index_id": "langgenius___stablediffusion",
        "install_count": 5172,
        "introduction": "# Stable\n\n## Overview\n\nStable Diffusion is a tool for generating images based on text prompts. Dify has implemented the interface to access the Stable Diffusion WebUI API, so you can use it directly in Dify. The following are steps to integrate Stable Diffusion into Dify.\n\n## Configuration\n\n### 1. Make sure you have a machine with a GPU\n\nStable Diffusion requires a machine with a GPU to generate images. However, it's not necessary; you can use CPU to generate images, but it will be slow.\n\n### 2. Launch Stable Diffusion WebUI\n\nLaunch the Stable Diffusion WebUI on your local machine or server.\n\n#### 2.1. Clone the Stable Diffusion WebUI repository\n\nClone the Stable Diffusion WebUI repository from the official repository:\n```\ngit clone https://github.com/AUTOMATIC1111/stable-diffusion-webui\n```\n\n#### 2.2. Launch it locally\n\nAfter cloning the repository, change directory to the cloned repository and run the following command to launch the Stable Diffusion WebUI.\n\n**Windows**\n```\ncd stable-diffusion-webui\n./webui.bat --api --listen\n```\n\n**Linux**\n```\ncd stable-diffusion-webui\n./webui.sh --api --listen\n```\n\n#### 2.3. Prepare Models\n\nAccess the Stable Diffusion WebUI on your browser according to the address shown in the terminal. Download the models from HuggingFace or other sources and put them in the `models` directory of the Stable Diffusion WebUI.\n\nFor example, we use [pastel-mix](https://huggingface.co/JamesFlare/pastel-mix) as the model, use `git lfs` to download the model and put it in the models directory in `stable-diffusion-webui`.\n```\ngit clone https://huggingface.co/JamesFlare/pastel-mix\n```\n\n#### 2.4 Get Model Name\n\nNow you can see `pastel-mix` in the model list, but we still need to get the model name, visit `http://your_id:port/sdapi/v1/sd-models` to get the model name. You will see output like:\n\n```json\n[\n    {\n        \"title\": \"pastel-mix/pastelmix-better-vae-fp32.ckpt [943a810f75]\",\n        \"model_name\": \"pastel-mix_pastelmix-better-vae-fp32\",\n        \"hash\": \"943a810f75\",\n        \"sha256\": \"943a810f7538b32f9d81dc5adea3792c07219964c8a8734565931fcec90d762d\",\n        \"filename\": \"/home/takatost/stable-diffusion-webui/models/Stable-diffusion/pastel-mix/pastelmix-better-vae-fp32.ckpt\",\n        \"config\": null\n    }\n]\n```\n\n### 3. Get Stable Diffusion tools from Plugin Marketplace\n\nThe Stable Diffusion tools could be found at the Plugin Marketplace, please install it first.\n\n### 4. Integrate Stable Diffusion in Dify\n\nFill in the Authentication and Model Configuration in `Tools > Stable Diffusion > To Authorize` with the information you get from the previous steps.\n\n![](./_assets/stablediffusion_1.png)\n\n### 5. Using the tool\n\nYou can use the Stable Diffusion tool in the following application types:\n![](./_assets/stablediffusion_2.png)\n\n#### Chatflow / Workflow Applications\n\nBoth Chatflow and Workflow applications support adding `Stable Diffusion` tool nodes. After adding, you need to fill in the variable referencing the user's input prompt or the content generated by the previous node in the \"Input Variables → Prompt\" section within the node. Finally, use a variable to reference the image output by `Stable Diffusion` in the \"End\" node.\n\n#### Agent Applications\n\nAdd the `Stable Diffusion` tool in the Agent application, then send image descriptions in the chat box to invoke the tool and generate AI images.",
        "label": {
          "en_US": "Stable Diffusion",
          "pt_BR": "Stable Diffusion",
          "zh_Hans": "Stable Diffusion"
        },
        "latest_package_identifier": "langgenius/stablediffusion:0.0.2@0981eaefd440dad630d56c52ef494c921e851ffd0bd30d07baff9a4b0862a317",
        "latest_version": "0.0.2",
        "model": {},
        "name": "stablediffusion",
        "org": "langgenius",
        "plugin_id": "langgenius/stablediffusion",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/stablediffusion.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "image"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "Base URL",
                "pt_BR": "Base URL",
                "zh_Hans": "StableDiffusion服务器的Base URL"
              },
              "name": "base_url",
              "options": null,
              "placeholder": {
                "en_US": "Please input your StableDiffusion server's Base URL",
                "pt_BR": "Please input your StableDiffusion server's Base URL",
                "zh_Hans": "请输入你的 StableDiffusion 服务器的 Base URL"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "Model",
                "pt_BR": "Model",
                "zh_Hans": "模型"
              },
              "name": "model",
              "options": null,
              "placeholder": {
                "en_US": "Please input your model",
                "pt_BR": "Please input your model",
                "zh_Hans": "请输入你的模型名称"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": "https://docs.dify.ai/tutorials/tool-configuration/stable-diffusion"
            }
          ],
          "identity": {
            "author": "langgenius",
            "description": {
              "en_US": "Stable Diffusion is a tool for generating images which can be deployed locally.",
              "pt_BR": "Stable Diffusion is a tool for generating images which can be deployed locally.",
              "zh_Hans": "Stable Diffusion 是一个可以在本地部署的图片生成的工具。"
            },
            "icon": "icon.png",
            "label": {
              "en_US": "Stable Diffusion",
              "pt_BR": "Stable Diffusion",
              "zh_Hans": "Stable Diffusion"
            },
            "name": "stablediffusion",
            "tags": [
              "image"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool for generating images which can be deployed locally, you can use stable-diffusion-webui to deploy it.",
                  "pt_BR": "A tool for generating images which can be deployed locally, you can use stable-diffusion-webui to deploy it.",
                  "zh_Hans": "一个可以在本地部署的图片生成的工具，您可以使用 stable-diffusion-webui 来部署它。"
                },
                "llm": "draw the image you want based on your prompt."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Stable Diffusion WebUI",
                  "pt_BR": "Stable Diffusion WebUI",
                  "zh_Hans": "Stable Diffusion WebUI"
                },
                "name": "stable_diffusion"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Image prompt, you can check the official documentation of Stable Diffusion",
                    "pt_BR": "Image prompt, you can check the official documentation of Stable Diffusion",
                    "zh_Hans": "图像提示词，您可以查看 Stable Diffusion 的官方文档"
                  },
                  "label": {
                    "en_US": "Prompt",
                    "pt_BR": "Prompt",
                    "zh_Hans": "提示词"
                  },
                  "llm_description": "Image prompt of Stable Diffusion, you should describe the image you want to generate as a list of words as possible as detailed, the prompt must be written in English.",
                  "max": null,
                  "min": null,
                  "name": "prompt",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Model Name",
                    "pt_BR": "Model Name",
                    "zh_Hans": "模型名称"
                  },
                  "label": {
                    "en_US": "Model Name",
                    "pt_BR": "Model Name",
                    "zh_Hans": "模型名称"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "",
                  "form": "form",
                  "human_description": {
                    "en_US": "Lora",
                    "pt_BR": "Lora",
                    "zh_Hans": "Lora"
                  },
                  "label": {
                    "en_US": "Lora",
                    "pt_BR": "Lora",
                    "zh_Hans": "Lora"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "lora",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 10,
                  "form": "form",
                  "human_description": {
                    "en_US": "Steps",
                    "pt_BR": "Steps",
                    "zh_Hans": "Steps"
                  },
                  "label": {
                    "en_US": "Steps",
                    "pt_BR": "Steps",
                    "zh_Hans": "Steps"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "steps",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 1024,
                  "form": "form",
                  "human_description": {
                    "en_US": "Width",
                    "pt_BR": "Width",
                    "zh_Hans": "Width"
                  },
                  "label": {
                    "en_US": "Width",
                    "pt_BR": "Width",
                    "zh_Hans": "Width"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "width",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 1024,
                  "form": "form",
                  "human_description": {
                    "en_US": "Height",
                    "pt_BR": "Height",
                    "zh_Hans": "Height"
                  },
                  "label": {
                    "en_US": "Height",
                    "pt_BR": "Height",
                    "zh_Hans": "Height"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "height",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "bad art, ugly, deformed, watermark, duplicated, discontinuous lines",
                  "form": "form",
                  "human_description": {
                    "en_US": "Negative prompt",
                    "pt_BR": "Negative prompt",
                    "zh_Hans": "Negative prompt"
                  },
                  "label": {
                    "en_US": "Negative prompt",
                    "pt_BR": "Negative prompt",
                    "zh_Hans": "Negative prompt"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "negative_prompt",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:15:16Z",
        "version_updated_at": "2025-02-17T07:15:16Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "The models of Amazon Bedrock",
          "ja_JP": "The models of Amazon Bedrock",
          "pt_BR": "The models of Amazon Bedrock",
          "zh_Hans": "The models of Amazon Bedrock"
        },
        "category": "model",
        "created_at": "2025-01-02T08:10:48Z",
        "endpoint": {},
        "icon": "langgenius/packages/bedrock/_assets/icon_s_en.svg",
        "index_id": "langgenius___bedrock",
        "install_count": 5160,
        "introduction": "## amazon-bedrock\n\n**Author:** aws\n**Version:** 0.0.1\n**Type:** extension\n\n### Description\n\n\n\n",
        "label": {
          "en_US": "Amazon Bedrock",
          "ja_JP": "Amazon Bedrock",
          "pt_BR": "Amazon Bedrock",
          "zh_Hans": "Amazon Bedrock"
        },
        "latest_package_identifier": "langgenius/bedrock:0.0.12@73277b1810f8ef28410bb493e19604f742bee636b40dbd1e8fe7c776bbe73196",
        "latest_version": "0.0.12",
        "model": {
          "background": "#FCFDFF",
          "configurate_methods": [
            "predefined-model"
          ],
          "description": {
            "en_US": "Bedrock LLM Model"
          },
          "help": {
            "title": {
              "en_US": "Get your Access Key and Secret Access Key from AWS Console"
            },
            "url": {
              "en_US": "https://console.aws.amazon.com/"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.svg"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "Amazon Bedrock"
          },
          "model_credential_schema": null,
          "models": [
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "J2 Mid V1"
              },
              "model": "ai21.j2-mid-v1",
              "model_properties": {
                "context_size": 8191,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "topP"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "topP",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "maxTokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "maxTokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": null,
                  "label": {
                    "en_US": "Count Penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "count_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": null,
                  "label": {
                    "en_US": "Presence Penalty"
                  },
                  "max": 5,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": null,
                  "label": {
                    "en_US": "Frequency Penalty"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "J2 Ultra V1"
              },
              "model": "ai21.j2-ultra-v1",
              "model_properties": {
                "context_size": 8191,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "topP"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "topP",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "maxTokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "maxTokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": null,
                  "label": {
                    "en_US": "Count Penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "count_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": null,
                  "label": {
                    "en_US": "Presence Penalty"
                  },
                  "max": 5,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": null,
                  "label": {
                    "en_US": "Frequency Penalty"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Jamba 1.5 Large"
              },
              "model": "ai21.jamba-1-5-large-v1:0",
              "model_properties": {
                "context_size": 256000,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_gen_len"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_gen_len",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.002",
                "output": "0.008",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Jamba 1.5 Mini"
              },
              "model": "ai21.jamba-1-5-mini-v1:0",
              "model_properties": {
                "context_size": 256000,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_gen_len"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_gen_len",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0002",
                "output": "0.0004",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "stream-tool-call",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Nova Lite V1"
              },
              "model": "amazon.nova-lite-v1:0",
              "model_properties": {
                "context_size": 300000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": true,
                  "help": {
                    "en_US": "Enable prompt caching to improve performance and reduce costs. Amazon Nova Lite supports cache checkpoints in system and messages fields with a minimum of 1024 tokens per checkpoint.",
                    "zh_Hans": "启用提示缓存可以提高性能并降低成本。Amazon Nova Lite支持在system和messages字段中使用缓存检查点，每个检查点至少需要1024个token。"
                  },
                  "label": {
                    "en_US": "Enable Prompt Cache",
                    "zh_Hans": "启用提示缓存"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_cache",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_new_tokens"
                  },
                  "max": 5000,
                  "min": 1,
                  "name": "max_new_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "The amount of randomness injected into the response.",
                    "zh_Hans": "生成内容的随机性。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.999,
                  "help": null,
                  "label": {
                    "en_US": "In nucleus sampling, Amazon Nova computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.",
                    "zh_Hans": "在核采样中，Amazon Nova 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": null,
                  "label": {
                    "en_US": "Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.",
                    "zh_Hans": "对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.00006",
                "output": "0.00024",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "stream-tool-call",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Nova Micro V1"
              },
              "model": "amazon.nova-micro-v1:0",
              "model_properties": {
                "context_size": 300000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": true,
                  "help": {
                    "en_US": "Enable prompt caching to improve performance and reduce costs. Amazon Nova Micro supports cache checkpoints in system and messages fields with a minimum of 1024 tokens per checkpoint.",
                    "zh_Hans": "启用提示缓存可以提高性能并降低成本。Amazon Nova Micro支持在system和messages字段中使用缓存检查点，每个检查点至少需要1024个token。"
                  },
                  "label": {
                    "en_US": "Enable Prompt Cache",
                    "zh_Hans": "启用提示缓存"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_cache",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_new_tokens"
                  },
                  "max": 5000,
                  "min": 1,
                  "name": "max_new_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "The amount of randomness injected into the response.",
                    "zh_Hans": "生成内容的随机性。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.999,
                  "help": null,
                  "label": {
                    "en_US": "In nucleus sampling, Amazon Nova computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.",
                    "zh_Hans": "在核采样中，Amazon Nova 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": null,
                  "label": {
                    "en_US": "Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.",
                    "zh_Hans": "对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.00003",
                "output": "0.00012",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "stream-tool-call",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Nova Pro V1"
              },
              "model": "amazon.nova-pro-v1:0",
              "model_properties": {
                "context_size": 300000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": true,
                  "help": {
                    "en_US": "Enable prompt caching to improve performance and reduce costs. Amazon Nova Pro supports cache checkpoints in system and messages fields with a minimum of 1024 tokens per checkpoint.",
                    "zh_Hans": "启用提示缓存可以提高性能并降低成本。Amazon Nova Pro支持在system和messages字段中使用缓存检查点，每个检查点至少需要1024个token。"
                  },
                  "label": {
                    "en_US": "Enable Prompt Cache",
                    "zh_Hans": "启用提示缓存"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_cache",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_new_tokens"
                  },
                  "max": 5000,
                  "min": 1,
                  "name": "max_new_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "The amount of randomness injected into the response.",
                    "zh_Hans": "生成内容的随机性。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.999,
                  "help": null,
                  "label": {
                    "en_US": "In nucleus sampling, Amazon Nova computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.",
                    "zh_Hans": "在核采样中，Amazon Nova 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": null,
                  "label": {
                    "en_US": "Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.",
                    "zh_Hans": "对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.00012",
                "output": "0.00048",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Titan Text G1 - Express"
              },
              "model": "amazon.titan-text-express-v1",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "topP"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "topP",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "maxTokenCount"
                  },
                  "max": 8000,
                  "min": 1,
                  "name": "maxTokenCount",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0008",
                "output": "0.0016",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Titan Text G1 - Lite"
              },
              "model": "amazon.titan-text-lite-v1",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "topP"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "topP",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "maxTokenCount"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "maxTokenCount",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0003",
                "output": "0.0004",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Claude 3.5 Haiku"
              },
              "model": "anthropic.claude-3-5-haiku-20241022-v1:0",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": true,
                  "help": {
                    "en_US": "Enable prompt caching to improve performance and reduce costs. Claude 3.5 Haiku supports cache checkpoints in system, messages, and tools fields with a minimum of 2048 tokens per checkpoint.",
                    "zh_Hans": "启用提示缓存可以提高性能并降低成本。Claude 3.5 Haiku支持在system、messages和tools字段中使用缓存检查点，每个检查点至少需要2048个token。"
                  },
                  "label": {
                    "en_US": "Enable Prompt Cache",
                    "zh_Hans": "启用提示缓存"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_cache",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.",
                    "zh_Hans": "停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "The amount of randomness injected into the response.",
                    "zh_Hans": "生成内容的随机性。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.999,
                  "help": null,
                  "label": {
                    "en_US": "In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.",
                    "zh_Hans": "在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": null,
                  "label": {
                    "en_US": "Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.",
                    "zh_Hans": "对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.00025",
                "output": "0.00125",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Claude 3.5 Sonnet"
              },
              "model": "anthropic.claude-3-5-sonnet-20240620-v1:0",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.",
                    "zh_Hans": "停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "The amount of randomness injected into the response.",
                    "zh_Hans": "生成内容的随机性。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.999,
                  "help": null,
                  "label": {
                    "en_US": "In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.",
                    "zh_Hans": "在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": null,
                  "label": {
                    "en_US": "Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.",
                    "zh_Hans": "对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.003",
                "output": "0.015",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Claude 3.5 Sonnet V2"
              },
              "model": "anthropic.claude-3-5-sonnet-20241022-v2:0",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.",
                    "zh_Hans": "停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "The amount of randomness injected into the response.",
                    "zh_Hans": "生成内容的随机性。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.999,
                  "help": null,
                  "label": {
                    "en_US": "In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.",
                    "zh_Hans": "在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": null,
                  "label": {
                    "en_US": "Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.",
                    "zh_Hans": "对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.003",
                "output": "0.015",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Claude 3 Haiku"
              },
              "model": "anthropic.claude-3-haiku-20240307-v1:0",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.",
                    "zh_Hans": "停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "The amount of randomness injected into the response.",
                    "zh_Hans": "生成内容的随机性。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.999,
                  "help": null,
                  "label": {
                    "en_US": "In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.",
                    "zh_Hans": "在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": null,
                  "label": {
                    "en_US": "Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.",
                    "zh_Hans": "对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.00025",
                "output": "0.00125",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Claude 3 Opus"
              },
              "model": "anthropic.claude-3-opus-20240229-v1:0",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.",
                    "zh_Hans": "停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "The amount of randomness injected into the response.",
                    "zh_Hans": "生成内容的随机性。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.999,
                  "help": null,
                  "label": {
                    "en_US": "In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.",
                    "zh_Hans": "在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": null,
                  "label": {
                    "en_US": "Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.",
                    "zh_Hans": "对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.015",
                "output": "0.075",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Claude 3 Sonnet"
              },
              "model": "anthropic.claude-3-sonnet-20240229-v1:0",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.",
                    "zh_Hans": "停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "The amount of randomness injected into the response.",
                    "zh_Hans": "生成内容的随机性。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.999,
                  "help": null,
                  "label": {
                    "en_US": "In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.",
                    "zh_Hans": "在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": null,
                  "label": {
                    "en_US": "Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.",
                    "zh_Hans": "对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.003",
                "output": "0.015",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Claude Instant 1"
              },
              "model": "anthropic.claude-instant-v1",
              "model_properties": {
                "context_size": 100000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.",
                    "zh_Hans": "停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "The amount of randomness injected into the response.",
                    "zh_Hans": "生成内容的随机性。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.999,
                  "help": null,
                  "label": {
                    "en_US": "In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.",
                    "zh_Hans": "在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": null,
                  "label": {
                    "en_US": "Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.",
                    "zh_Hans": "对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0008",
                "output": "0.0024",
                "unit": "0.001"
              }
            },
            {
              "deprecated": true,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Claude 1"
              },
              "model": "anthropic.claude-v1",
              "model_properties": {
                "context_size": 100000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.",
                    "zh_Hans": "停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "The amount of randomness injected into the response.",
                    "zh_Hans": "生成内容的随机性。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.999,
                  "help": null,
                  "label": {
                    "en_US": "In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.",
                    "zh_Hans": "在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": null,
                  "label": {
                    "en_US": "Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.",
                    "zh_Hans": "对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.008",
                "output": "0.024",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Claude 2.1"
              },
              "model": "anthropic.claude-v2:1",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.",
                    "zh_Hans": "停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "The amount of randomness injected into the response.",
                    "zh_Hans": "生成内容的随机性。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.999,
                  "help": null,
                  "label": {
                    "en_US": "In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.",
                    "zh_Hans": "在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": null,
                  "label": {
                    "en_US": "Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.",
                    "zh_Hans": "对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.008",
                "output": "0.024",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Claude 2"
              },
              "model": "anthropic.claude-v2",
              "model_properties": {
                "context_size": 100000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.",
                    "zh_Hans": "停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "The amount of randomness injected into the response.",
                    "zh_Hans": "生成内容的随机性。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.999,
                  "help": null,
                  "label": {
                    "en_US": "In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.",
                    "zh_Hans": "在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": null,
                  "label": {
                    "en_US": "Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.",
                    "zh_Hans": "对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.008",
                "output": "0.024",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Command Light Text V14"
              },
              "model": "cohere.command-light-text-v14",
              "model_properties": {
                "context_size": 4096,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0003",
                "output": "0.0006",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Command R+"
              },
              "model": "cohere.command-r-plus-v1:0",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 5,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.75,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "p"
                  },
                  "max": 0.99,
                  "min": 0.01,
                  "name": "p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "3",
                "output": "15",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Command R"
              },
              "model": "cohere.command-r-v1:0",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 5,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.75,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "p"
                  },
                  "max": 0.99,
                  "min": 0.01,
                  "name": "p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.5",
                "output": "1.5",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Command Text V14"
              },
              "model": "cohere.command-text-v14",
              "model_properties": {
                "context_size": 4096,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0015",
                "output": "0.002",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Claude 3.5 Sonnet(EU.Cross Region Inference)"
              },
              "model": "eu.anthropic.claude-3-5-sonnet-20240620-v1:0",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.",
                    "zh_Hans": "停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "The amount of randomness injected into the response.",
                    "zh_Hans": "生成内容的随机性。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.999,
                  "help": null,
                  "label": {
                    "en_US": "In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.",
                    "zh_Hans": "在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": null,
                  "label": {
                    "en_US": "Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.",
                    "zh_Hans": "对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.003",
                "output": "0.015",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Claude 3.5 Sonnet V2(EU.Cross Region Inference)"
              },
              "model": "eu.anthropic.claude-3-5-sonnet-20241022-v2:0",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.",
                    "zh_Hans": "停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "The amount of randomness injected into the response.",
                    "zh_Hans": "生成内容的随机性。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.999,
                  "help": null,
                  "label": {
                    "en_US": "In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.",
                    "zh_Hans": "在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": null,
                  "label": {
                    "en_US": "Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.",
                    "zh_Hans": "对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.003",
                "output": "0.015",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Claude 3 Haiku(EU.Cross Region Inference)"
              },
              "model": "eu.anthropic.claude-3-haiku-20240307-v1:0",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.",
                    "zh_Hans": "停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "The amount of randomness injected into the response.",
                    "zh_Hans": "生成内容的随机性。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.999,
                  "help": null,
                  "label": {
                    "en_US": "In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.",
                    "zh_Hans": "在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": null,
                  "label": {
                    "en_US": "Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.",
                    "zh_Hans": "对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.00025",
                "output": "0.00125",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Claude 3 Sonnet(EU.Cross Region Inference)"
              },
              "model": "eu.anthropic.claude-3-sonnet-20240229-v1:0",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.",
                    "zh_Hans": "停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "The amount of randomness injected into the response.",
                    "zh_Hans": "生成内容的随机性。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.999,
                  "help": null,
                  "label": {
                    "en_US": "In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.",
                    "zh_Hans": "在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": null,
                  "label": {
                    "en_US": "Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.",
                    "zh_Hans": "对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.003",
                "output": "0.015",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama 2 Chat 13B"
              },
              "model": "meta.llama2-13b-chat-v1",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_gen_len"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_gen_len",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.00075",
                "output": "0.001",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama 2 Chat 70B"
              },
              "model": "meta.llama2-70b-chat-v1",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_gen_len"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_gen_len",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.00195",
                "output": "0.00256",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama 3.1 405B Instruct"
              },
              "model": "meta.llama3-1-405b-instruct-v1:0",
              "model_properties": {
                "context_size": 128000,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.9,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_gen_len"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_gen_len",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.00532",
                "output": "0.016",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama 3.1 Instruct 70B"
              },
              "model": "meta.llama3-1-70b-instruct-v1:0",
              "model_properties": {
                "context_size": 128000,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.9,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_gen_len"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_gen_len",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.00265",
                "output": "0.0035",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama 3.1 Instruct 8B"
              },
              "model": "meta.llama3-1-8b-instruct-v1:0",
              "model_properties": {
                "context_size": 128000,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.9,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_gen_len"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_gen_len",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0003",
                "output": "0.0006",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama 3 Instruct 70B"
              },
              "model": "meta.llama3-70b-instruct-v1:0",
              "model_properties": {
                "context_size": 8192,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_gen_len"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_gen_len",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.00265",
                "output": "0.0035",
                "unit": "0.00001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama 3 Instruct 8B"
              },
              "model": "meta.llama3-8b-instruct-v1:0",
              "model_properties": {
                "context_size": 8192,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_gen_len"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_gen_len",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0004",
                "output": "0.0006",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Mistral 7B Instruct"
              },
              "model": "mistral.mistral-7b-instruct-v0:2",
              "model_properties": {
                "context_size": 32000,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.9,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 50,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 200,
                  "min": 1,
                  "name": "top_k",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "top_k"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.00015",
                "output": "0.0002",
                "unit": "0.00001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "tool-call",
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Mistral Large"
              },
              "model": "mistral.mistral-large-2402-v1:0",
              "model_properties": {
                "context_size": 32000,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.008",
                "output": "0.024",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Mistral Large 2 (24.07)"
              },
              "model": "mistral.mistral-large-2407-v1:0",
              "model_properties": {
                "context_size": 128000,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.003",
                "output": "0.009",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Mistral Small"
              },
              "model": "mistral.mistral-small-2402-v1:0",
              "model_properties": {
                "context_size": 32000,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.001",
                "output": "0.03",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Mixtral 8X7B Instruct"
              },
              "model": "mistral.mixtral-8x7b-instruct-v0:1",
              "model_properties": {
                "context_size": 32000,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.9,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 50,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 200,
                  "min": 1,
                  "name": "top_k",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "top_k"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.00045",
                "output": "0.0007",
                "unit": "0.00001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "stream-tool-call",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Nova Lite V1 (US.Cross Region Inference)"
              },
              "model": "us.amazon.nova-lite-v1:0",
              "model_properties": {
                "context_size": 300000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": true,
                  "help": {
                    "en_US": "Enable prompt caching to improve performance and reduce costs. Amazon Nova Lite supports cache checkpoints in system and messages fields with a minimum of 1024 tokens per checkpoint.",
                    "zh_Hans": "启用提示缓存可以提高性能并降低成本。Amazon Nova Lite支持在system和messages字段中使用缓存检查点，每个检查点至少需要1024个token。"
                  },
                  "label": {
                    "en_US": "Enable Prompt Cache",
                    "zh_Hans": "启用提示缓存"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_cache",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_new_tokens"
                  },
                  "max": 5000,
                  "min": 1,
                  "name": "max_new_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "The amount of randomness injected into the response.",
                    "zh_Hans": "生成内容的随机性。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.999,
                  "help": null,
                  "label": {
                    "en_US": "In nucleus sampling, Amazon Nova computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.",
                    "zh_Hans": "在核采样中，Amazon Nova 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": null,
                  "label": {
                    "en_US": "Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.",
                    "zh_Hans": "对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.00006",
                "output": "0.00024",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Nova Micro V1 (US.Cross Region Inference)"
              },
              "model": "us.amazon.nova-micro-v1:0",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": true,
                  "help": {
                    "en_US": "Enable prompt caching to improve performance and reduce costs. Amazon Nova Micro supports cache checkpoints in system and messages fields with a minimum of 1024 tokens per checkpoint.",
                    "zh_Hans": "启用提示缓存可以提高性能并降低成本。Amazon Nova Micro支持在system和messages字段中使用缓存检查点，每个检查点至少需要1024个token。"
                  },
                  "label": {
                    "en_US": "Enable Prompt Cache",
                    "zh_Hans": "启用提示缓存"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_cache",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_new_tokens"
                  },
                  "max": 5000,
                  "min": 1,
                  "name": "max_new_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "The amount of randomness injected into the response.",
                    "zh_Hans": "生成内容的随机性。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.999,
                  "help": null,
                  "label": {
                    "en_US": "In nucleus sampling, Amazon Nova computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.",
                    "zh_Hans": "在核采样中，Amazon Nova 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": null,
                  "label": {
                    "en_US": "Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.",
                    "zh_Hans": "对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.000035",
                "output": "0.00014",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "stream-tool-call",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Nova Pro V1 (US.Cross Region Inference)"
              },
              "model": "us.amazon.nova-pro-v1:0",
              "model_properties": {
                "context_size": 300000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": true,
                  "help": {
                    "en_US": "Enable prompt caching to improve performance and reduce costs. Amazon Nova Pro supports cache checkpoints in system and messages fields with a minimum of 1024 tokens per checkpoint.",
                    "zh_Hans": "启用提示缓存可以提高性能并降低成本。Amazon Nova Pro支持在system和messages字段中使用缓存检查点，每个检查点至少需要1024个token。"
                  },
                  "label": {
                    "en_US": "Enable Prompt Cache",
                    "zh_Hans": "启用提示缓存"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_cache",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_new_tokens"
                  },
                  "max": 5000,
                  "min": 1,
                  "name": "max_new_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "The amount of randomness injected into the response.",
                    "zh_Hans": "生成内容的随机性。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.999,
                  "help": null,
                  "label": {
                    "en_US": "In nucleus sampling, Amazon Nova computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.",
                    "zh_Hans": "在核采样中，Amazon Nova 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": null,
                  "label": {
                    "en_US": "Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.",
                    "zh_Hans": "对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0008",
                "output": "0.0032",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Claude 3.5 Haiku(US.Cross Region Inference)"
              },
              "model": "us.anthropic.claude-3-5-haiku-20241022-v1:0",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": true,
                  "help": {
                    "en_US": "Enable prompt caching to improve performance and reduce costs. Claude 3.5 Haiku supports cache checkpoints in system, messages, and tools fields with a minimum of 2048 tokens per checkpoint.",
                    "zh_Hans": "启用提示缓存可以提高性能并降低成本。Claude 3.5 Haiku支持在system、messages和tools字段中使用缓存检查点，每个检查点至少需要2048个token。"
                  },
                  "label": {
                    "en_US": "Enable Prompt Cache",
                    "zh_Hans": "启用提示缓存"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_cache",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.",
                    "zh_Hans": "停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "The amount of randomness injected into the response.",
                    "zh_Hans": "生成内容的随机性。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.999,
                  "help": null,
                  "label": {
                    "en_US": "In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.",
                    "zh_Hans": "在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": null,
                  "label": {
                    "en_US": "Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.",
                    "zh_Hans": "对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.001",
                "output": "0.005",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Claude 3.5 Sonnet(US.Cross Region Inference)"
              },
              "model": "us.anthropic.claude-3-5-sonnet-20240620-v1:0",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.",
                    "zh_Hans": "停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "The amount of randomness injected into the response.",
                    "zh_Hans": "生成内容的随机性。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.999,
                  "help": null,
                  "label": {
                    "en_US": "In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.",
                    "zh_Hans": "在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": null,
                  "label": {
                    "en_US": "Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.",
                    "zh_Hans": "对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.003",
                "output": "0.015",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Claude 3.5 Sonnet V2(US.Cross Region Inference)"
              },
              "model": "us.anthropic.claude-3-5-sonnet-20241022-v2:0",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.",
                    "zh_Hans": "停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "The amount of randomness injected into the response.",
                    "zh_Hans": "生成内容的随机性。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.999,
                  "help": null,
                  "label": {
                    "en_US": "In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.",
                    "zh_Hans": "在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": null,
                  "label": {
                    "en_US": "Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.",
                    "zh_Hans": "对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.003",
                "output": "0.015",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Claude 3.7 Sonnet(US.Cross Region Inference)"
              },
              "model": "us.anthropic.claude-3-7-sonnet-20250219-v1:0",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": true,
                  "help": {
                    "en_US": "Enable prompt caching to improve performance and reduce costs. Claude 3.7 Sonnet supports cache checkpoints in system, messages, and tools fields.",
                    "zh_Hans": "启用提示缓存可以提高性能并降低成本。Claude 3.7 Sonnet支持在system、messages和tools字段中使用缓存检查点。"
                  },
                  "label": {
                    "en_US": "Enable Prompt Cache",
                    "zh_Hans": "启用提示缓存"
                  },
                  "max": null,
                  "min": null,
                  "name": "enable_cache",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "Controls the model's reasoning capability. When enabled, temperature will be fixed to 1 and top_p will be disabled.",
                    "zh_Hans": "控制模型的推理能力。启用时，temperature将固定为1且top_p将被禁用。"
                  },
                  "label": {
                    "en_US": "Reasoning Type",
                    "zh_Hans": "推理配置"
                  },
                  "max": null,
                  "min": null,
                  "name": "reasoning_type",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Budget limit for reasoning (minimum 1024), must be less than max_tokens. Only available when reasoning type is enabled.",
                    "zh_Hans": "推理的预算限制（最小1024），必须小于max_tokens。仅在推理类型为enabled时可用。"
                  },
                  "label": {
                    "en_US": "Reasoning Budget",
                    "zh_Hans": "推理预算"
                  },
                  "max": 128000,
                  "min": 0,
                  "name": "reasoning_budget",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.",
                    "zh_Hans": "停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "zh_Hans": "最大token数"
                  },
                  "max": 128000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "The amount of randomness injected into the response. When reasoning is enabled, this value will be fixed to 1.",
                    "zh_Hans": "生成内容的随机性。当推理功能启用时，该值将被固定为1。"
                  },
                  "label": {
                    "en_US": "Model Temperature",
                    "zh_Hans": "模型温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.999,
                  "help": {
                    "en_US": "The probability threshold in nucleus sampling. When reasoning is enabled, this parameter will be disabled.",
                    "zh_Hans": "在核采样中的概率阈值。当推理功能启用时，该参数将被禁用。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.",
                    "zh_Hans": "对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.003",
                "output": "0.015",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Claude 3 Haiku(US.Cross Region Inference)"
              },
              "model": "us.anthropic.claude-3-haiku-20240307-v1:0",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.",
                    "zh_Hans": "停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "The amount of randomness injected into the response.",
                    "zh_Hans": "生成内容的随机性。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.999,
                  "help": null,
                  "label": {
                    "en_US": "In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.",
                    "zh_Hans": "在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": null,
                  "label": {
                    "en_US": "Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.",
                    "zh_Hans": "对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.00025",
                "output": "0.00125",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Claude 3 Opus(US.Cross Region Inference)"
              },
              "model": "us.anthropic.claude-3-opus-20240229-v1:0",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.",
                    "zh_Hans": "停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "The amount of randomness injected into the response.",
                    "zh_Hans": "生成内容的随机性。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.999,
                  "help": null,
                  "label": {
                    "en_US": "In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.",
                    "zh_Hans": "在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": null,
                  "label": {
                    "en_US": "Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.",
                    "zh_Hans": "对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.015",
                "output": "0.075",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Claude 3 Sonnet(US.Cross Region Inference)"
              },
              "model": "us.anthropic.claude-3-sonnet-20240229-v1:0",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.",
                    "zh_Hans": "停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "The amount of randomness injected into the response.",
                    "zh_Hans": "生成内容的随机性。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.999,
                  "help": null,
                  "label": {
                    "en_US": "In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.",
                    "zh_Hans": "在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": null,
                  "label": {
                    "en_US": "Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.",
                    "zh_Hans": "对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.003",
                "output": "0.015",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "DeepSeek-R1(US.Cross Region Inference)"
              },
              "model": "us.deepseek.r1-v1:0",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 8192,
                  "help": {
                    "en_US": "The maximum number of tokens to generate before stopping.",
                    "zh_Hans": "停止前生成的最大令牌数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "zh_Hans": "最大token数"
                  },
                  "max": 128000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "The amount of randomness injected into the response. When reasoning is enabled, this value will be fixed to 1.",
                    "zh_Hans": "生成内容的随机性。当推理功能启用时，该值将被固定为1。"
                  },
                  "label": {
                    "en_US": "Model Temperature",
                    "zh_Hans": "模型温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.999,
                  "help": {
                    "en_US": "The probability threshold in nucleus sampling. When reasoning is enabled, this parameter will be disabled.",
                    "zh_Hans": "在核采样中的概率阈值。当推理功能启用时，该参数将被禁用。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.001",
                "output": "0.005",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "US Meta Llama 3.1 Instruct 70B"
              },
              "model": "us.meta.llama3-1-70b-instruct-v1:0",
              "model_properties": {
                "context_size": 128000,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.9,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_gen_len"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_gen_len",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.00265",
                "output": "0.0035",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "vision",
                "tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "US Meta Llama 3.2 11B Instruct"
              },
              "model": "us.meta.llama3-2-11b-instruct-v1:0",
              "model_properties": {
                "context_size": 128000,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_gen_len"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_gen_len",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.00035",
                "output": "0.00035",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "US Meta Llama 3.2 1B Instruct"
              },
              "model": "us.meta.llama3-2-1b-instruct-v1:0",
              "model_properties": {
                "context_size": 128000,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_gen_len"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_gen_len",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0001",
                "output": "0.0001",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "US Meta Llama 3.2 3B Instruct"
              },
              "model": "us.meta.llama3-2-3b-instruct-v1:0",
              "model_properties": {
                "context_size": 128000,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_gen_len"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_gen_len",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.00015",
                "output": "0.00015",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "US Meta Llama 3.2 90B Instruct"
              },
              "model": "us.meta.llama3-2-90b-instruct-v1:0",
              "model_properties": {
                "context_size": 128000,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.9,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_gen_len"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_gen_len",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.002",
                "output": "0.002",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "amazon.rerank-v1:0"
              },
              "model": "amazon.rerank-v1:0",
              "model_properties": {
                "context_size": 5120
              },
              "model_type": "rerank",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "cohere.rerank-v3-5:0"
              },
              "model": "cohere.rerank-v3-5:0",
              "model_properties": {
                "context_size": 5120
              },
              "model_type": "rerank",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "amazon.titan-embed-text-v1"
              },
              "model": "amazon.titan-embed-text-v1",
              "model_properties": {
                "context_size": 8192
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.0001",
                "output": null,
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "amazon.titan-embed-text-v2:0"
              },
              "model": "amazon.titan-embed-text-v2:0",
              "model_properties": {
                "context_size": 8192
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.00002",
                "output": null,
                "unit": "0.00001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "cohere.embed-english-v3"
              },
              "model": "cohere.embed-english-v3",
              "model_properties": {
                "context_size": 512
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.1",
                "output": null,
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "cohere.embed-multilingual-v3"
              },
              "model": "cohere.embed-multilingual-v3",
              "model_properties": {
                "context_size": 512
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.1",
                "output": null,
                "unit": "0.000001"
              }
            }
          ],
          "position": {},
          "provider": "bedrock",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "Access Key (If not provided, credentials are obtained from the running environment.)",
                  "zh_Hans": "Access Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Access Key",
                  "zh_Hans": "在此输入您的 Access Key"
                },
                "required": false,
                "show_on": [],
                "type": "secret-input",
                "variable": "aws_access_key_id"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Secret Access Key",
                  "zh_Hans": "Secret Access Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Secret Access Key",
                  "zh_Hans": "在此输入您的 Secret Access Key"
                },
                "required": false,
                "show_on": [],
                "type": "secret-input",
                "variable": "aws_secret_access_key"
              },
              {
                "default": "us-east-1",
                "label": {
                  "en_US": "AWS Region",
                  "ja_JP": "AWS リージョン",
                  "zh_Hans": "AWS 地区"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "US East (N. Virginia)",
                      "ja_JP": "米国 (バージニア北部)",
                      "zh_Hans": "美国东部 (弗吉尼亚北部)"
                    },
                    "show_on": [],
                    "value": "us-east-1"
                  },
                  {
                    "label": {
                      "en_US": "US East (Ohio)",
                      "ja_JP": "米国 (オハイオ)",
                      "zh_Hans": "美国东部 (俄亥俄)"
                    },
                    "show_on": [],
                    "value": "us-east-2"
                  },
                  {
                    "label": {
                      "en_US": "US West (Oregon)",
                      "ja_JP": "米国 (オレゴン)",
                      "zh_Hans": "美国西部 (俄勒冈州)"
                    },
                    "show_on": [],
                    "value": "us-west-2"
                  },
                  {
                    "label": {
                      "en_US": "Asia Pacific (Mumbai)",
                      "ja_JP": "アジアパシフィック (ムンバイ)",
                      "zh_Hans": "亚太地区（孟买）"
                    },
                    "show_on": [],
                    "value": "ap-south-1"
                  },
                  {
                    "label": {
                      "en_US": "Asia Pacific (Singapore)",
                      "ja_JP": "アジアパシフィック (シンガポール)",
                      "zh_Hans": "亚太地区 (新加坡)"
                    },
                    "show_on": [],
                    "value": "ap-southeast-1"
                  },
                  {
                    "label": {
                      "en_US": "Asia Pacific (Sydney)",
                      "ja_JP": "アジアパシフィック (シドニー)",
                      "zh_Hans": "亚太地区 (悉尼)"
                    },
                    "show_on": [],
                    "value": "ap-southeast-2"
                  },
                  {
                    "label": {
                      "en_US": "Asia Pacific (Tokyo)",
                      "ja_JP": "アジアパシフィック (東京)",
                      "zh_Hans": "亚太地区 (东京)"
                    },
                    "show_on": [],
                    "value": "ap-northeast-1"
                  },
                  {
                    "label": {
                      "en_US": "Asia Pacific (Seoul)",
                      "ja_JP": "アジアパシフィック (ソウル)",
                      "zh_Hans": "亚太地区（首尔）"
                    },
                    "show_on": [],
                    "value": "ap-northeast-2"
                  },
                  {
                    "label": {
                      "en_US": "Canada (Central)",
                      "ja_JP": "カナダ (中部)",
                      "zh_Hans": "加拿大（中部）"
                    },
                    "show_on": [],
                    "value": "ca-central-1"
                  },
                  {
                    "label": {
                      "en_US": "Europe (Frankfurt)",
                      "ja_JP": "欧州 (フランクフルト)",
                      "zh_Hans": "欧洲 (法兰克福)"
                    },
                    "show_on": [],
                    "value": "eu-central-1"
                  },
                  {
                    "label": {
                      "en_US": "Europe (Ireland)",
                      "ja_JP": "欧州 (アイルランド)",
                      "zh_Hans": "欧洲（爱尔兰）"
                    },
                    "show_on": [],
                    "value": "eu-west-1"
                  },
                  {
                    "label": {
                      "en_US": "Europe (London)",
                      "ja_JP": "欧州 (ロンドン)",
                      "zh_Hans": "欧洲西部 (伦敦)"
                    },
                    "show_on": [],
                    "value": "eu-west-2"
                  },
                  {
                    "label": {
                      "en_US": "Europe (Paris)",
                      "ja_JP": "欧州 (パリ)",
                      "zh_Hans": "欧洲（巴黎）"
                    },
                    "show_on": [],
                    "value": "eu-west-3"
                  },
                  {
                    "label": {
                      "en_US": "South America (São Paulo)",
                      "ja_JP": "南米 (サンパウロ)",
                      "zh_Hans": "南美洲（圣保罗）"
                    },
                    "show_on": [],
                    "value": "sa-east-1"
                  },
                  {
                    "label": {
                      "en_US": "AWS GovCloud (US-West)",
                      "ja_JP": "AWS GovCloud (米国西部)",
                      "zh_Hans": "AWS GovCloud (US-West)"
                    },
                    "show_on": [],
                    "value": "us-gov-west-1"
                  }
                ],
                "placeholder": null,
                "required": true,
                "show_on": [],
                "type": "select",
                "variable": "aws_region"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Bedrock Endpoint URL",
                  "zh_Hans": "Bedrock Endpoint URL"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Bedrock Endpoint URL, e.g. https://123456.cloudfront.net",
                  "zh_Hans": "在此输入您的 Bedrock Endpoint URL, 如：https://123456.cloudfront.net"
                },
                "required": false,
                "show_on": [],
                "type": "text-input",
                "variable": "bedrock_endpoint_url"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Available Model Name",
                  "zh_Hans": "可用模型名称"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "A model you have access to (e.g. amazon.titan-text-lite-v1) for validation.",
                  "zh_Hans": "为了进行验证，请输入一个您可用的模型名称 (例如：amazon.titan-text-lite-v1)"
                },
                "required": false,
                "show_on": [],
                "type": "text-input",
                "variable": "model_for_validation"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Bedrock Proxy URL",
                  "zh_Hans": "Bedrock Proxy URL"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your proxy address (e.g. 127.0.0.1:7890)"
                },
                "required": false,
                "show_on": [],
                "type": "text-input",
                "variable": "bedrock_proxy_url"
              }
            ]
          },
          "supported_model_types": [
            "llm",
            "text-embedding",
            "rerank"
          ]
        },
        "name": "bedrock",
        "org": "langgenius",
        "plugin_id": "langgenius/bedrock",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/bedrock.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-23T01:22:33Z",
        "version_updated_at": "2025-04-23T01:22:33Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "LocalAI"
        },
        "category": "model",
        "created_at": "2024-12-05T09:45:31Z",
        "endpoint": {},
        "icon": "langgenius/packages/localai/_assets/icon_s_en.svg",
        "index_id": "langgenius___localai",
        "install_count": 5023,
        "introduction": "## Overview\n\n[LocalAI](https://github.com/go-skynet/LocalAI) is a drop-in replacement REST API that's compatible with OpenAI API specifications for local inferencing. It allows you to run LLMs (and not only) locally or on-prem with consumer grade hardware, supporting multiple model families that are compatible with the ggml format. Does not require GPU.\n\nDify allows integration with LocalAI for local deployment of large language model inference and embedding capabilities.\n\n## Configure\n\n1. First, clone the LocalAI code repository and navigate to the specified directory.\n```\n$ git clone https://github.com/go-skynet/LocalAI$ cd LocalAI/examples/langchain-chroma\n```\n\n2. Download example LLM and Embedding models.\n```\n$ wget https://huggingface.co/skeskinen/ggml/resolve/main/all-MiniLM-L6-v2/ggml-model-q4_0.bin -O models/bert$ wget https://gpt4all.io/models/ggml-gpt4all-j.bin -O models/ggml-gpt4all-j\n```\nHere, we choose two smaller models that are compatible across all platforms. `ggml-gpt4all-j` serves as the default LLM model, and `all-MiniLM-L6-v2` serves as the default Embedding model, for quick local deployment.\n\n3. Configure the .env file.\n```\n$ mv .env.example .env\n```\nNOTE: Ensure that the THREADS variable value in `.env` doesn't exceed the number of CPU cores on your machine.\n\n4. Start LocalAI.\n```\n# start with docker-compose$ docker-compose up -d --build\n# tail the logs & wait until the build completes$ docker logs -f langchain-chroma-api-17:16AM INF Starting LocalAI using 4 threads, with models path: /models7:16AM INF LocalAI version: v1.24.1 (9cc8d9086580bd2a96f5c96a6b873242879c70bc)\n```\n\nThe LocalAI request API endpoint will be available at [http://127.0.0.1:8080](http://127.0.0.1:8080).\n\nAnd it provides two models, namely:\n  - LLM Model: `ggml-gpt4all-j`\n  - External access name: `gpt-3.5-turbo` (This name is customizable and can be configured in `models/gpt-3.5-turbo.yaml`).\n  - Embedding Model: `all-MiniLM-L6-v2`\n  - External access name: `text-embedding-ada-002` (This name is customizable and can be configured in `models/embeddings.yaml`).\n\n> If you use the Dify Docker deployment method, you need to pay attention to the network configuration to ensure that the Dify container can access the endpoint of LocalAI. The Dify container cannot access localhost inside, and you need to use the host IP address.\n\n5. Integrate the models into Dify.\nGo to `Settings > Model Providers > LocalAI` and fill in:\nModel 1: `ggml-gpt4all-j`\n- Model Type: Text Generation\n- Model Name: `gpt-3.5-turbo`\n- Server URL: [http://127.0.0.1:8080](http://127.0.0.1:8080)\n- If Dify is deployed via docker, fill in the host domain: `http://<your-LocalAI-endpoint-domain>:8080`, which can be a LAN IP address, like: [http://192.168.1.100:8080](http://192.168.1.100:8080)\nClick \"Save\" to use the model in the application.\nModel 2: `all-MiniLM-L6-v2`\n  - Model Type: Embeddings\n  - Model Name: `text-embedding-ada-002`\n  - Server URL: [http://127.0.0.1:8080](http://127.0.0.1:8080)\n    - If Dify is deployed via docker, fill in the host domain: `http://<your-LocalAI-endpoint-domain>:8080`, which can be a LAN IP address, like: [http://192.168.1.100:8080](http://192.168.1.100:8080)\n\nClick \"Save\" to use the model in the application.\n\nFor more information about LocalAI, please refer to: [https://github.com/go-skynet/LocalAI](https://github.com/go-skynet/LocalAI)",
        "label": {
          "en_US": "LocalAI"
        },
        "latest_package_identifier": "langgenius/localai:0.0.3@ffa71a9c05d5f8de48aed4bc7616d880670ed12c68bc313188d8c48e72ccc2a5",
        "latest_version": "0.0.3",
        "model": {
          "background": "#F3F4F6",
          "configurate_methods": [
            "customizable-model"
          ],
          "description": {
            "en_US": "LocalAI"
          },
          "help": {
            "title": {
              "en_US": "How to deploy LocalAI",
              "zh_Hans": "如何部署 LocalAI"
            },
            "url": {
              "en_US": "https://github.com/go-skynet/LocalAI"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.svg"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "LocalAI"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": "chat_completion",
                "label": {
                  "en_US": "Completion type"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Completion",
                      "zh_Hans": "补全"
                    },
                    "show_on": [],
                    "value": "completion"
                  },
                  {
                    "label": {
                      "en_US": "ChatCompletion",
                      "zh_Hans": "对话"
                    },
                    "show_on": [],
                    "value": "chat_completion"
                  }
                ],
                "placeholder": {
                  "en_US": "Select completion type",
                  "zh_Hans": "选择对话类型"
                },
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "select",
                "variable": "completion_type"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Server url",
                  "zh_Hans": "服务器URL"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter the url of your LocalAI, e.g. http://192.168.1.100:8080",
                  "zh_Hans": "在此输入LocalAI的服务器地址，如 http://192.168.1.100:8080"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "server_url"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Context size",
                  "zh_Hans": "上下文大小"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter context size",
                  "zh_Hans": "输入上下文大小"
                },
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "text-input",
                "variable": "context_size"
              }
            ],
            "model": {
              "label": {
                "en_US": "Model Name",
                "zh_Hans": "模型名称"
              },
              "placeholder": {
                "en_US": "Enter your model name",
                "zh_Hans": "输入模型名称"
              }
            }
          },
          "models": [],
          "provider": "localai",
          "provider_credential_schema": null,
          "supported_model_types": [
            "llm",
            "text-embedding",
            "rerank",
            "speech2text"
          ]
        },
        "name": "localai",
        "org": "langgenius",
        "plugin_id": "langgenius/localai",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/localai.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-02-28T01:10:06Z",
        "version_updated_at": "2025-02-28T01:10:06Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Finance, and Yahoo! get the latest news, stock quotes, and interactive chart with Yahoo!",
          "pt_BR": "Finance, and Yahoo! get the latest news, stock quotes, and interactive chart with Yahoo!",
          "zh_Hans": "雅虎财经，获取并整理出最新的新闻、股票报价等一切你想要的财经信息。"
        },
        "category": "tool",
        "created_at": "2025-01-02T06:30:45Z",
        "endpoint": {},
        "icon": "langgenius/packages/yahoo/_assets/icon.png",
        "index_id": "langgenius___yahoo",
        "install_count": 4804,
        "introduction": "# Yahoo Finance\n\n## Overview\n\nThe Yahoo Finance is a service that provides access to real-time and historical stock market data. It enables users to fetch various types of stock information, such as price quotes, historical prices, company profiles, and financial news. The API offers structured data, allowing developers to integrate market data into their applications and analysis tools.\n\n## Configuration\n\n### 1. Get YahooFinance tools from Plugin Marketplace\n\nThe YahooFinance tools could be found at the Plugin Marketplace, please install it.\n\n![](./_assets/yahoo_1.png)\n\n### 2. Using the tool\n\nYou can use the `YahooFinance` tool in the following application types:\n\n![](./_assets/yahoo_2.png)\n\n#### Chatflow / Workflow applications\n\nBoth Chatflow and Workflow applications support adding one of the `YahooFinance` tool nodes.\n\n#### Agent applications\n\nAdd one of the `YahooFinance` tools in the Agent application, then enter online search instructions to call this tool.",
        "label": {
          "en_US": "YahooFinance",
          "pt_BR": "YahooFinance",
          "zh_Hans": "雅虎财经"
        },
        "latest_package_identifier": "langgenius/yahoo:0.0.4@251cb9671af71cde1acdb921b9d2dbe1225986e3da7cc29c9470c24be7f7c885",
        "latest_version": "0.0.4",
        "model": {},
        "name": "yahoo",
        "org": "langgenius",
        "plugin_id": "langgenius/yahoo",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/yahoo.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "business"
          },
          {
            "name": "finance"
          }
        ],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "langgenius",
            "description": {
              "en_US": "Finance, and Yahoo! get the latest news, stock quotes, and interactive chart with Yahoo!",
              "pt_BR": "Finance, and Yahoo! get the latest news, stock quotes, and interactive chart with Yahoo!",
              "zh_Hans": "雅虎财经，获取并整理出最新的新闻、股票报价等一切你想要的财经信息。"
            },
            "icon": "icon.png",
            "label": {
              "en_US": "YahooFinance",
              "pt_BR": "YahooFinance",
              "zh_Hans": "雅虎财经"
            },
            "name": "yahoo",
            "tags": [
              "business",
              "finance"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool for get analytics about a ticker from Yahoo Finance.",
                  "pt_BR": "Uma ferramenta para obter análises sobre um ticker do Yahoo Finance.",
                  "zh_Hans": "一个用于从雅虎财经获取分析数据的工具。"
                },
                "llm": "A tool for get analytics from Yahoo Finance. Input should be the ticker symbol like AAPL."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Analytics",
                  "pt_BR": "Análises",
                  "zh_Hans": "分析"
                },
                "name": "yahoo_finance_analytics"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ticker symbol of the company you want to analyze.",
                    "pt_BR": "O símbolo do ticker da empresa que você deseja analisar.",
                    "zh_Hans": "你想要搜索的公司的股票代码。"
                  },
                  "label": {
                    "en_US": "Ticker symbol",
                    "pt_BR": "Símbolo do ticker",
                    "zh_Hans": "股票代码"
                  },
                  "llm_description": "The ticker symbol of the company you want to analyze.",
                  "max": null,
                  "min": null,
                  "name": "symbol",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The start date of the analytics.",
                    "pt_BR": "A data de início das análises.",
                    "zh_Hans": "分析的开始日期。"
                  },
                  "label": {
                    "en_US": "Start date",
                    "pt_BR": "Data de início",
                    "zh_Hans": "开始日期"
                  },
                  "llm_description": "The start date of the analytics, the format of the date must be YYYY-MM-DD like 2020-01-01.",
                  "max": null,
                  "min": null,
                  "name": "start_date",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The end date of the analytics.",
                    "pt_BR": "A data de término das análises.",
                    "zh_Hans": "分析的结束日期。"
                  },
                  "label": {
                    "en_US": "End date",
                    "pt_BR": "Data de término",
                    "zh_Hans": "结束日期"
                  },
                  "llm_description": "The end date of the analytics, the format of the date must be YYYY-MM-DD like 2024-01-01.",
                  "max": null,
                  "min": null,
                  "name": "end_date",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for search ticker information from Yahoo Finance.",
                  "pt_BR": "Uma ferramenta para buscar informações de ticker do Yahoo Finance.",
                  "zh_Hans": "一个用于从雅虎财经搜索股票信息的工具。"
                },
                "llm": "A tool for search ticker information from Yahoo Finance. Input should be the ticker symbol like AAPL."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Ticker",
                  "pt_BR": "Ticker",
                  "zh_Hans": "股票信息"
                },
                "name": "yahoo_finance_ticker"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ticker symbol of the company you want to search.",
                    "pt_BR": "O símbolo do ticker da empresa que você deseja pesquisar.",
                    "zh_Hans": "你想要搜索的公司的股票代码。"
                  },
                  "label": {
                    "en_US": "Ticker symbol",
                    "pt_BR": "Símbolo do ticker",
                    "zh_Hans": "股票代码"
                  },
                  "llm_description": "The ticker symbol of the company you want to search.",
                  "max": null,
                  "min": null,
                  "name": "symbol",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for get news about a ticker from Yahoo Finance.",
                  "pt_BR": "Uma ferramenta para obter notícias sobre um ticker da Yahoo Finance.",
                  "zh_Hans": "一个用于从雅虎财经获取新闻的工具。"
                },
                "llm": "A tool for get news from Yahoo Finance. Input should be the ticker symbol like AAPL."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "News",
                  "pt_BR": "Notícias",
                  "zh_Hans": "新闻"
                },
                "name": "yahoo_finance_news"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ticker symbol of the company you want to search.",
                    "pt_BR": "O símbolo do ticker da empresa que você deseja pesquisar.",
                    "zh_Hans": "你想要搜索的公司的股票代码。"
                  },
                  "label": {
                    "en_US": "Ticker symbol",
                    "pt_BR": "Símbolo do ticker",
                    "zh_Hans": "股票代码"
                  },
                  "llm_description": "The ticker symbol of the company you want to search.",
                  "max": null,
                  "min": null,
                  "name": "symbol",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-18T06:06:45Z",
        "version_updated_at": "2025-04-18T06:06:45Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Minimax"
        },
        "category": "model",
        "created_at": "2025-01-02T06:49:13Z",
        "endpoint": {},
        "icon": "langgenius/packages/minimax/_assets/icon_s_en.png",
        "index_id": "langgenius___minimax",
        "install_count": 4686,
        "introduction": "# Overview\nMiniMax is an advanced AI platform that provides a suite of powerful models designed for various applications, including LLMs. \n\n# Configure\n1. Install Minimax from Dify Marketplace.\n2. Create a Minimax account and [get API keys](https://platform.minimaxi.com/user-center/basic-information/interface-key).\n3. Fill in the configurations for Minimax in Settings -> Model Provider.\n\n![](_assets/minimax.PNG)",
        "label": {
          "en_US": "Minimax"
        },
        "latest_package_identifier": "langgenius/minimax:0.0.5@e3dc9410e71e42bb952eb9043ed8e791b91fc064f64d68162e3e36312c7828b7",
        "latest_version": "0.0.5",
        "model": {
          "background": "#FFEFEF",
          "configurate_methods": [
            "predefined-model"
          ],
          "description": {
            "en_US": "Minimax"
          },
          "help": {
            "title": {
              "en_US": "Get your API Key from Minimax",
              "zh_Hans": "从 Minimax 获取您的 API Key"
            },
            "url": {
              "en_US": "https://api.minimax.chat/user-center/basic-information/interface-key"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.png"
          },
          "icon_small": {
            "en_US": "icon_s_en.png"
          },
          "label": {
            "en_US": "Minimax"
          },
          "model_credential_schema": null,
          "models": [
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Abab5-Chat"
              },
              "model": "abab5-chat",
              "model_properties": {
                "context_size": 6144,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 6144,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 6144,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "Mask the sensitive info of the generated content, such as email/domain/link/address/phone/id..",
                    "zh_Hans": "对输出中易涉及隐私问题的文本信息进行打码，目前包括但不限于邮箱、域名、链接、证件号、家庭住址等，默认true，即开启打码"
                  },
                  "label": {
                    "en_US": "Moderate",
                    "zh_Hans": "隐私保护"
                  },
                  "max": null,
                  "min": null,
                  "name": "mask_sensitive_info",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.015",
                "output": "0.015",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Abab5.5-Chat"
              },
              "model": "abab5.5-chat",
              "model_properties": {
                "context_size": 16384,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.9,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0.01,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0.01,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 6144,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 16384,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "Mask the sensitive info of the generated content, such as email/domain/link/address/phone/id..",
                    "zh_Hans": "对输出中易涉及隐私问题的文本信息进行打码，目前包括但不限于邮箱、域名、链接、证件号、家庭住址等，默认true，即开启打码"
                  },
                  "label": {
                    "en_US": "Moderate",
                    "zh_Hans": "隐私保护"
                  },
                  "max": null,
                  "min": null,
                  "name": "mask_sensitive_info",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": false,
                  "help": null,
                  "label": {
                    "en_US": "Enable Web Search",
                    "zh_Hans": "开启网页搜索"
                  },
                  "max": null,
                  "min": null,
                  "name": "plugin_web_search",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.015",
                "output": "0.015",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Abab5.5s-Chat"
              },
              "model": "abab5.5s-chat",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.9,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0.01,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0.01,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 3072,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "Mask the sensitive info of the generated content, such as email/domain/link/address/phone/id..",
                    "zh_Hans": "对输出中易涉及隐私问题的文本信息进行打码，目前包括但不限于邮箱、域名、链接、证件号、家庭住址等，默认true，即开启打码"
                  },
                  "label": {
                    "en_US": "Moderate",
                    "zh_Hans": "隐私保护"
                  },
                  "max": null,
                  "min": null,
                  "name": "mask_sensitive_info",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.005",
                "output": "0.005",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Abab6-Chat"
              },
              "model": "abab6-chat",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0.01,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.9,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0.01,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 32768,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "Mask the sensitive info of the generated content, such as email/domain/link/address/phone/id..",
                    "zh_Hans": "对输出中易涉及隐私问题的文本信息进行打码，目前包括但不限于邮箱、域名、链接、证件号、家庭住址等，默认true，即开启打码"
                  },
                  "label": {
                    "en_US": "Moderate",
                    "zh_Hans": "隐私保护"
                  },
                  "max": null,
                  "min": null,
                  "name": "mask_sensitive_info",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.1",
                "output": "0.1",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Abab6.5-Chat"
              },
              "model": "abab6.5-chat",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0.01,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0.01,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "Mask the sensitive info of the generated content, such as email/domain/link/address/phone/id..",
                    "zh_Hans": "对输出中易涉及隐私问题的文本信息进行打码，目前包括但不限于邮箱、域名、链接、证件号、家庭住址等，默认true，即开启打码"
                  },
                  "label": {
                    "en_US": "Moderate",
                    "zh_Hans": "隐私保护"
                  },
                  "max": null,
                  "min": null,
                  "name": "mask_sensitive_info",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.03",
                "output": "0.03",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Abab6.5s-Chat"
              },
              "model": "abab6.5s-chat",
              "model_properties": {
                "context_size": 245760,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0.01,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0.01,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 245760,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "Mask the sensitive info of the generated content, such as email/domain/link/address/phone/id..",
                    "zh_Hans": "对输出中易涉及隐私问题的文本信息进行打码，目前包括但不限于邮箱、域名、链接、证件号、家庭住址等，默认true，即开启打码"
                  },
                  "label": {
                    "en_US": "Moderate",
                    "zh_Hans": "隐私保护"
                  },
                  "max": null,
                  "min": null,
                  "name": "mask_sensitive_info",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.01",
                "output": "0.01",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Abab6.5t-Chat"
              },
              "model": "abab6.5t-chat",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.9,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0.01,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0.01,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 3072,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "Mask the sensitive info of the generated content, such as email/domain/link/address/phone/id..",
                    "zh_Hans": "对输出中易涉及隐私问题的文本信息进行打码，目前包括但不限于邮箱、域名、链接、证件号、家庭住址等，默认true，即开启打码"
                  },
                  "label": {
                    "en_US": "Moderate",
                    "zh_Hans": "隐私保护"
                  },
                  "max": null,
                  "min": null,
                  "name": "mask_sensitive_info",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.005",
                "output": "0.005",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Abab7-chat-preview"
              },
              "model": "abab7-chat-preview",
              "model_properties": {
                "context_size": 245760,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0.01,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0.01,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 245760,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "Mask the sensitive info of the generated content, such as email/domain/link/address/phone/id..",
                    "zh_Hans": "对输出中易涉及隐私问题的文本信息进行打码，目前包括但不限于邮箱、域名、链接、证件号、家庭住址等，默认true，即开启打码"
                  },
                  "label": {
                    "en_US": "Moderate",
                    "zh_Hans": "隐私保护"
                  },
                  "max": null,
                  "min": null,
                  "name": "mask_sensitive_info",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.1",
                "output": "0.1",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Minimax-Text-01"
              },
              "model": "minimax-text-01",
              "model_properties": {
                "context_size": 1000192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0.01,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.95,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0.01,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 1000192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": true,
                  "help": {
                    "en_US": "Mask the sensitive info of the generated content, such as email/domain/link/address/phone/id..",
                    "zh_Hans": "对输出中易涉及隐私问题的文本信息进行打码，目前包括但不限于邮箱、域名、链接、证件号、家庭住址等，默认true，即开启打码"
                  },
                  "label": {
                    "en_US": "Moderate",
                    "zh_Hans": "隐私保护"
                  },
                  "max": null,
                  "min": null,
                  "name": "mask_sensitive_info",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.001",
                "output": "0.008",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "embo-01"
              },
              "model": "embo-01",
              "model_properties": {
                "context_size": 4096,
                "max_chunks": 1
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "RMB",
                "input": "0.0005",
                "output": null,
                "unit": "0.001"
              }
            }
          ],
          "position": {},
          "provider": "minimax",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "minimax_api_key"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Group ID"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your group ID",
                  "zh_Hans": "在此输入您的 Group ID"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "minimax_group_id"
              }
            ]
          },
          "supported_model_types": [
            "llm",
            "text-embedding",
            "tts"
          ]
        },
        "name": "minimax",
        "org": "langgenius",
        "plugin_id": "langgenius/minimax",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/minimax.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-20T09:25:36Z",
        "version_updated_at": "2025-04-20T09:25:36Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Convert Markdown text to Microsoft Word DOCX documents",
          "ja_JP": "Markdown テキストを Microsoft Word DOCX ドキュメントに変換します",
          "pt_BR": "Converta texto Markdown para documentos DOCX do Microsoft Word",
          "zh_Hans": "将Markdown文本转换为Microsoft Word DOCX文档"
        },
        "category": "tool",
        "created_at": "2025-03-19T16:16:19Z",
        "endpoint": {},
        "icon": "stvlynn/packages/doc/_assets/icon.svg",
        "index_id": "stvlynn___doc",
        "install_count": 4558,
        "introduction": "# Markdown to DOCX Converter\n\n**Author:** [Steven Lynn](https://github.com/stvlynn)\n\n**Version:** 0.0.1\n\n**Type:** tool\n\n**Repository:** https://github.com/stvlynn/DOC-Dify-Plugin\n\n---\n\nThis plugin allows you to easily convert Markdown content to Microsoft Word DOCX documents directly within Dify.\n\n## Setup\n\n### Installation\n\n1. Install the plugin from [Dify Marketplace](https://marketplace.dify.ai/plugins/stvlynn/doc)\n2. Navigate to **Plugins** section in your Dify workspace\n3. Find the \"Markdown to DOCX\" plugin and click \"Install\"\n4. Once installed, you can use the plugin in your applications\n\n### Adding to Applications\n\n1. Create or edit a Chatflow or Workflow application\n2. In the tool selection panel, select \"DOC\" tool\n3. Configure the tool in your application flow as needed\n4. Save and publish your application\n\n\n\n## Usage\n\nYou can use this tool to convert Markdown content to DOCX format with two parameters:\n\n- **markdown_content** (required): The Markdown content you want to convert\n\n- **title** (optional): The title for the document (defaults to \"Document\")\n\n![Tool Configuration](./_assets/doc-configure.png)\n\n## Feedback and Issues\n\nIf you encounter any problems or have suggestions for improvements:\n\n1. Please open an issue in the [plugin's GitHub repository](https://github.com/stvlynn/DOC-Dify-Plugin/issues)\n\n2. Provide details about your problem, including error messages and steps to reproduce\n\n3. **Do not** submit issues to the main [Dify](https://github.com/langgenius/dify) repository for plugin-specific problems\n\n## License\n\n[MIT](./LICENSE)\n\n\n\n",
        "label": {
          "en_US": "DOC",
          "ja_JP": "DOC",
          "pt_BR": "DOC",
          "zh_Hans": "DOC"
        },
        "latest_package_identifier": "stvlynn/doc:0.0.1@f02f0f26cb1c81eb1309d79277678688af037554d5c90e06982db17763d7b43f",
        "latest_version": "0.0.1",
        "model": {},
        "name": "doc",
        "org": "stvlynn",
        "plugin_id": "stvlynn/doc",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/doc.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "storage": {
              "enabled": true,
              "size": 1048576
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "stvlynn",
            "description": {
              "en_US": "Convert Markdown text to Microsoft Word DOCX files",
              "ja_JP": "Markdown テキストを Microsoft Word DOCX ファイルに変換します",
              "pt_BR": "Converter texto Markdown para arquivos DOCX do Microsoft Word",
              "zh_Hans": "将Markdown文本转换为Microsoft Word DOCX文件"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "DOC",
              "ja_JP": "DOC",
              "pt_BR": "DOC",
              "zh_Hans": "DOC"
            },
            "name": "doc",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Convert Markdown content to a DOCX (Word) document",
                  "ja_JP": "Markdown コンテンツを DOCX（Word）ドキュメントに変換します",
                  "pt_BR": "Converter conteúdo Markdown para um documento DOCX (Word)",
                  "zh_Hans": "将Markdown内容转换为DOCX（Word）文档"
                },
                "llm": "A tool that converts Markdown formatted text into Microsoft Word DOCX format documents, maintaining basic formatting and structure."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "stvlynn",
                "label": {
                  "en_US": "Markdown to DOCX Converter",
                  "ja_JP": "Markdown から DOCX コンバーター",
                  "pt_BR": "Conversor de Markdown para DOCX",
                  "zh_Hans": "Markdown转DOCX转换器"
                },
                "name": "markdown_to_docx_converter"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The Markdown content to be converted to Word document",
                    "ja_JP": "Word ドキュメントに変換する Markdown コンテンツ",
                    "pt_BR": "O conteúdo Markdown a ser convertido para documento Word",
                    "zh_Hans": "要转换为Word文档的Markdown内容"
                  },
                  "label": {
                    "en_US": "Markdown Content",
                    "ja_JP": "Markdown コンテンツ",
                    "pt_BR": "Conteúdo Markdown",
                    "zh_Hans": "Markdown内容"
                  },
                  "llm_description": "The Markdown content that will be converted to a Word document",
                  "max": null,
                  "min": null,
                  "name": "markdown_content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The title of the Word document",
                    "ja_JP": "Word ドキュメントのタイトル",
                    "pt_BR": "O título do documento Word",
                    "zh_Hans": "Word文档的标题"
                  },
                  "label": {
                    "en_US": "Document Title",
                    "ja_JP": "ドキュメントタイトル",
                    "pt_BR": "Título do Documento",
                    "zh_Hans": "文档标题"
                  },
                  "llm_description": "The title that will be displayed at the top of the Word document",
                  "max": null,
                  "min": null,
                  "name": "title",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-19T16:16:28Z",
        "version_updated_at": "2025-03-19T16:16:28Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Activating humanity's potential through generative AI",
          "pt_BR": "Activating humanity's potential through generative AI",
          "zh_Hans": "通过生成式 AI 激活人类的潜力"
        },
        "category": "tool",
        "created_at": "2024-12-03T08:47:39Z",
        "endpoint": {},
        "icon": "langgenius/packages/stability/_assets/icon.svg",
        "index_id": "langgenius___stability",
        "install_count": 4533,
        "introduction": "# Stability AI Tool\n\n## Overview\n\nStability offers a suite of AI tools and models focused on generative media. It provides capabilities for creating images, audio, and video content from text prompts or other inputs. The suite includes various generative models specializing in different artistic styles and media types.\n\n## Configuration\n\n### 1. Apply for Stability API Key\nPlease apply for an API Key on [Stability.ai](https://platform.stability.ai/account/keys).\n\n### 2. Get Stability tools from Plugin Marketplace\nThe Stability tools could be found at the Plugin Marketplace, please install it first.\n\n### 3. On the Dify navigation page, click `Tools > Stability > Authorize` and fill in the API key.\n\n![](./_assets/stability_1.PNG)\n\n### 4. You can use the Stability tool in the following application types.\n\n![](./_assets/stability_2.PNG)\n\n#### Chatflow / Workflow applications\nBoth Chatflow and Workflow applications support the Stability tool node.\n\n#### Agent applications\nAdd the Stability tool in the Agent application, then enter the short text to call this tool and get the image.",
        "label": {
          "en_US": "Stability",
          "pt_BR": "Stability",
          "zh_Hans": "Stability"
        },
        "latest_package_identifier": "langgenius/stability:0.0.2@b0a227423a7e79785a962c9adcd66c0455389c07a232b93e34069e1231da544b",
        "latest_version": "0.0.2",
        "model": {},
        "name": "stability",
        "org": "langgenius",
        "plugin_id": "langgenius/stability",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/stability.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "image"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "API key",
                "pt_BR": "API key",
                "zh_Hans": "API key"
              },
              "name": "api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your API key",
                "pt_BR": "Please input your API key",
                "zh_Hans": "请输入你的 API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://platform.stability.ai/account/keys"
            }
          ],
          "identity": {
            "author": "langgenius",
            "description": {
              "en_US": "Activating humanity's potential through generative AI",
              "pt_BR": "Activating humanity's potential through generative AI",
              "zh_Hans": "通过生成式 AI 激活人类的潜力"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Stability",
              "pt_BR": "Stability",
              "zh_Hans": "Stability"
            },
            "name": "stability",
            "tags": [
              "image"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool for generate images based on the text input",
                  "pt_BR": "A tool for generate images based on the text input",
                  "zh_Hans": "一个基于文本输入生成图像的工具"
                },
                "llm": "A tool for generate images based on the text input"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "StableDiffusion",
                  "pt_BR": "StableDiffusion",
                  "zh_Hans": "稳定扩散"
                },
                "name": "stability_text2image"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "used for generating images",
                    "pt_BR": "used for generating images",
                    "zh_Hans": "用于生成图像"
                  },
                  "label": {
                    "en_US": "Prompt",
                    "pt_BR": "Prompt",
                    "zh_Hans": "提示词"
                  },
                  "llm_description": "key words for generating images",
                  "max": null,
                  "min": null,
                  "name": "prompt",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "sd3-turbo",
                  "form": "form",
                  "human_description": {
                    "en_US": "Model for generating images",
                    "pt_BR": "Model for generating images",
                    "zh_Hans": "用于生成图像的模型"
                  },
                  "label": {
                    "en_US": "Model",
                    "pt_BR": "Model",
                    "zh_Hans": "模型"
                  },
                  "llm_description": "Model for generating images",
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": [
                    {
                      "label": {
                        "en_US": "Core",
                        "pt_BR": "Core",
                        "zh_Hans": "Core"
                      },
                      "value": "core"
                    },
                    {
                      "label": {
                        "en_US": "Stable Diffusion 3",
                        "pt_BR": "Stable Diffusion 3",
                        "zh_Hans": "Stable Diffusion 3"
                      },
                      "value": "sd3"
                    },
                    {
                      "label": {
                        "en_US": "Stable Diffusion 3 Turbo",
                        "pt_BR": "Stable Diffusion 3 Turbo",
                        "zh_Hans": "Stable Diffusion 3 Turbo"
                      },
                      "value": "sd3-turbo"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "bad art, ugly, deformed, watermark, duplicated, discontinuous lines",
                  "form": "form",
                  "human_description": {
                    "en_US": "Negative Prompt",
                    "pt_BR": "Negative Prompt",
                    "zh_Hans": "负面提示"
                  },
                  "label": {
                    "en_US": "Negative Prompt",
                    "pt_BR": "Negative Prompt",
                    "zh_Hans": "负面提示"
                  },
                  "llm_description": "Negative Prompt",
                  "max": null,
                  "min": null,
                  "name": "negative_prompt",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 0,
                  "form": "form",
                  "human_description": {
                    "en_US": "Seeds",
                    "pt_BR": "Seeds",
                    "zh_Hans": "种子"
                  },
                  "label": {
                    "en_US": "Seeds",
                    "pt_BR": "Seeds",
                    "zh_Hans": "种子"
                  },
                  "llm_description": "Seeds",
                  "max": 4294967294,
                  "min": 0,
                  "name": "seeds",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "16:9",
                  "form": "form",
                  "human_description": {
                    "en_US": "Aspect Ratio",
                    "pt_BR": "Aspect Ratio",
                    "zh_Hans": "长宽比"
                  },
                  "label": {
                    "en_US": "Aspect Ratio",
                    "pt_BR": "Aspect Ratio",
                    "zh_Hans": "长宽比"
                  },
                  "llm_description": "Aspect Ratio",
                  "max": null,
                  "min": null,
                  "name": "aspect_ratio",
                  "options": [
                    {
                      "label": {
                        "en_US": "16:9",
                        "pt_BR": "16:9",
                        "zh_Hans": "16:9"
                      },
                      "value": "16:9"
                    },
                    {
                      "label": {
                        "en_US": "1:1",
                        "pt_BR": "1:1",
                        "zh_Hans": "1:1"
                      },
                      "value": "1:1"
                    },
                    {
                      "label": {
                        "en_US": "21:9",
                        "pt_BR": "21:9",
                        "zh_Hans": "21:9"
                      },
                      "value": "21:9"
                    },
                    {
                      "label": {
                        "en_US": "2:3",
                        "pt_BR": "2:3",
                        "zh_Hans": "2:3"
                      },
                      "value": "2:3"
                    },
                    {
                      "label": {
                        "en_US": "4:5",
                        "pt_BR": "4:5",
                        "zh_Hans": "4:5"
                      },
                      "value": "4:5"
                    },
                    {
                      "label": {
                        "en_US": "5:4",
                        "pt_BR": "5:4",
                        "zh_Hans": "5:4"
                      },
                      "value": "5:4"
                    },
                    {
                      "label": {
                        "en_US": "9:16",
                        "pt_BR": "9:16",
                        "zh_Hans": "9:16"
                      },
                      "value": "9:16"
                    },
                    {
                      "label": {
                        "en_US": "9:21",
                        "pt_BR": "9:21",
                        "zh_Hans": "9:21"
                      },
                      "value": "9:21"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:12:35Z",
        "version_updated_at": "2025-02-17T07:12:35Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Deploy local models using LM Studio",
          "ja_JP": "LM Studio を使用してローカルモデルをデプロイ",
          "zh_Hans": "使用LM Studio部署本地模型"
        },
        "category": "model",
        "created_at": "2025-03-19T02:32:45Z",
        "endpoint": {},
        "icon": "stvlynn/packages/lmstudio/_assets/icon.webp",
        "index_id": "stvlynn___lmstudio",
        "install_count": 4110,
        "introduction": "# LM Studio Plugin for Dify\n\n**Author:** [Steven Lynn](https://github.com/stvlynn)\n\n**Version:** 0.0.1\n\n**Type:** model\n\n**Repository:** https://github.com/stvlynn/lmstudio-Dify-Plugin\n\n---\n\nThis plugin allows you to connect your LM Studio local models to Dify.\n\n## Features\n\n- Support for both Chat and Completion models\n- Support text embedding models\n\n## Setup\n\n### LM Studio\n1. Install [LM Studio](https://lmstudio.ai/) on your computer\n2. Run LM Studio and load a local model\n![](./_assets/lmstudio-server.png)\n3. Configure LM Studio to serve the model via API (in server mode)\n4. Configure the plugin with your LM Studio server URL (default is http://localhost:1234)\n\n### Models\n\n1. Install [LM Studio](https://https://marketplace.dify.ai/plugins/stvlynn/lmstudio) from Dify Marketplace.\n2. Set up models in **Model Provider** -> **LM Studio** -> **Add Model**\n![](./_assets/lmstudio-provider.png)\n3. Add a model.\n![](./_assets/lmstudio-add.png)\n4. If you added an embedding model, apply it in **Model Provider** -> **System Model Setting** -> **embedding Model**\n![](./_assets/embedding.png)\n\n## Requirements\n\n- LM Studio running with at least one model loaded\n- API server mode enabled in LM Studio\n\n## Usage\n\nAfter setting up the plugin, you can use any loaded LM Studio model in your Dify applications by selecting it in the model dropdown.\n\n## License\n\n[MIT](./LICENSE)\n\n\n\n\n\n\n\n\n",
        "label": {
          "en_US": "LM Studio",
          "zh_Hans": "LM Studio"
        },
        "latest_package_identifier": "stvlynn/lmstudio:0.0.2@bb52d30875ae816c8defaf6af82bd2bbd919280a98c51ca174e87298c7b57af7",
        "latest_version": "0.0.2",
        "model": {
          "background": "#F9FAFB",
          "configurate_methods": [
            "customizable-model"
          ],
          "description": {
            "en_US": "Models provided by lmstudio.",
            "ja_JP": "LM Studioが提供するモデル。",
            "zh_Hans": "LM Studio 提供的模型。"
          },
          "help": {
            "title": {
              "en_US": "How to integrate with LM Studio",
              "ja_JP": "LM Studioとの統合方法",
              "zh_Hans": "如何集成 LM Studio"
            },
            "url": {
              "en_US": "https://github.com/stvlynn/lmstudio-Dify-Plugin"
            }
          },
          "icon_large": {
            "en_US": "icon.webp"
          },
          "icon_small": {
            "en_US": "icon.webp"
          },
          "label": {
            "en_US": "LM Studio"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "Base URL",
                  "zh_Hans": "基础 URL"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Base url of LM Studio server, e.g. http://localhost:1234",
                  "ja_JP": "LM Studio サーバーの基本 URL、例: http://localhost:1234",
                  "zh_Hans": "LM Studio server 的基础 URL，例如 http://localhost:1234"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "base_url"
              },
              {
                "default": "chat",
                "label": {
                  "en_US": "Completion mode",
                  "ja_JP": "モデルタイプ",
                  "zh_Hans": "模型类型"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Chat",
                      "ja_JP": "チャット",
                      "zh_Hans": "对话"
                    },
                    "show_on": [],
                    "value": "chat"
                  },
                  {
                    "label": {
                      "en_US": "Completion",
                      "ja_JP": "補完",
                      "zh_Hans": "补全"
                    },
                    "show_on": [],
                    "value": "completion"
                  }
                ],
                "placeholder": {
                  "en_US": "Select completion mode",
                  "ja_JP": "チャットタイプを選択",
                  "zh_Hans": "选择对话类型"
                },
                "required": true,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "select",
                "variable": "mode"
              },
              {
                "default": "4096",
                "label": {
                  "en_US": "Model context size",
                  "ja_JP": "モデルコンテキストサイズ",
                  "zh_Hans": "模型上下文长度"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Model context size",
                  "ja_JP": "モデルコンテキストサイズを入力",
                  "zh_Hans": "在此输入您的模型上下文长度"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "context_size"
              },
              {
                "default": "4096",
                "label": {
                  "en_US": "Upper bound for max tokens",
                  "ja_JP": "最大トークン上限",
                  "zh_Hans": "最大 token 上限"
                },
                "max_length": 0,
                "options": [],
                "placeholder": null,
                "required": true,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "text-input",
                "variable": "max_tokens"
              },
              {
                "default": "1536",
                "label": {
                  "en_US": "Embedding dimensions",
                  "ja_JP": "埋め込み次元",
                  "zh_Hans": "嵌入向量维度"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter the embedding dimensions",
                  "ja_JP": "埋め込み次元を入力",
                  "zh_Hans": "输入嵌入向量维度"
                },
                "required": true,
                "show_on": [
                  {
                    "value": "text-embedding",
                    "variable": "__model_type"
                  }
                ],
                "type": "text-input",
                "variable": "dimensions"
              }
            ],
            "model": {
              "label": {
                "en_US": "Model Name",
                "ja_JP": "モデル名",
                "zh_Hans": "模型名称"
              },
              "placeholder": {
                "en_US": "Enter your model name",
                "ja_JP": "モデル名を入力",
                "zh_Hans": "输入模型名称"
              }
            }
          },
          "models": [
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gpt-3.5-turbo-16k-0613",
                "zh_Hans": "gpt-3.5-turbo-16k-0613"
              },
              "model": "gpt-3.5-turbo-16k-0613",
              "model_properties": {
                "context_size": 16385,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 16385,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.003",
                "output": "0.004",
                "unit": "0.001"
              }
            }
          ],
          "position": {},
          "provider": "lmstudio",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "ja_JP": "API キーを入力",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "openai_api_key"
              }
            ]
          },
          "supported_model_types": [
            "llm",
            "text-embedding"
          ]
        },
        "name": "lmstudio",
        "org": "stvlynn",
        "plugin_id": "stvlynn/lmstudio",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/lmstudio.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": false
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-03-19T02:33:01Z",
        "version_updated_at": "2025-03-19T02:33:01Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "SearchApi is a robust real-time SERP API delivering structured data from a collection of search engines including Google Search, Google Jobs, YouTube, Google News, and many more.",
          "pt_BR": "SearchApi is a robust real-time SERP API delivering structured data from a collection of search engines including Google Search, Google Jobs, YouTube, Google News, and many more.",
          "zh_Hans": "SearchApi 是一个强大的实时 SERP API，可提供来自 Google 搜索、Google 招聘、YouTube、Google 新闻等搜索引擎集合的结构化数据。"
        },
        "category": "tool",
        "created_at": "2024-11-29T10:06:31Z",
        "endpoint": {},
        "icon": "langgenius/packages/searchapi/_assets/icon.svg",
        "index_id": "langgenius___searchapi",
        "install_count": 3838,
        "introduction": "# SearchApi\n\n## Overview\n\nSearchApi is a powerful real-time SERP API that provides structured data from a collection of search engines including Google Search, Google Jobs, YouTube, Google News, and more. Here are the steps to configure and use the SearchApi search tool in Dify.\n\n## Configuration\n\n### 1. Apply for an API Key\n\nApply for an API Key at [SearchApi](https://www.searchapi.io/).\n\n### 2. Get SearchApi tools from Plugin Marketplace\n\nThe SearchApi tools could be found at the Plugin Marketplace, please install it.\n\n### 3. Fill in the configuration in Dify\n\nOn the Dify navigation page, go to `Tools > SearchApi > Authentication` to fill in the API Key.\n\n![](./_assets/SearchApi_1.PNG)\n\n### 4. Using the tool\n\nYou can use the SearchApi tool in the following application types.\n\n![](./_assets/SearchApi_2.PNG)\n\n#### Chatflow / Workflow applications\n\nBoth Chatflow and Workflow applications support adding SearchApi series tool nodes, providing four tools: Google Jobs API, Google News API, Google Search API, and YouTube Scraper API.\n\n#### Agent applications\n\nSelect the SearchApi tool you need to add in the Agent application, then enter commands to call the tool.",
        "label": {
          "en_US": "SearchApi",
          "pt_BR": "SearchApi",
          "zh_Hans": "SearchApi"
        },
        "latest_package_identifier": "langgenius/searchapi:0.0.2@665b4d71daa29fb015035b4affde2d97c6047209ee1a310420e9d118974551f8",
        "latest_version": "0.0.2",
        "model": {},
        "name": "searchapi",
        "org": "langgenius",
        "plugin_id": "langgenius/searchapi",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/searchapi.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "search"
          },
          {
            "name": "business"
          },
          {
            "name": "news"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "SearchApi API key",
                "pt_BR": "SearchApi API key",
                "zh_Hans": "SearchApi API key"
              },
              "name": "searchapi_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your SearchApi API key",
                "pt_BR": "Please input your SearchApi API key",
                "zh_Hans": "请输入你的 SearchApi API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://www.searchapi.io/"
            }
          ],
          "identity": {
            "author": "SearchApi",
            "description": {
              "en_US": "SearchApi is a robust real-time SERP API delivering structured data from a collection of search engines including Google Search, Google Jobs, YouTube, Google News, and many more.",
              "pt_BR": "SearchApi is a robust real-time SERP API delivering structured data from a collection of search engines including Google Search, Google Jobs, YouTube, Google News, and many more.",
              "zh_Hans": "SearchApi 是一个强大的实时 SERP API，可提供来自 Google 搜索、Google 招聘、YouTube、Google 新闻等搜索引擎集合的结构化数据。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "SearchApi",
              "pt_BR": "SearchApi",
              "zh_Hans": "SearchApi"
            },
            "name": "searchapi",
            "tags": [
              "search",
              "business",
              "news",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool to retrieve job titles, company names and description from Google Jobs engine.",
                  "zh_Hans": "一个从 Google 招聘引擎检索职位名称、公司名称和描述的工具。"
                },
                "llm": "A tool to retrieve job titles, company names and description from Google Jobs engine."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "SearchApi",
                "label": {
                  "en_US": "Google Jobs API",
                  "zh_Hans": "Google Jobs API"
                },
                "name": "google_jobs_api"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Defines the query you want to search.",
                    "zh_Hans": "定义您要搜索的查询。"
                  },
                  "label": {
                    "en_US": "Query",
                    "zh_Hans": "询问"
                  },
                  "llm_description": "Defines the search query you want to search.",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "text",
                  "form": "form",
                  "human_description": {
                    "en_US": "used for selecting the result type, text or link",
                    "zh_Hans": "用于选择结果类型，使用文本还是链接进行展示"
                  },
                  "label": {
                    "en_US": "Result type",
                    "zh_Hans": "结果类型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "result_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "text",
                        "zh_Hans": "文本"
                      },
                      "value": "text"
                    },
                    {
                      "label": {
                        "en_US": "link",
                        "zh_Hans": "链接"
                      },
                      "value": "link"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Defines from where you want the search to originate. (For example - New York)",
                    "zh_Hans": "定义您想要搜索的起始位置。 （例如 - 纽约）"
                  },
                  "label": {
                    "en_US": "Location",
                    "zh_Hans": "询问"
                  },
                  "llm_description": "Defines from where you want the search to originate. (For example - New York)",
                  "max": null,
                  "min": null,
                  "name": "location",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "US",
                  "form": "form",
                  "human_description": {
                    "en_US": "Defines the country of the search. Default is \"US\".",
                    "zh_Hans": "定义搜索的国家/地区。默认为“美国”。"
                  },
                  "label": {
                    "en_US": "Country",
                    "zh_Hans": "国家"
                  },
                  "llm_description": "Defines the gl parameter of the Google search.",
                  "max": null,
                  "min": null,
                  "name": "gl",
                  "options": [
                    {
                      "label": {
                        "en_US": "Algeria",
                        "pt_BR": "Algeria",
                        "zh_Hans": "阿尔及利亚"
                      },
                      "value": "DZ"
                    },
                    {
                      "label": {
                        "en_US": "American Samoa",
                        "pt_BR": "American Samoa",
                        "zh_Hans": "美属萨摩亚"
                      },
                      "value": "AS"
                    },
                    {
                      "label": {
                        "en_US": "Angola",
                        "pt_BR": "Angola",
                        "zh_Hans": "安哥拉"
                      },
                      "value": "AO"
                    },
                    {
                      "label": {
                        "en_US": "Anguilla",
                        "pt_BR": "Anguilla",
                        "zh_Hans": "安圭拉"
                      },
                      "value": "AI"
                    },
                    {
                      "label": {
                        "en_US": "Antigua and Barbuda",
                        "pt_BR": "Antigua and Barbuda",
                        "zh_Hans": "安提瓜和巴布达"
                      },
                      "value": "AG"
                    },
                    {
                      "label": {
                        "en_US": "Aruba",
                        "pt_BR": "Aruba",
                        "zh_Hans": "阿鲁巴"
                      },
                      "value": "AW"
                    },
                    {
                      "label": {
                        "en_US": "Austria",
                        "pt_BR": "Austria",
                        "zh_Hans": "奥地利"
                      },
                      "value": "AT"
                    },
                    {
                      "label": {
                        "en_US": "Bahamas",
                        "pt_BR": "Bahamas",
                        "zh_Hans": "巴哈马"
                      },
                      "value": "BS"
                    },
                    {
                      "label": {
                        "en_US": "Bahrain",
                        "pt_BR": "Bahrain",
                        "zh_Hans": "巴林"
                      },
                      "value": "BH"
                    },
                    {
                      "label": {
                        "en_US": "Bangladesh",
                        "pt_BR": "Bangladesh",
                        "zh_Hans": "孟加拉国"
                      },
                      "value": "BD"
                    },
                    {
                      "label": {
                        "en_US": "Belarus",
                        "pt_BR": "Belarus",
                        "zh_Hans": "白俄罗斯"
                      },
                      "value": "BY"
                    },
                    {
                      "label": {
                        "en_US": "Belgium",
                        "pt_BR": "Belgium",
                        "zh_Hans": "比利时"
                      },
                      "value": "BE"
                    },
                    {
                      "label": {
                        "en_US": "Belize",
                        "pt_BR": "Belize",
                        "zh_Hans": "伯利兹"
                      },
                      "value": "BZ"
                    },
                    {
                      "label": {
                        "en_US": "Benin",
                        "pt_BR": "Benin",
                        "zh_Hans": "贝宁"
                      },
                      "value": "BJ"
                    },
                    {
                      "label": {
                        "en_US": "Bermuda",
                        "pt_BR": "Bermuda",
                        "zh_Hans": "百慕大"
                      },
                      "value": "BM"
                    },
                    {
                      "label": {
                        "en_US": "Bolivia",
                        "pt_BR": "Bolivia",
                        "zh_Hans": "玻利维亚"
                      },
                      "value": "BO"
                    },
                    {
                      "label": {
                        "en_US": "Botswana",
                        "pt_BR": "Botswana",
                        "zh_Hans": "博茨瓦纳"
                      },
                      "value": "BW"
                    },
                    {
                      "label": {
                        "en_US": "Brazil",
                        "pt_BR": "Brazil",
                        "zh_Hans": "巴西"
                      },
                      "value": "BR"
                    },
                    {
                      "label": {
                        "en_US": "British Indian Ocean Territory",
                        "pt_BR": "British Indian Ocean Territory",
                        "zh_Hans": "英属印度洋领地"
                      },
                      "value": "IO"
                    },
                    {
                      "label": {
                        "en_US": "Burkina Faso",
                        "pt_BR": "Burkina Faso",
                        "zh_Hans": "布基纳法索"
                      },
                      "value": "BF"
                    },
                    {
                      "label": {
                        "en_US": "Burundi",
                        "pt_BR": "Burundi",
                        "zh_Hans": "布隆迪"
                      },
                      "value": "BI"
                    },
                    {
                      "label": {
                        "en_US": "Cameroon",
                        "pt_BR": "Cameroon",
                        "zh_Hans": "喀麦隆"
                      },
                      "value": "CM"
                    },
                    {
                      "label": {
                        "en_US": "Canada",
                        "pt_BR": "Canada",
                        "zh_Hans": "加拿大"
                      },
                      "value": "CA"
                    },
                    {
                      "label": {
                        "en_US": "Cape Verde",
                        "pt_BR": "Cape Verde",
                        "zh_Hans": "佛得角"
                      },
                      "value": "CV"
                    },
                    {
                      "label": {
                        "en_US": "Cayman Islands",
                        "pt_BR": "Cayman Islands",
                        "zh_Hans": "开曼群岛"
                      },
                      "value": "KY"
                    },
                    {
                      "label": {
                        "en_US": "Central African Republic",
                        "pt_BR": "Central African Republic",
                        "zh_Hans": "中非共和国"
                      },
                      "value": "CF"
                    },
                    {
                      "label": {
                        "en_US": "Chad",
                        "pt_BR": "Chad",
                        "zh_Hans": "乍得"
                      },
                      "value": "TD"
                    },
                    {
                      "label": {
                        "en_US": "Chile",
                        "pt_BR": "Chile",
                        "zh_Hans": "智利"
                      },
                      "value": "CL"
                    },
                    {
                      "label": {
                        "en_US": "Colombia",
                        "pt_BR": "Colombia",
                        "zh_Hans": "哥伦比亚"
                      },
                      "value": "CO"
                    },
                    {
                      "label": {
                        "en_US": "Congo, the Democratic Republic of the",
                        "pt_BR": "Congo, the Democratic Republic of the",
                        "zh_Hans": "刚果民主共和国"
                      },
                      "value": "CD"
                    },
                    {
                      "label": {
                        "en_US": "Costa Rica",
                        "pt_BR": "Costa Rica",
                        "zh_Hans": "哥斯达黎加"
                      },
                      "value": "CR"
                    },
                    {
                      "label": {
                        "en_US": "Cote D'ivoire",
                        "pt_BR": "Cote D'ivoire",
                        "zh_Hans": "科特迪瓦"
                      },
                      "value": "CI"
                    },
                    {
                      "label": {
                        "en_US": "Cuba",
                        "pt_BR": "Cuba",
                        "zh_Hans": "古巴"
                      },
                      "value": "CU"
                    },
                    {
                      "label": {
                        "en_US": "Denmark",
                        "pt_BR": "Denmark",
                        "zh_Hans": "丹麦"
                      },
                      "value": "DK"
                    },
                    {
                      "label": {
                        "en_US": "Djibouti",
                        "pt_BR": "Djibouti",
                        "zh_Hans": "吉布提"
                      },
                      "value": "DJ"
                    },
                    {
                      "label": {
                        "en_US": "Dominica",
                        "pt_BR": "Dominica",
                        "zh_Hans": "多米尼克"
                      },
                      "value": "DM"
                    },
                    {
                      "label": {
                        "en_US": "Dominican Republic",
                        "pt_BR": "Dominican Republic",
                        "zh_Hans": "多米尼加共和国"
                      },
                      "value": "DO"
                    },
                    {
                      "label": {
                        "en_US": "Ecuador",
                        "pt_BR": "Ecuador",
                        "zh_Hans": "厄瓜多尔"
                      },
                      "value": "EC"
                    },
                    {
                      "label": {
                        "en_US": "Egypt",
                        "pt_BR": "Egypt",
                        "zh_Hans": "埃及"
                      },
                      "value": "EG"
                    },
                    {
                      "label": {
                        "en_US": "El Salvador",
                        "pt_BR": "El Salvador",
                        "zh_Hans": "萨尔瓦多"
                      },
                      "value": "SV"
                    },
                    {
                      "label": {
                        "en_US": "Ethiopia",
                        "pt_BR": "Ethiopia",
                        "zh_Hans": "埃塞俄比亚"
                      },
                      "value": "ET"
                    },
                    {
                      "label": {
                        "en_US": "Falkland Islands (Malvinas)",
                        "pt_BR": "Falkland Islands (Malvinas)",
                        "zh_Hans": "福克兰群岛（马尔维纳斯）"
                      },
                      "value": "FK"
                    },
                    {
                      "label": {
                        "en_US": "France",
                        "pt_BR": "France",
                        "zh_Hans": "法国"
                      },
                      "value": "FR"
                    },
                    {
                      "label": {
                        "en_US": "French Guiana",
                        "pt_BR": "French Guiana",
                        "zh_Hans": "法属圭亚那"
                      },
                      "value": "GF"
                    },
                    {
                      "label": {
                        "en_US": "French Polynesia",
                        "pt_BR": "French Polynesia",
                        "zh_Hans": "法属波利尼西亚"
                      },
                      "value": "PF"
                    },
                    {
                      "label": {
                        "en_US": "French Southern Territories",
                        "pt_BR": "French Southern Territories",
                        "zh_Hans": "法属南部领地"
                      },
                      "value": "TF"
                    },
                    {
                      "label": {
                        "en_US": "Gabon",
                        "pt_BR": "Gabon",
                        "zh_Hans": "加蓬"
                      },
                      "value": "GA"
                    },
                    {
                      "label": {
                        "en_US": "Gambia",
                        "pt_BR": "Gambia",
                        "zh_Hans": "冈比亚"
                      },
                      "value": "GM"
                    },
                    {
                      "label": {
                        "en_US": "Germany",
                        "pt_BR": "Germany",
                        "zh_Hans": "德国"
                      },
                      "value": "DE"
                    },
                    {
                      "label": {
                        "en_US": "Ghana",
                        "pt_BR": "Ghana",
                        "zh_Hans": "加纳"
                      },
                      "value": "GH"
                    },
                    {
                      "label": {
                        "en_US": "Greece",
                        "pt_BR": "Greece",
                        "zh_Hans": "希腊"
                      },
                      "value": "GR"
                    },
                    {
                      "label": {
                        "en_US": "Guadeloupe",
                        "pt_BR": "Guadeloupe",
                        "zh_Hans": "瓜德罗普"
                      },
                      "value": "GP"
                    },
                    {
                      "label": {
                        "en_US": "Guatemala",
                        "pt_BR": "Guatemala",
                        "zh_Hans": "危地马拉"
                      },
                      "value": "GT"
                    },
                    {
                      "label": {
                        "en_US": "Guyana",
                        "pt_BR": "Guyana",
                        "zh_Hans": "圭亚那"
                      },
                      "value": "GY"
                    },
                    {
                      "label": {
                        "en_US": "Haiti",
                        "pt_BR": "Haiti",
                        "zh_Hans": "海地"
                      },
                      "value": "HT"
                    },
                    {
                      "label": {
                        "en_US": "Honduras",
                        "pt_BR": "Honduras",
                        "zh_Hans": "洪都拉斯"
                      },
                      "value": "HN"
                    },
                    {
                      "label": {
                        "en_US": "Hong Kong",
                        "pt_BR": "Hong Kong",
                        "zh_Hans": "香港"
                      },
                      "value": "HK"
                    },
                    {
                      "label": {
                        "en_US": "India",
                        "pt_BR": "India",
                        "zh_Hans": "印度"
                      },
                      "value": "IN"
                    },
                    {
                      "label": {
                        "en_US": "Indonesia",
                        "pt_BR": "Indonesia",
                        "zh_Hans": "印度尼西亚"
                      },
                      "value": "ID"
                    },
                    {
                      "label": {
                        "en_US": "Iraq",
                        "pt_BR": "Iraq",
                        "zh_Hans": "伊拉克"
                      },
                      "value": "IQ"
                    },
                    {
                      "label": {
                        "en_US": "Italy",
                        "pt_BR": "Italy",
                        "zh_Hans": "意大利"
                      },
                      "value": "IT"
                    },
                    {
                      "label": {
                        "en_US": "Jamaica",
                        "pt_BR": "Jamaica",
                        "zh_Hans": "牙买加"
                      },
                      "value": "JM"
                    },
                    {
                      "label": {
                        "en_US": "Japan",
                        "pt_BR": "Japan",
                        "zh_Hans": "日本"
                      },
                      "value": "JP"
                    },
                    {
                      "label": {
                        "en_US": "Jordan",
                        "pt_BR": "Jordan",
                        "zh_Hans": "约旦"
                      },
                      "value": "JO"
                    },
                    {
                      "label": {
                        "en_US": "Kazakhstan",
                        "pt_BR": "Kazakhstan",
                        "zh_Hans": "哈萨克斯坦"
                      },
                      "value": "KZ"
                    },
                    {
                      "label": {
                        "en_US": "Kenya",
                        "pt_BR": "Kenya",
                        "zh_Hans": "肯尼亚"
                      },
                      "value": "KE"
                    },
                    {
                      "label": {
                        "en_US": "Kuwait",
                        "pt_BR": "Kuwait",
                        "zh_Hans": "科威特"
                      },
                      "value": "KW"
                    },
                    {
                      "label": {
                        "en_US": "Kyrgyzstan",
                        "pt_BR": "Kyrgyzstan",
                        "zh_Hans": "吉尔吉斯斯坦"
                      },
                      "value": "KG"
                    },
                    {
                      "label": {
                        "en_US": "Lebanon",
                        "pt_BR": "Lebanon",
                        "zh_Hans": "黎巴嫩"
                      },
                      "value": "LB"
                    },
                    {
                      "label": {
                        "en_US": "Lesotho",
                        "pt_BR": "Lesotho",
                        "zh_Hans": "莱索托"
                      },
                      "value": "LS"
                    },
                    {
                      "label": {
                        "en_US": "Libyan Arab Jamahiriya",
                        "pt_BR": "Libyan Arab Jamahiriya",
                        "zh_Hans": "利比亚"
                      },
                      "value": "LY"
                    },
                    {
                      "label": {
                        "en_US": "Madagascar",
                        "pt_BR": "Madagascar",
                        "zh_Hans": "马达加斯加"
                      },
                      "value": "MG"
                    },
                    {
                      "label": {
                        "en_US": "Malawi",
                        "pt_BR": "Malawi",
                        "zh_Hans": "马拉维"
                      },
                      "value": "MW"
                    },
                    {
                      "label": {
                        "en_US": "Malaysia",
                        "pt_BR": "Malaysia",
                        "zh_Hans": "马来西亚"
                      },
                      "value": "MY"
                    },
                    {
                      "label": {
                        "en_US": "Mali",
                        "pt_BR": "Mali",
                        "zh_Hans": "马里"
                      },
                      "value": "ML"
                    },
                    {
                      "label": {
                        "en_US": "Martinique",
                        "pt_BR": "Martinique",
                        "zh_Hans": "马提尼克"
                      },
                      "value": "MQ"
                    },
                    {
                      "label": {
                        "en_US": "Mauritius",
                        "pt_BR": "Mauritius",
                        "zh_Hans": "毛里求斯"
                      },
                      "value": "MU"
                    },
                    {
                      "label": {
                        "en_US": "Mayotte",
                        "pt_BR": "Mayotte",
                        "zh_Hans": "马约特"
                      },
                      "value": "YT"
                    },
                    {
                      "label": {
                        "en_US": "Mexico",
                        "pt_BR": "Mexico",
                        "zh_Hans": "墨西哥"
                      },
                      "value": "MX"
                    },
                    {
                      "label": {
                        "en_US": "Montserrat",
                        "pt_BR": "Montserrat",
                        "zh_Hans": "蒙特塞拉特"
                      },
                      "value": "MS"
                    },
                    {
                      "label": {
                        "en_US": "Morocco",
                        "pt_BR": "Morocco",
                        "zh_Hans": "摩洛哥"
                      },
                      "value": "MA"
                    },
                    {
                      "label": {
                        "en_US": "Mozambique",
                        "pt_BR": "Mozambique",
                        "zh_Hans": "莫桑比克"
                      },
                      "value": "MZ"
                    },
                    {
                      "label": {
                        "en_US": "Namibia",
                        "pt_BR": "Namibia",
                        "zh_Hans": "纳米比亚"
                      },
                      "value": "NA"
                    },
                    {
                      "label": {
                        "en_US": "Netherlands",
                        "pt_BR": "Netherlands",
                        "zh_Hans": "荷兰"
                      },
                      "value": "NL"
                    },
                    {
                      "label": {
                        "en_US": "New Caledonia",
                        "pt_BR": "New Caledonia",
                        "zh_Hans": "新喀里多尼亚"
                      },
                      "value": "NC"
                    },
                    {
                      "label": {
                        "en_US": "Nicaragua",
                        "pt_BR": "Nicaragua",
                        "zh_Hans": "尼加拉瓜"
                      },
                      "value": "NI"
                    },
                    {
                      "label": {
                        "en_US": "Niger",
                        "pt_BR": "Niger",
                        "zh_Hans": "尼日尔"
                      },
                      "value": "NE"
                    },
                    {
                      "label": {
                        "en_US": "Nigeria",
                        "pt_BR": "Nigeria",
                        "zh_Hans": "尼日利亚"
                      },
                      "value": "NG"
                    },
                    {
                      "label": {
                        "en_US": "Oman",
                        "pt_BR": "Oman",
                        "zh_Hans": "阿曼"
                      },
                      "value": "OM"
                    },
                    {
                      "label": {
                        "en_US": "Pakistan",
                        "pt_BR": "Pakistan",
                        "zh_Hans": "巴基斯坦"
                      },
                      "value": "PK"
                    },
                    {
                      "label": {
                        "en_US": "Palestinian Territory, Occupied",
                        "pt_BR": "Palestinian Territory, Occupied",
                        "zh_Hans": "巴勒斯坦领土"
                      },
                      "value": "PS"
                    },
                    {
                      "label": {
                        "en_US": "Panama",
                        "pt_BR": "Panama",
                        "zh_Hans": "巴拿马"
                      },
                      "value": "PA"
                    },
                    {
                      "label": {
                        "en_US": "Paraguay",
                        "pt_BR": "Paraguay",
                        "zh_Hans": "巴拉圭"
                      },
                      "value": "PY"
                    },
                    {
                      "label": {
                        "en_US": "Peru",
                        "pt_BR": "Peru",
                        "zh_Hans": "秘鲁"
                      },
                      "value": "PE"
                    },
                    {
                      "label": {
                        "en_US": "Philippines",
                        "pt_BR": "Philippines",
                        "zh_Hans": "菲律宾"
                      },
                      "value": "PH"
                    },
                    {
                      "label": {
                        "en_US": "Portugal",
                        "pt_BR": "Portugal",
                        "zh_Hans": "葡萄牙"
                      },
                      "value": "PT"
                    },
                    {
                      "label": {
                        "en_US": "Puerto Rico",
                        "pt_BR": "Puerto Rico",
                        "zh_Hans": "波多黎各"
                      },
                      "value": "PR"
                    },
                    {
                      "label": {
                        "en_US": "Qatar",
                        "pt_BR": "Qatar",
                        "zh_Hans": "卡塔尔"
                      },
                      "value": "QA"
                    },
                    {
                      "label": {
                        "en_US": "Reunion",
                        "pt_BR": "Reunion",
                        "zh_Hans": "留尼旺"
                      },
                      "value": "RE"
                    },
                    {
                      "label": {
                        "en_US": "Russian Federation",
                        "pt_BR": "Russian Federation",
                        "zh_Hans": "俄罗斯联邦"
                      },
                      "value": "RU"
                    },
                    {
                      "label": {
                        "en_US": "Rwanda",
                        "pt_BR": "Rwanda",
                        "zh_Hans": "卢旺达"
                      },
                      "value": "RW"
                    },
                    {
                      "label": {
                        "en_US": "Saint Helena",
                        "pt_BR": "Saint Helena",
                        "zh_Hans": "圣赫勒拿"
                      },
                      "value": "SH"
                    },
                    {
                      "label": {
                        "en_US": "Saint Pierre and Miquelon",
                        "pt_BR": "Saint Pierre and Miquelon",
                        "zh_Hans": "圣皮埃尔和密克隆"
                      },
                      "value": "PM"
                    },
                    {
                      "label": {
                        "en_US": "Saint Vincent and the Grenadines",
                        "pt_BR": "Saint Vincent and the Grenadines",
                        "zh_Hans": "圣文森特和格林纳丁斯"
                      },
                      "value": "VC"
                    },
                    {
                      "label": {
                        "en_US": "Sao Tome and Principe",
                        "pt_BR": "Sao Tome and Principe",
                        "zh_Hans": "圣多美和普林西比"
                      },
                      "value": "ST"
                    },
                    {
                      "label": {
                        "en_US": "Saudi Arabia",
                        "pt_BR": "Saudi Arabia",
                        "zh_Hans": "沙特阿拉伯"
                      },
                      "value": "SA"
                    },
                    {
                      "label": {
                        "en_US": "Senegal",
                        "pt_BR": "Senegal",
                        "zh_Hans": "塞内加尔"
                      },
                      "value": "SN"
                    },
                    {
                      "label": {
                        "en_US": "Seychelles",
                        "pt_BR": "Seychelles",
                        "zh_Hans": "塞舌尔"
                      },
                      "value": "SC"
                    },
                    {
                      "label": {
                        "en_US": "Sierra Leone",
                        "pt_BR": "Sierra Leone",
                        "zh_Hans": "塞拉利昂"
                      },
                      "value": "SL"
                    },
                    {
                      "label": {
                        "en_US": "Singapore",
                        "pt_BR": "Singapore",
                        "zh_Hans": "新加坡"
                      },
                      "value": "SG"
                    },
                    {
                      "label": {
                        "en_US": "Somalia",
                        "pt_BR": "Somalia",
                        "zh_Hans": "索马里"
                      },
                      "value": "SO"
                    },
                    {
                      "label": {
                        "en_US": "South Africa",
                        "pt_BR": "South Africa",
                        "zh_Hans": "南非"
                      },
                      "value": "ZA"
                    },
                    {
                      "label": {
                        "en_US": "South Georgia and the South Sandwich Islands",
                        "pt_BR": "South Georgia and the South Sandwich Islands",
                        "zh_Hans": "南乔治亚和南桑威奇群岛"
                      },
                      "value": "GS"
                    },
                    {
                      "label": {
                        "en_US": "Spain",
                        "pt_BR": "Spain",
                        "zh_Hans": "西班牙"
                      },
                      "value": "ES"
                    },
                    {
                      "label": {
                        "en_US": "Sri Lanka",
                        "pt_BR": "Sri Lanka",
                        "zh_Hans": "斯里兰卡"
                      },
                      "value": "LK"
                    },
                    {
                      "label": {
                        "en_US": "Suriname",
                        "pt_BR": "Suriname",
                        "zh_Hans": "苏里南"
                      },
                      "value": "SR"
                    },
                    {
                      "label": {
                        "en_US": "Switzerland",
                        "pt_BR": "Switzerland",
                        "zh_Hans": "瑞士"
                      },
                      "value": "CH"
                    },
                    {
                      "label": {
                        "en_US": "Taiwan, Province of China",
                        "pt_BR": "Taiwan, Province of China",
                        "zh_Hans": "中国台湾省"
                      },
                      "value": "TW"
                    },
                    {
                      "label": {
                        "en_US": "Tanzania, United Republic of",
                        "pt_BR": "Tanzania, United Republic of",
                        "zh_Hans": "坦桑尼亚联合共和国"
                      },
                      "value": "TZ"
                    },
                    {
                      "label": {
                        "en_US": "Thailand",
                        "pt_BR": "Thailand",
                        "zh_Hans": "泰国"
                      },
                      "value": "TH"
                    },
                    {
                      "label": {
                        "en_US": "Togo",
                        "pt_BR": "Togo",
                        "zh_Hans": "多哥"
                      },
                      "value": "TG"
                    },
                    {
                      "label": {
                        "en_US": "Trinidad and Tobago",
                        "pt_BR": "Trinidad and Tobago",
                        "zh_Hans": "特立尼达和多巴哥"
                      },
                      "value": "TT"
                    },
                    {
                      "label": {
                        "en_US": "Tunisia",
                        "pt_BR": "Tunisia",
                        "zh_Hans": "突尼斯"
                      },
                      "value": "TN"
                    },
                    {
                      "label": {
                        "en_US": "Turks and Caicos Islands",
                        "pt_BR": "Turks and Caicos Islands",
                        "zh_Hans": "特克斯和凯科斯群岛"
                      },
                      "value": "TC"
                    },
                    {
                      "label": {
                        "en_US": "Uganda",
                        "pt_BR": "Uganda",
                        "zh_Hans": "乌干达"
                      },
                      "value": "UG"
                    },
                    {
                      "label": {
                        "en_US": "United Arab Emirates",
                        "pt_BR": "United Arab Emirates",
                        "zh_Hans": "阿联酋"
                      },
                      "value": "AE"
                    },
                    {
                      "label": {
                        "en_US": "United Kingdom",
                        "pt_BR": "United Kingdom",
                        "zh_Hans": "英国"
                      },
                      "value": "UK"
                    },
                    {
                      "label": {
                        "en_US": "United Kingdom",
                        "pt_BR": "United Kingdom",
                        "zh_Hans": "英国"
                      },
                      "value": "GB"
                    },
                    {
                      "label": {
                        "en_US": "United States",
                        "pt_BR": "United States",
                        "zh_Hans": "美国"
                      },
                      "value": "US"
                    },
                    {
                      "label": {
                        "en_US": "Uruguay",
                        "pt_BR": "Uruguay",
                        "zh_Hans": "乌拉圭"
                      },
                      "value": "UY"
                    },
                    {
                      "label": {
                        "en_US": "Uzbekistan",
                        "pt_BR": "Uzbekistan",
                        "zh_Hans": "乌兹别克斯坦"
                      },
                      "value": "UZ"
                    },
                    {
                      "label": {
                        "en_US": "Venezuela",
                        "pt_BR": "Venezuela",
                        "zh_Hans": "委内瑞拉"
                      },
                      "value": "VE"
                    },
                    {
                      "label": {
                        "en_US": "Viet Nam",
                        "pt_BR": "Viet Nam",
                        "zh_Hans": "越南"
                      },
                      "value": "VN"
                    },
                    {
                      "label": {
                        "en_US": "Virgin Islands, British",
                        "pt_BR": "Virgin Islands, British",
                        "zh_Hans": "英属维尔京群岛"
                      },
                      "value": "VG"
                    },
                    {
                      "label": {
                        "en_US": "Virgin Islands, U.S.",
                        "pt_BR": "Virgin Islands, U.S.",
                        "zh_Hans": "美属维尔京群岛"
                      },
                      "value": "VI"
                    },
                    {
                      "label": {
                        "en_US": "Zambia",
                        "pt_BR": "Zambia",
                        "zh_Hans": "赞比亚"
                      },
                      "value": "ZM"
                    },
                    {
                      "label": {
                        "en_US": "Zimbabwe",
                        "pt_BR": "Zimbabwe",
                        "zh_Hans": "津巴布韦"
                      },
                      "value": "ZW"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "en",
                  "form": "form",
                  "human_description": {
                    "en_US": "Defines the interface language of the search. Default is \"en\".",
                    "zh_Hans": "定义搜索的界面语言。默认为“en”。"
                  },
                  "label": {
                    "en_US": "Language",
                    "zh_Hans": "语言"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "hl",
                  "options": [
                    {
                      "label": {
                        "en_US": "Afrikaans",
                        "zh_Hans": "南非语"
                      },
                      "value": "af"
                    },
                    {
                      "label": {
                        "en_US": "Akan",
                        "zh_Hans": "阿坎语"
                      },
                      "value": "ak"
                    },
                    {
                      "label": {
                        "en_US": "Albanian",
                        "zh_Hans": "阿尔巴尼亚语"
                      },
                      "value": "sq"
                    },
                    {
                      "label": {
                        "en_US": "Samoa",
                        "zh_Hans": "萨摩亚语"
                      },
                      "value": "ws"
                    },
                    {
                      "label": {
                        "en_US": "Amharic",
                        "zh_Hans": "阿姆哈拉语"
                      },
                      "value": "am"
                    },
                    {
                      "label": {
                        "en_US": "Arabic",
                        "zh_Hans": "阿拉伯语"
                      },
                      "value": "ar"
                    },
                    {
                      "label": {
                        "en_US": "Armenian",
                        "zh_Hans": "亚美尼亚语"
                      },
                      "value": "hy"
                    },
                    {
                      "label": {
                        "en_US": "Azerbaijani",
                        "zh_Hans": "阿塞拜疆语"
                      },
                      "value": "az"
                    },
                    {
                      "label": {
                        "en_US": "Basque",
                        "zh_Hans": "巴斯克语"
                      },
                      "value": "eu"
                    },
                    {
                      "label": {
                        "en_US": "Belarusian",
                        "zh_Hans": "白俄罗斯语"
                      },
                      "value": "be"
                    },
                    {
                      "label": {
                        "en_US": "Bemba",
                        "zh_Hans": "班巴语"
                      },
                      "value": "bem"
                    },
                    {
                      "label": {
                        "en_US": "Bengali",
                        "zh_Hans": "孟加拉语"
                      },
                      "value": "bn"
                    },
                    {
                      "label": {
                        "en_US": "Bihari",
                        "zh_Hans": "比哈尔语"
                      },
                      "value": "bh"
                    },
                    {
                      "label": {
                        "en_US": "Bork, bork, bork!",
                        "zh_Hans": "博克语"
                      },
                      "value": "xx-bork"
                    },
                    {
                      "label": {
                        "en_US": "Bosnian",
                        "zh_Hans": "波斯尼亚语"
                      },
                      "value": "bs"
                    },
                    {
                      "label": {
                        "en_US": "Breton",
                        "zh_Hans": "布列塔尼语"
                      },
                      "value": "br"
                    },
                    {
                      "label": {
                        "en_US": "Bulgarian",
                        "zh_Hans": "保加利亚语"
                      },
                      "value": "bg"
                    },
                    {
                      "label": {
                        "en_US": "Bhutanese",
                        "zh_Hans": "不丹语"
                      },
                      "value": "bt"
                    },
                    {
                      "label": {
                        "en_US": "Cambodian",
                        "zh_Hans": "高棉语"
                      },
                      "value": "km"
                    },
                    {
                      "label": {
                        "en_US": "Catalan",
                        "zh_Hans": "加泰罗尼亚语"
                      },
                      "value": "ca"
                    },
                    {
                      "label": {
                        "en_US": "Cherokee",
                        "zh_Hans": "切罗基语"
                      },
                      "value": "chr"
                    },
                    {
                      "label": {
                        "en_US": "Chichewa",
                        "zh_Hans": "齐切瓦语"
                      },
                      "value": "ny"
                    },
                    {
                      "label": {
                        "en_US": "Chinese (Simplified)",
                        "zh_Hans": "中文（简体）"
                      },
                      "value": "zh-cn"
                    },
                    {
                      "label": {
                        "en_US": "Chinese (Traditional)",
                        "zh_Hans": "中文（繁体）"
                      },
                      "value": "zh-tw"
                    },
                    {
                      "label": {
                        "en_US": "Corsican",
                        "zh_Hans": "科西嘉语"
                      },
                      "value": "co"
                    },
                    {
                      "label": {
                        "en_US": "Croatian",
                        "zh_Hans": "克罗地亚语"
                      },
                      "value": "hr"
                    },
                    {
                      "label": {
                        "en_US": "Czech",
                        "zh_Hans": "捷克语"
                      },
                      "value": "cs"
                    },
                    {
                      "label": {
                        "en_US": "Danish",
                        "zh_Hans": "丹麦语"
                      },
                      "value": "da"
                    },
                    {
                      "label": {
                        "en_US": "Dutch",
                        "zh_Hans": "荷兰语"
                      },
                      "value": "nl"
                    },
                    {
                      "label": {
                        "en_US": "Elmer Fudd",
                        "zh_Hans": "艾尔默福德语"
                      },
                      "value": "xx-elmer"
                    },
                    {
                      "label": {
                        "en_US": "English",
                        "zh_Hans": "英语"
                      },
                      "value": "en"
                    },
                    {
                      "label": {
                        "en_US": "Esperanto",
                        "zh_Hans": "世界语"
                      },
                      "value": "eo"
                    },
                    {
                      "label": {
                        "en_US": "Estonian",
                        "zh_Hans": "爱沙尼亚语"
                      },
                      "value": "et"
                    },
                    {
                      "label": {
                        "en_US": "Ewe",
                        "zh_Hans": "埃维语"
                      },
                      "value": "ee"
                    },
                    {
                      "label": {
                        "en_US": "Faroese",
                        "zh_Hans": "法罗语"
                      },
                      "value": "fo"
                    },
                    {
                      "label": {
                        "en_US": "Filipino",
                        "zh_Hans": "菲律宾语"
                      },
                      "value": "tl"
                    },
                    {
                      "label": {
                        "en_US": "Finnish",
                        "zh_Hans": "芬兰语"
                      },
                      "value": "fi"
                    },
                    {
                      "label": {
                        "en_US": "French",
                        "zh_Hans": "法语"
                      },
                      "value": "fr"
                    },
                    {
                      "label": {
                        "en_US": "Frisian",
                        "zh_Hans": "弗里西亚语"
                      },
                      "value": "fy"
                    },
                    {
                      "label": {
                        "en_US": "Ga",
                        "zh_Hans": "加语"
                      },
                      "value": "gaa"
                    },
                    {
                      "label": {
                        "en_US": "Galician",
                        "zh_Hans": "加利西亚语"
                      },
                      "value": "gl"
                    },
                    {
                      "label": {
                        "en_US": "Georgian",
                        "zh_Hans": "格鲁吉亚语"
                      },
                      "value": "ka"
                    },
                    {
                      "label": {
                        "en_US": "German",
                        "zh_Hans": "德语"
                      },
                      "value": "de"
                    },
                    {
                      "label": {
                        "en_US": "Greek",
                        "zh_Hans": "希腊语"
                      },
                      "value": "el"
                    },
                    {
                      "label": {
                        "en_US": "Greenlandic",
                        "zh_Hans": "格陵兰语"
                      },
                      "value": "kl"
                    },
                    {
                      "label": {
                        "en_US": "Guarani",
                        "zh_Hans": "瓜拉尼语"
                      },
                      "value": "gn"
                    },
                    {
                      "label": {
                        "en_US": "Gujarati",
                        "zh_Hans": "古吉拉特语"
                      },
                      "value": "gu"
                    },
                    {
                      "label": {
                        "en_US": "Hacker",
                        "zh_Hans": "黑客语"
                      },
                      "value": "xx-hacker"
                    },
                    {
                      "label": {
                        "en_US": "Haitian Creole",
                        "zh_Hans": "海地克里奥尔语"
                      },
                      "value": "ht"
                    },
                    {
                      "label": {
                        "en_US": "Hausa",
                        "zh_Hans": "豪萨语"
                      },
                      "value": "ha"
                    },
                    {
                      "label": {
                        "en_US": "Hawaiian",
                        "zh_Hans": "夏威夷语"
                      },
                      "value": "haw"
                    },
                    {
                      "label": {
                        "en_US": "Hebrew",
                        "zh_Hans": "希伯来语"
                      },
                      "value": "iw"
                    },
                    {
                      "label": {
                        "en_US": "Hindi",
                        "zh_Hans": "印地语"
                      },
                      "value": "hi"
                    },
                    {
                      "label": {
                        "en_US": "Hungarian",
                        "zh_Hans": "匈牙利语"
                      },
                      "value": "hu"
                    },
                    {
                      "label": {
                        "en_US": "Icelandic",
                        "zh_Hans": "冰岛语"
                      },
                      "value": "is"
                    },
                    {
                      "label": {
                        "en_US": "Igbo",
                        "zh_Hans": "伊博语"
                      },
                      "value": "ig"
                    },
                    {
                      "label": {
                        "en_US": "Indonesian",
                        "zh_Hans": "印尼语"
                      },
                      "value": "id"
                    },
                    {
                      "label": {
                        "en_US": "Interlingua",
                        "zh_Hans": "国际语"
                      },
                      "value": "ia"
                    },
                    {
                      "label": {
                        "en_US": "Irish",
                        "zh_Hans": "爱尔兰语"
                      },
                      "value": "ga"
                    },
                    {
                      "label": {
                        "en_US": "Italian",
                        "zh_Hans": "意大利语"
                      },
                      "value": "it"
                    },
                    {
                      "label": {
                        "en_US": "Japanese",
                        "zh_Hans": "日语"
                      },
                      "value": "ja"
                    },
                    {
                      "label": {
                        "en_US": "Javanese",
                        "zh_Hans": "爪哇语"
                      },
                      "value": "jw"
                    },
                    {
                      "label": {
                        "en_US": "Kannada",
                        "zh_Hans": "卡纳达语"
                      },
                      "value": "kn"
                    },
                    {
                      "label": {
                        "en_US": "Kazakh",
                        "zh_Hans": "哈萨克语"
                      },
                      "value": "kk"
                    },
                    {
                      "label": {
                        "en_US": "Kinyarwanda",
                        "zh_Hans": "基尼亚卢旺达语"
                      },
                      "value": "rw"
                    },
                    {
                      "label": {
                        "en_US": "Kirundi",
                        "zh_Hans": "基隆迪语"
                      },
                      "value": "rn"
                    },
                    {
                      "label": {
                        "en_US": "Klingon",
                        "zh_Hans": "克林贡语"
                      },
                      "value": "xx-klingon"
                    },
                    {
                      "label": {
                        "en_US": "Kongo",
                        "zh_Hans": "刚果语"
                      },
                      "value": "kg"
                    },
                    {
                      "label": {
                        "en_US": "Korean",
                        "zh_Hans": "韩语"
                      },
                      "value": "ko"
                    },
                    {
                      "label": {
                        "en_US": "Krio (Sierra Leone)",
                        "zh_Hans": "塞拉利昂克里奥尔语"
                      },
                      "value": "kri"
                    },
                    {
                      "label": {
                        "en_US": "Kurdish",
                        "zh_Hans": "库尔德语"
                      },
                      "value": "ku"
                    },
                    {
                      "label": {
                        "en_US": "Kurdish (Soranî)",
                        "zh_Hans": "库尔德语（索拉尼）"
                      },
                      "value": "ckb"
                    },
                    {
                      "label": {
                        "en_US": "Kyrgyz",
                        "zh_Hans": "吉尔吉斯语"
                      },
                      "value": "ky"
                    },
                    {
                      "label": {
                        "en_US": "Laothian",
                        "zh_Hans": "老挝语"
                      },
                      "value": "lo"
                    },
                    {
                      "label": {
                        "en_US": "Latin",
                        "zh_Hans": "拉丁语"
                      },
                      "value": "la"
                    },
                    {
                      "label": {
                        "en_US": "Latvian",
                        "zh_Hans": "拉脱维亚语"
                      },
                      "value": "lv"
                    },
                    {
                      "label": {
                        "en_US": "Lingala",
                        "zh_Hans": "林加拉语"
                      },
                      "value": "ln"
                    },
                    {
                      "label": {
                        "en_US": "Lithuanian",
                        "zh_Hans": "立陶宛语"
                      },
                      "value": "lt"
                    },
                    {
                      "label": {
                        "en_US": "Lozi",
                        "zh_Hans": "洛齐语"
                      },
                      "value": "loz"
                    },
                    {
                      "label": {
                        "en_US": "Luganda",
                        "zh_Hans": "卢干达语"
                      },
                      "value": "lg"
                    },
                    {
                      "label": {
                        "en_US": "Luo",
                        "zh_Hans": "卢奥语"
                      },
                      "value": "ach"
                    },
                    {
                      "label": {
                        "en_US": "Macedonian",
                        "zh_Hans": "马其顿语"
                      },
                      "value": "mk"
                    },
                    {
                      "label": {
                        "en_US": "Malagasy",
                        "zh_Hans": "马尔加什语"
                      },
                      "value": "mg"
                    },
                    {
                      "label": {
                        "en_US": "Malay",
                        "zh_Hans": "马来语"
                      },
                      "value": "my"
                    },
                    {
                      "label": {
                        "en_US": "Malayalam",
                        "zh_Hans": "马拉雅拉姆语"
                      },
                      "value": "ml"
                    },
                    {
                      "label": {
                        "en_US": "Maltese",
                        "zh_Hans": "马耳他语"
                      },
                      "value": "mt"
                    },
                    {
                      "label": {
                        "en_US": "Maldives",
                        "zh_Hans": "马尔代夫语"
                      },
                      "value": "mv"
                    },
                    {
                      "label": {
                        "en_US": "Maori",
                        "zh_Hans": "毛利语"
                      },
                      "value": "mi"
                    },
                    {
                      "label": {
                        "en_US": "Marathi",
                        "zh_Hans": "马拉地语"
                      },
                      "value": "mr"
                    },
                    {
                      "label": {
                        "en_US": "Mauritian Creole",
                        "zh_Hans": "毛里求斯克里奥尔语"
                      },
                      "value": "mfe"
                    },
                    {
                      "label": {
                        "en_US": "Moldavian",
                        "zh_Hans": "摩尔达维亚语"
                      },
                      "value": "mo"
                    },
                    {
                      "label": {
                        "en_US": "Mongolian",
                        "zh_Hans": "蒙古语"
                      },
                      "value": "mn"
                    },
                    {
                      "label": {
                        "en_US": "Montenegrin",
                        "zh_Hans": "黑山语"
                      },
                      "value": "sr-me"
                    },
                    {
                      "label": {
                        "en_US": "Nepali",
                        "zh_Hans": "尼泊尔语"
                      },
                      "value": "ne"
                    },
                    {
                      "label": {
                        "en_US": "Nigerian Pidgin",
                        "zh_Hans": "尼日利亚皮钦语"
                      },
                      "value": "pcm"
                    },
                    {
                      "label": {
                        "en_US": "Northern Sotho",
                        "zh_Hans": "北索托语"
                      },
                      "value": "nso"
                    },
                    {
                      "label": {
                        "en_US": "Norwegian",
                        "zh_Hans": "挪威语"
                      },
                      "value": "no"
                    },
                    {
                      "label": {
                        "en_US": "Norwegian (Nynorsk)",
                        "zh_Hans": "挪威语（尼诺斯克语）"
                      },
                      "value": "nn"
                    },
                    {
                      "label": {
                        "en_US": "Occitan",
                        "zh_Hans": "奥克语"
                      },
                      "value": "oc"
                    },
                    {
                      "label": {
                        "en_US": "Oriya",
                        "zh_Hans": "奥里亚语"
                      },
                      "value": "or"
                    },
                    {
                      "label": {
                        "en_US": "Oromo",
                        "zh_Hans": "奥罗莫语"
                      },
                      "value": "om"
                    },
                    {
                      "label": {
                        "en_US": "Pashto",
                        "zh_Hans": "普什图语"
                      },
                      "value": "ps"
                    },
                    {
                      "label": {
                        "en_US": "Persian",
                        "zh_Hans": "波斯语"
                      },
                      "value": "fa"
                    },
                    {
                      "label": {
                        "en_US": "Pirate",
                        "zh_Hans": "海盗语"
                      },
                      "value": "xx-pirate"
                    },
                    {
                      "label": {
                        "en_US": "Polish",
                        "zh_Hans": "波兰语"
                      },
                      "value": "pl"
                    },
                    {
                      "label": {
                        "en_US": "Portuguese",
                        "zh_Hans": "葡萄牙语"
                      },
                      "value": "pt"
                    },
                    {
                      "label": {
                        "en_US": "Portuguese (Brazil)",
                        "zh_Hans": "葡萄牙语（巴西）"
                      },
                      "value": "pt-br"
                    },
                    {
                      "label": {
                        "en_US": "Portuguese (Portugal)",
                        "zh_Hans": "葡萄牙语（葡萄牙）"
                      },
                      "value": "pt-pt"
                    },
                    {
                      "label": {
                        "en_US": "Punjabi",
                        "zh_Hans": "旁遮普语"
                      },
                      "value": "pa"
                    },
                    {
                      "label": {
                        "en_US": "Quechua",
                        "zh_Hans": "克丘亚语"
                      },
                      "value": "qu"
                    },
                    {
                      "label": {
                        "en_US": "Romanian",
                        "zh_Hans": "罗马尼亚语"
                      },
                      "value": "ro"
                    },
                    {
                      "label": {
                        "en_US": "Romansh",
                        "zh_Hans": "罗曼什语"
                      },
                      "value": "rm"
                    },
                    {
                      "label": {
                        "en_US": "Runyakitara",
                        "zh_Hans": "卢尼亚基塔拉语"
                      },
                      "value": "nyn"
                    },
                    {
                      "label": {
                        "en_US": "Russian",
                        "zh_Hans": "俄语"
                      },
                      "value": "ru"
                    },
                    {
                      "label": {
                        "en_US": "Scots Gaelic",
                        "zh_Hans": "苏格兰盖尔语"
                      },
                      "value": "gd"
                    },
                    {
                      "label": {
                        "en_US": "Serbian",
                        "zh_Hans": "塞尔维亚语"
                      },
                      "value": "sr"
                    },
                    {
                      "label": {
                        "en_US": "Serbo-Croatian",
                        "zh_Hans": "塞尔维亚-克罗地亚语"
                      },
                      "value": "sh"
                    },
                    {
                      "label": {
                        "en_US": "Sesotho",
                        "zh_Hans": "塞索托语"
                      },
                      "value": "st"
                    },
                    {
                      "label": {
                        "en_US": "Setswana",
                        "zh_Hans": "塞茨瓦纳语"
                      },
                      "value": "tn"
                    },
                    {
                      "label": {
                        "en_US": "Seychellois Creole",
                        "zh_Hans": "塞舌尔克里奥尔语"
                      },
                      "value": "crs"
                    },
                    {
                      "label": {
                        "en_US": "Shona",
                        "zh_Hans": "绍纳语"
                      },
                      "value": "sn"
                    },
                    {
                      "label": {
                        "en_US": "Sindhi",
                        "zh_Hans": "信德语"
                      },
                      "value": "sd"
                    },
                    {
                      "label": {
                        "en_US": "Sinhalese",
                        "zh_Hans": "僧伽罗语"
                      },
                      "value": "si"
                    },
                    {
                      "label": {
                        "en_US": "Slovak",
                        "zh_Hans": "斯洛伐克语"
                      },
                      "value": "sk"
                    },
                    {
                      "label": {
                        "en_US": "Slovenian",
                        "zh_Hans": "斯洛文尼亚语"
                      },
                      "value": "sl"
                    },
                    {
                      "label": {
                        "en_US": "Somali",
                        "zh_Hans": "索马里语"
                      },
                      "value": "so"
                    },
                    {
                      "label": {
                        "en_US": "Spanish",
                        "zh_Hans": "西班牙语"
                      },
                      "value": "es"
                    },
                    {
                      "label": {
                        "en_US": "Spanish (Latin American)",
                        "zh_Hans": "西班牙语（拉丁美洲）"
                      },
                      "value": "es-419"
                    },
                    {
                      "label": {
                        "en_US": "Sundanese",
                        "zh_Hans": "巽他语"
                      },
                      "value": "su"
                    },
                    {
                      "label": {
                        "en_US": "Swahili",
                        "zh_Hans": "斯瓦希里语"
                      },
                      "value": "sw"
                    },
                    {
                      "label": {
                        "en_US": "Swedish",
                        "zh_Hans": "瑞典语"
                      },
                      "value": "sv"
                    },
                    {
                      "label": {
                        "en_US": "Tajik",
                        "zh_Hans": "塔吉克语"
                      },
                      "value": "tg"
                    },
                    {
                      "label": {
                        "en_US": "Tamil",
                        "zh_Hans": "泰米尔语"
                      },
                      "value": "ta"
                    },
                    {
                      "label": {
                        "en_US": "Tatar",
                        "zh_Hans": "鞑靼语"
                      },
                      "value": "tt"
                    },
                    {
                      "label": {
                        "en_US": "Telugu",
                        "zh_Hans": "泰卢固语"
                      },
                      "value": "te"
                    },
                    {
                      "label": {
                        "en_US": "Thai",
                        "zh_Hans": "泰语"
                      },
                      "value": "th"
                    },
                    {
                      "label": {
                        "en_US": "Tigrinya",
                        "zh_Hans": "提格利尼亚语"
                      },
                      "value": "ti"
                    },
                    {
                      "label": {
                        "en_US": "Tonga",
                        "zh_Hans": "汤加语"
                      },
                      "value": "to"
                    },
                    {
                      "label": {
                        "en_US": "Tshiluba",
                        "zh_Hans": "卢巴语"
                      },
                      "value": "lua"
                    },
                    {
                      "label": {
                        "en_US": "Tumbuka",
                        "zh_Hans": "图布卡语"
                      },
                      "value": "tum"
                    },
                    {
                      "label": {
                        "en_US": "Turkish",
                        "zh_Hans": "土耳其语"
                      },
                      "value": "tr"
                    },
                    {
                      "label": {
                        "en_US": "Turkmen",
                        "zh_Hans": "土库曼语"
                      },
                      "value": "tk"
                    },
                    {
                      "label": {
                        "en_US": "Twi",
                        "zh_Hans": "契维语"
                      },
                      "value": "tw"
                    },
                    {
                      "label": {
                        "en_US": "Uighur",
                        "zh_Hans": "维吾尔语"
                      },
                      "value": "ug"
                    },
                    {
                      "label": {
                        "en_US": "Ukrainian",
                        "zh_Hans": "乌克兰语"
                      },
                      "value": "uk"
                    },
                    {
                      "label": {
                        "en_US": "Urdu",
                        "zh_Hans": "乌尔都语"
                      },
                      "value": "ur"
                    },
                    {
                      "label": {
                        "en_US": "Uzbek",
                        "zh_Hans": "乌兹别克语"
                      },
                      "value": "uz"
                    },
                    {
                      "label": {
                        "en_US": "Vanuatu",
                        "zh_Hans": "瓦努阿图语"
                      },
                      "value": "vu"
                    },
                    {
                      "label": {
                        "en_US": "Vietnamese",
                        "zh_Hans": "越南语"
                      },
                      "value": "vi"
                    },
                    {
                      "label": {
                        "en_US": "Welsh",
                        "zh_Hans": "威尔士语"
                      },
                      "value": "cy"
                    },
                    {
                      "label": {
                        "en_US": "Wolof",
                        "zh_Hans": "沃洛夫语"
                      },
                      "value": "wo"
                    },
                    {
                      "label": {
                        "en_US": "Xhosa",
                        "zh_Hans": "科萨语"
                      },
                      "value": "xh"
                    },
                    {
                      "label": {
                        "en_US": "Yiddish",
                        "zh_Hans": "意第绪语"
                      },
                      "value": "yi"
                    },
                    {
                      "label": {
                        "en_US": "Yoruba",
                        "zh_Hans": "约鲁巴语"
                      },
                      "value": "yo"
                    },
                    {
                      "label": {
                        "en_US": "Zulu",
                        "zh_Hans": "祖鲁语"
                      },
                      "value": "zu"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Filter results based on the work arrangement. Set it to true to find jobs that offer work from home or remote work opportunities.",
                    "zh_Hans": "根据工作安排过滤结果。将其设置为 true 可查找提供在家工作或远程工作机会的工作。"
                  },
                  "label": {
                    "en_US": "is_remote",
                    "zh_Hans": "很遥远"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "is_remote",
                  "options": [
                    {
                      "label": {
                        "en_US": "true",
                        "zh_Hans": "true"
                      },
                      "value": "true"
                    },
                    {
                      "label": {
                        "en_US": "false",
                        "zh_Hans": "false"
                      },
                      "value": "false"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool to retrieve organic search results snippets and links from Google News engine.",
                  "zh_Hans": "一种从 Google 新闻引擎检索有机搜索结果片段和链接的工具。"
                },
                "llm": "A tool to retrieve organic search results snippets and links from Google News engine."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "SearchApi",
                "label": {
                  "en_US": "Google News API",
                  "zh_Hans": "Google News API"
                },
                "name": "google_news_api"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Defines the query you want to search.",
                    "zh_Hans": "定义您要搜索的查询。"
                  },
                  "label": {
                    "en_US": "Query",
                    "zh_Hans": "询问"
                  },
                  "llm_description": "Defines the search query you want to search.",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "text",
                  "form": "form",
                  "human_description": {
                    "en_US": "used for selecting the result type, text or link.",
                    "zh_Hans": "用于选择结果类型，使用文本还是链接进行展示。"
                  },
                  "label": {
                    "en_US": "Result type",
                    "zh_Hans": "结果类型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "result_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "text",
                        "zh_Hans": "文本"
                      },
                      "value": "text"
                    },
                    {
                      "label": {
                        "en_US": "link",
                        "zh_Hans": "链接"
                      },
                      "value": "link"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Defines from where you want the search to originate. (For example - New York)",
                    "zh_Hans": "定义您想要搜索的起始位置。 （例如 - 纽约）"
                  },
                  "label": {
                    "en_US": "Location",
                    "zh_Hans": "询问"
                  },
                  "llm_description": "Defines from where you want the search to originate. (For example - New York)",
                  "max": null,
                  "min": null,
                  "name": "location",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "US",
                  "form": "form",
                  "human_description": {
                    "en_US": "Defines the country of the search. Default is \"US\".",
                    "zh_Hans": "定义搜索的国家/地区。默认为“美国”。"
                  },
                  "label": {
                    "en_US": "Country",
                    "zh_Hans": "国家"
                  },
                  "llm_description": "Defines the gl parameter of the Google search.",
                  "max": null,
                  "min": null,
                  "name": "gl",
                  "options": [
                    {
                      "label": {
                        "en_US": "Afghanistan",
                        "pt_BR": "Afeganistão",
                        "zh_Hans": "阿富汗"
                      },
                      "value": "AF"
                    },
                    {
                      "label": {
                        "en_US": "Albania",
                        "pt_BR": "Albânia",
                        "zh_Hans": "阿尔巴尼亚"
                      },
                      "value": "AL"
                    },
                    {
                      "label": {
                        "en_US": "Algeria",
                        "pt_BR": "Argélia",
                        "zh_Hans": "阿尔及利亚"
                      },
                      "value": "DZ"
                    },
                    {
                      "label": {
                        "en_US": "American Samoa",
                        "pt_BR": "Samoa Americana",
                        "zh_Hans": "美属萨摩亚"
                      },
                      "value": "AS"
                    },
                    {
                      "label": {
                        "en_US": "Andorra",
                        "pt_BR": "Andorra",
                        "zh_Hans": "安道尔"
                      },
                      "value": "AD"
                    },
                    {
                      "label": {
                        "en_US": "Angola",
                        "pt_BR": "Angola",
                        "zh_Hans": "安哥拉"
                      },
                      "value": "AO"
                    },
                    {
                      "label": {
                        "en_US": "Anguilla",
                        "pt_BR": "Anguilla",
                        "zh_Hans": "安圭拉"
                      },
                      "value": "AI"
                    },
                    {
                      "label": {
                        "en_US": "Antarctica",
                        "pt_BR": "Antártica",
                        "zh_Hans": "南极洲"
                      },
                      "value": "AQ"
                    },
                    {
                      "label": {
                        "en_US": "Antigua and Barbuda",
                        "pt_BR": "Antígua e Barbuda",
                        "zh_Hans": "安提瓜和巴布达"
                      },
                      "value": "AG"
                    },
                    {
                      "label": {
                        "en_US": "Argentina",
                        "pt_BR": "Argentina",
                        "zh_Hans": "阿根廷"
                      },
                      "value": "AR"
                    },
                    {
                      "label": {
                        "en_US": "Armenia",
                        "pt_BR": "Armênia",
                        "zh_Hans": "亚美尼亚"
                      },
                      "value": "AM"
                    },
                    {
                      "label": {
                        "en_US": "Aruba",
                        "pt_BR": "Aruba",
                        "zh_Hans": "阿鲁巴"
                      },
                      "value": "AW"
                    },
                    {
                      "label": {
                        "en_US": "Australia",
                        "pt_BR": "Austrália",
                        "zh_Hans": "澳大利亚"
                      },
                      "value": "AU"
                    },
                    {
                      "label": {
                        "en_US": "Austria",
                        "pt_BR": "Áustria",
                        "zh_Hans": "奥地利"
                      },
                      "value": "AT"
                    },
                    {
                      "label": {
                        "en_US": "Azerbaijan",
                        "pt_BR": "Azerbaijão",
                        "zh_Hans": "阿塞拜疆"
                      },
                      "value": "AZ"
                    },
                    {
                      "label": {
                        "en_US": "Bahamas",
                        "pt_BR": "Bahamas",
                        "zh_Hans": "巴哈马"
                      },
                      "value": "BS"
                    },
                    {
                      "label": {
                        "en_US": "Bahrain",
                        "pt_BR": "Bahrein",
                        "zh_Hans": "巴林"
                      },
                      "value": "BH"
                    },
                    {
                      "label": {
                        "en_US": "Bangladesh",
                        "pt_BR": "Bangladesh",
                        "zh_Hans": "孟加拉国"
                      },
                      "value": "BD"
                    },
                    {
                      "label": {
                        "en_US": "Barbados",
                        "pt_BR": "Barbados",
                        "zh_Hans": "巴巴多斯"
                      },
                      "value": "BB"
                    },
                    {
                      "label": {
                        "en_US": "Belarus",
                        "pt_BR": "Bielorrússia",
                        "zh_Hans": "白俄罗斯"
                      },
                      "value": "BY"
                    },
                    {
                      "label": {
                        "en_US": "Belgium",
                        "pt_BR": "Bélgica",
                        "zh_Hans": "比利时"
                      },
                      "value": "BE"
                    },
                    {
                      "label": {
                        "en_US": "Belize",
                        "pt_BR": "Belize",
                        "zh_Hans": "伯利兹"
                      },
                      "value": "BZ"
                    },
                    {
                      "label": {
                        "en_US": "Benin",
                        "pt_BR": "Benim",
                        "zh_Hans": "贝宁"
                      },
                      "value": "BJ"
                    },
                    {
                      "label": {
                        "en_US": "Bermuda",
                        "pt_BR": "Bermudas",
                        "zh_Hans": "百慕大"
                      },
                      "value": "BM"
                    },
                    {
                      "label": {
                        "en_US": "Bhutan",
                        "pt_BR": "Butão",
                        "zh_Hans": "不丹"
                      },
                      "value": "BT"
                    },
                    {
                      "label": {
                        "en_US": "Bolivia",
                        "pt_BR": "Bolívia",
                        "zh_Hans": "玻利维亚"
                      },
                      "value": "BO"
                    },
                    {
                      "label": {
                        "en_US": "Bosnia and Herzegovina",
                        "pt_BR": "Bósnia e Herzegovina",
                        "zh_Hans": "波斯尼亚和黑塞哥维那"
                      },
                      "value": "BA"
                    },
                    {
                      "label": {
                        "en_US": "Botswana",
                        "pt_BR": "Botsuana",
                        "zh_Hans": "博茨瓦纳"
                      },
                      "value": "BW"
                    },
                    {
                      "label": {
                        "en_US": "Bouvet Island",
                        "pt_BR": "Ilha Bouvet",
                        "zh_Hans": "布韦岛"
                      },
                      "value": "BV"
                    },
                    {
                      "label": {
                        "en_US": "Brazil",
                        "pt_BR": "Brasil",
                        "zh_Hans": "巴西"
                      },
                      "value": "BR"
                    },
                    {
                      "label": {
                        "en_US": "British Indian Ocean Territory",
                        "pt_BR": "Território Britânico do Oceano Índico",
                        "zh_Hans": "英属印度洋领地"
                      },
                      "value": "IO"
                    },
                    {
                      "label": {
                        "en_US": "Brunei Darussalam",
                        "pt_BR": "Brunei Darussalam",
                        "zh_Hans": "文莱"
                      },
                      "value": "BN"
                    },
                    {
                      "label": {
                        "en_US": "Bulgaria",
                        "pt_BR": "Bulgária",
                        "zh_Hans": "保加利亚"
                      },
                      "value": "BG"
                    },
                    {
                      "label": {
                        "en_US": "Burkina Faso",
                        "pt_BR": "Burkina Faso",
                        "zh_Hans": "布基纳法索"
                      },
                      "value": "BF"
                    },
                    {
                      "label": {
                        "en_US": "Burundi",
                        "pt_BR": "Burundi",
                        "zh_Hans": "布隆迪"
                      },
                      "value": "BI"
                    },
                    {
                      "label": {
                        "en_US": "Cambodia",
                        "pt_BR": "Camboja",
                        "zh_Hans": "柬埔寨"
                      },
                      "value": "KH"
                    },
                    {
                      "label": {
                        "en_US": "Cameroon",
                        "pt_BR": "Camarões",
                        "zh_Hans": "喀麦隆"
                      },
                      "value": "CM"
                    },
                    {
                      "label": {
                        "en_US": "Canada",
                        "pt_BR": "Canadá",
                        "zh_Hans": "加拿大"
                      },
                      "value": "CA"
                    },
                    {
                      "label": {
                        "en_US": "Cape Verde",
                        "pt_BR": "Cabo Verde",
                        "zh_Hans": "佛得角"
                      },
                      "value": "CV"
                    },
                    {
                      "label": {
                        "en_US": "Cayman Islands",
                        "pt_BR": "Ilhas Cayman",
                        "zh_Hans": "开曼群岛"
                      },
                      "value": "KY"
                    },
                    {
                      "label": {
                        "en_US": "Central African Republic",
                        "pt_BR": "República Centro-Africana",
                        "zh_Hans": "中非共和国"
                      },
                      "value": "CF"
                    },
                    {
                      "label": {
                        "en_US": "Chad",
                        "pt_BR": "Chade",
                        "zh_Hans": "乍得"
                      },
                      "value": "TD"
                    },
                    {
                      "label": {
                        "en_US": "Chile",
                        "pt_BR": "Chile",
                        "zh_Hans": "智利"
                      },
                      "value": "CL"
                    },
                    {
                      "label": {
                        "en_US": "China",
                        "pt_BR": "China",
                        "zh_Hans": "中国"
                      },
                      "value": "CN"
                    },
                    {
                      "label": {
                        "en_US": "Christmas Island",
                        "pt_BR": "Ilha do Natal",
                        "zh_Hans": "圣诞岛"
                      },
                      "value": "CX"
                    },
                    {
                      "label": {
                        "en_US": "Cocos (Keeling) Islands",
                        "pt_BR": "Ilhas Cocos (Keeling)",
                        "zh_Hans": "科科斯（基林）群岛"
                      },
                      "value": "CC"
                    },
                    {
                      "label": {
                        "en_US": "Colombia",
                        "pt_BR": "Colômbia",
                        "zh_Hans": "哥伦比亚"
                      },
                      "value": "CO"
                    },
                    {
                      "label": {
                        "en_US": "Comoros",
                        "pt_BR": "Comores",
                        "zh_Hans": "科摩罗"
                      },
                      "value": "KM"
                    },
                    {
                      "label": {
                        "en_US": "Congo",
                        "pt_BR": "Congo",
                        "zh_Hans": "刚果"
                      },
                      "value": "CG"
                    },
                    {
                      "label": {
                        "en_US": "Congo, the Democratic Republic of the",
                        "pt_BR": "Congo, República Democrática do",
                        "zh_Hans": "刚果民主共和国"
                      },
                      "value": "CD"
                    },
                    {
                      "label": {
                        "en_US": "Cook Islands",
                        "pt_BR": "Ilhas Cook",
                        "zh_Hans": "库克群岛"
                      },
                      "value": "CK"
                    },
                    {
                      "label": {
                        "en_US": "Costa Rica",
                        "pt_BR": "Costa Rica",
                        "zh_Hans": "哥斯达黎加"
                      },
                      "value": "CR"
                    },
                    {
                      "label": {
                        "en_US": "Cote D'ivoire",
                        "pt_BR": "Costa do Marfim",
                        "zh_Hans": "科特迪瓦"
                      },
                      "value": "CI"
                    },
                    {
                      "label": {
                        "en_US": "Croatia",
                        "pt_BR": "Croácia",
                        "zh_Hans": "克罗地亚"
                      },
                      "value": "HR"
                    },
                    {
                      "label": {
                        "en_US": "Cuba",
                        "pt_BR": "Cuba",
                        "zh_Hans": "古巴"
                      },
                      "value": "CU"
                    },
                    {
                      "label": {
                        "en_US": "Cyprus",
                        "pt_BR": "Chipre",
                        "zh_Hans": "塞浦路斯"
                      },
                      "value": "CY"
                    },
                    {
                      "label": {
                        "en_US": "Czech Republic",
                        "pt_BR": "República Tcheca",
                        "zh_Hans": "捷克共和国"
                      },
                      "value": "CZ"
                    },
                    {
                      "label": {
                        "en_US": "Denmark",
                        "pt_BR": "Dinamarca",
                        "zh_Hans": "丹麦"
                      },
                      "value": "DK"
                    },
                    {
                      "label": {
                        "en_US": "Djibouti",
                        "pt_BR": "Djibuti",
                        "zh_Hans": "吉布提"
                      },
                      "value": "DJ"
                    },
                    {
                      "label": {
                        "en_US": "Dominica",
                        "pt_BR": "Dominica",
                        "zh_Hans": "多米尼克"
                      },
                      "value": "DM"
                    },
                    {
                      "label": {
                        "en_US": "Dominican Republic",
                        "pt_BR": "República Dominicana",
                        "zh_Hans": "多米尼加共和国"
                      },
                      "value": "DO"
                    },
                    {
                      "label": {
                        "en_US": "Ecuador",
                        "pt_BR": "Equador",
                        "zh_Hans": "厄瓜多尔"
                      },
                      "value": "EC"
                    },
                    {
                      "label": {
                        "en_US": "Egypt",
                        "pt_BR": "Egito",
                        "zh_Hans": "埃及"
                      },
                      "value": "EG"
                    },
                    {
                      "label": {
                        "en_US": "El Salvador",
                        "pt_BR": "El Salvador",
                        "zh_Hans": "萨尔瓦多"
                      },
                      "value": "SV"
                    },
                    {
                      "label": {
                        "en_US": "Equatorial Guinea",
                        "pt_BR": "Guiné Equatorial",
                        "zh_Hans": "赤道几内亚"
                      },
                      "value": "GQ"
                    },
                    {
                      "label": {
                        "en_US": "Eritrea",
                        "pt_BR": "Eritreia",
                        "zh_Hans": "厄立特里亚"
                      },
                      "value": "ER"
                    },
                    {
                      "label": {
                        "en_US": "Estonia",
                        "pt_BR": "Estônia",
                        "zh_Hans": "爱沙尼亚"
                      },
                      "value": "EE"
                    },
                    {
                      "label": {
                        "en_US": "Ethiopia",
                        "pt_BR": "Etiópia",
                        "zh_Hans": "埃塞俄比亚"
                      },
                      "value": "ET"
                    },
                    {
                      "label": {
                        "en_US": "Falkland Islands (Malvinas)",
                        "pt_BR": "Ilhas Falkland (Malvinas)",
                        "zh_Hans": "福克兰群岛（马尔维纳斯）"
                      },
                      "value": "FK"
                    },
                    {
                      "label": {
                        "en_US": "Faroe Islands",
                        "pt_BR": "Ilhas Faroe",
                        "zh_Hans": "法罗群岛"
                      },
                      "value": "FO"
                    },
                    {
                      "label": {
                        "en_US": "Fiji",
                        "pt_BR": "Fiji",
                        "zh_Hans": "斐济"
                      },
                      "value": "FJ"
                    },
                    {
                      "label": {
                        "en_US": "Finland",
                        "pt_BR": "Finlândia",
                        "zh_Hans": "芬兰"
                      },
                      "value": "FI"
                    },
                    {
                      "label": {
                        "en_US": "France",
                        "pt_BR": "França",
                        "zh_Hans": "法国"
                      },
                      "value": "FR"
                    },
                    {
                      "label": {
                        "en_US": "French Guiana",
                        "pt_BR": "Guiana Francesa",
                        "zh_Hans": "法属圭亚那"
                      },
                      "value": "GF"
                    },
                    {
                      "label": {
                        "en_US": "French Polynesia",
                        "pt_BR": "Polinésia Francesa",
                        "zh_Hans": "法属波利尼西亚"
                      },
                      "value": "PF"
                    },
                    {
                      "label": {
                        "en_US": "French Southern Territories",
                        "pt_BR": "Territórios Franceses do Sul",
                        "zh_Hans": "法属南部领地"
                      },
                      "value": "TF"
                    },
                    {
                      "label": {
                        "en_US": "Gabon",
                        "pt_BR": "Gabão",
                        "zh_Hans": "加蓬"
                      },
                      "value": "GA"
                    },
                    {
                      "label": {
                        "en_US": "Gambia",
                        "pt_BR": "Gâmbia",
                        "zh_Hans": "冈比亚"
                      },
                      "value": "GM"
                    },
                    {
                      "label": {
                        "en_US": "Georgia",
                        "pt_BR": "Geórgia",
                        "zh_Hans": "格鲁吉亚"
                      },
                      "value": "GE"
                    },
                    {
                      "label": {
                        "en_US": "Germany",
                        "pt_BR": "Alemanha",
                        "zh_Hans": "德国"
                      },
                      "value": "DE"
                    },
                    {
                      "label": {
                        "en_US": "Ghana",
                        "pt_BR": "Gana",
                        "zh_Hans": "加纳"
                      },
                      "value": "GH"
                    },
                    {
                      "label": {
                        "en_US": "Gibraltar",
                        "pt_BR": "Gibraltar",
                        "zh_Hans": "直布罗陀"
                      },
                      "value": "GI"
                    },
                    {
                      "label": {
                        "en_US": "Greece",
                        "pt_BR": "Grécia",
                        "zh_Hans": "希腊"
                      },
                      "value": "GR"
                    },
                    {
                      "label": {
                        "en_US": "Greenland",
                        "pt_BR": "Groenlândia",
                        "zh_Hans": "格陵兰"
                      },
                      "value": "GL"
                    },
                    {
                      "label": {
                        "en_US": "Grenada",
                        "pt_BR": "Granada",
                        "zh_Hans": "格林纳达"
                      },
                      "value": "GD"
                    },
                    {
                      "label": {
                        "en_US": "Guadeloupe",
                        "pt_BR": "Guadalupe",
                        "zh_Hans": "瓜德罗普"
                      },
                      "value": "GP"
                    },
                    {
                      "label": {
                        "en_US": "Guam",
                        "pt_BR": "Guam",
                        "zh_Hans": "关岛"
                      },
                      "value": "GU"
                    },
                    {
                      "label": {
                        "en_US": "Guatemala",
                        "pt_BR": "Guatemala",
                        "zh_Hans": "危地马拉"
                      },
                      "value": "GT"
                    },
                    {
                      "label": {
                        "en_US": "Guinea",
                        "pt_BR": "Guiné",
                        "zh_Hans": "几内亚"
                      },
                      "value": "GN"
                    },
                    {
                      "label": {
                        "en_US": "Guinea-Bissau",
                        "pt_BR": "Guiné-Bissau",
                        "zh_Hans": "几内亚比绍"
                      },
                      "value": "GW"
                    },
                    {
                      "label": {
                        "en_US": "Guyana",
                        "pt_BR": "Guiana",
                        "zh_Hans": "圭亚那"
                      },
                      "value": "GY"
                    },
                    {
                      "label": {
                        "en_US": "Haiti",
                        "pt_BR": "Haiti",
                        "zh_Hans": "海地"
                      },
                      "value": "HT"
                    },
                    {
                      "label": {
                        "en_US": "Heard Island and McDonald Islands",
                        "pt_BR": "Ilha Heard e Ilhas McDonald",
                        "zh_Hans": "赫德岛和麦克唐纳群岛"
                      },
                      "value": "HM"
                    },
                    {
                      "label": {
                        "en_US": "Holy See (Vatican City State)",
                        "pt_BR": "Santa Sé (Estado da Cidade do Vaticano)",
                        "zh_Hans": "教廷（梵蒂冈城国）"
                      },
                      "value": "VA"
                    },
                    {
                      "label": {
                        "en_US": "Honduras",
                        "pt_BR": "Honduras",
                        "zh_Hans": "洪都拉斯"
                      },
                      "value": "HN"
                    },
                    {
                      "label": {
                        "en_US": "Hong Kong",
                        "pt_BR": "Hong Kong",
                        "zh_Hans": "香港"
                      },
                      "value": "HK"
                    },
                    {
                      "label": {
                        "en_US": "Hungary",
                        "pt_BR": "Hungria",
                        "zh_Hans": "匈牙利"
                      },
                      "value": "HU"
                    },
                    {
                      "label": {
                        "en_US": "Iceland",
                        "pt_BR": "Islândia",
                        "zh_Hans": "冰岛"
                      },
                      "value": "IS"
                    },
                    {
                      "label": {
                        "en_US": "India",
                        "pt_BR": "Índia",
                        "zh_Hans": "印度"
                      },
                      "value": "IN"
                    },
                    {
                      "label": {
                        "en_US": "Indonesia",
                        "pt_BR": "Indonésia",
                        "zh_Hans": "印度尼西亚"
                      },
                      "value": "ID"
                    },
                    {
                      "label": {
                        "en_US": "Iran, Islamic Republic of",
                        "pt_BR": "Irã",
                        "zh_Hans": "伊朗"
                      },
                      "value": "IR"
                    },
                    {
                      "label": {
                        "en_US": "Iraq",
                        "pt_BR": "Iraque",
                        "zh_Hans": "伊拉克"
                      },
                      "value": "IQ"
                    },
                    {
                      "label": {
                        "en_US": "Ireland",
                        "pt_BR": "Irlanda",
                        "zh_Hans": "爱尔兰"
                      },
                      "value": "IE"
                    },
                    {
                      "label": {
                        "en_US": "Israel",
                        "pt_BR": "Israel",
                        "zh_Hans": "以色列"
                      },
                      "value": "IL"
                    },
                    {
                      "label": {
                        "en_US": "Italy",
                        "pt_BR": "Itália",
                        "zh_Hans": "意大利"
                      },
                      "value": "IT"
                    },
                    {
                      "label": {
                        "en_US": "Jamaica",
                        "pt_BR": "Jamaica",
                        "zh_Hans": "牙买加"
                      },
                      "value": "JM"
                    },
                    {
                      "label": {
                        "en_US": "Japan",
                        "pt_BR": "Japão",
                        "zh_Hans": "日本"
                      },
                      "value": "JP"
                    },
                    {
                      "label": {
                        "en_US": "Jordan",
                        "pt_BR": "Jordânia",
                        "zh_Hans": "约旦"
                      },
                      "value": "JO"
                    },
                    {
                      "label": {
                        "en_US": "Kazakhstan",
                        "pt_BR": "Cazaquistão",
                        "zh_Hans": "哈萨克斯坦"
                      },
                      "value": "KZ"
                    },
                    {
                      "label": {
                        "en_US": "Kenya",
                        "pt_BR": "Quênia",
                        "zh_Hans": "肯尼亚"
                      },
                      "value": "KE"
                    },
                    {
                      "label": {
                        "en_US": "Kiribati",
                        "pt_BR": "Kiribati",
                        "zh_Hans": "基里巴斯"
                      },
                      "value": "KI"
                    },
                    {
                      "label": {
                        "en_US": "Korea, Democratic People's Republic of",
                        "pt_BR": "Coreia, República Democrática Popular da",
                        "zh_Hans": "朝鲜"
                      },
                      "value": "KP"
                    },
                    {
                      "label": {
                        "en_US": "Korea, Republic of",
                        "pt_BR": "Coreia, República da",
                        "zh_Hans": "韩国"
                      },
                      "value": "KR"
                    },
                    {
                      "label": {
                        "en_US": "Kuwait",
                        "pt_BR": "Kuwait",
                        "zh_Hans": "科威特"
                      },
                      "value": "KW"
                    },
                    {
                      "label": {
                        "en_US": "Kyrgyzstan",
                        "pt_BR": "Quirguistão",
                        "zh_Hans": "吉尔吉斯斯坦"
                      },
                      "value": "KG"
                    },
                    {
                      "label": {
                        "en_US": "Lao People's Democratic Republic",
                        "pt_BR": "República Democrática Popular do Laos",
                        "zh_Hans": "老挝"
                      },
                      "value": "LA"
                    },
                    {
                      "label": {
                        "en_US": "Latvia",
                        "pt_BR": "Letônia",
                        "zh_Hans": "拉脱维亚"
                      },
                      "value": "LV"
                    },
                    {
                      "label": {
                        "en_US": "Lebanon",
                        "pt_BR": "Líbano",
                        "zh_Hans": "黎巴嫩"
                      },
                      "value": "LB"
                    },
                    {
                      "label": {
                        "en_US": "Lesotho",
                        "pt_BR": "Lesoto",
                        "zh_Hans": "莱索托"
                      },
                      "value": "LS"
                    },
                    {
                      "label": {
                        "en_US": "Liberia",
                        "pt_BR": "Libéria",
                        "zh_Hans": "利比里亚"
                      },
                      "value": "LR"
                    },
                    {
                      "label": {
                        "en_US": "Libyan Arab Jamahiriya",
                        "pt_BR": "Líbia",
                        "zh_Hans": "利比亚"
                      },
                      "value": "LY"
                    },
                    {
                      "label": {
                        "en_US": "Liechtenstein",
                        "pt_BR": "Liechtenstein",
                        "zh_Hans": "列支敦士登"
                      },
                      "value": "LI"
                    },
                    {
                      "label": {
                        "en_US": "Lithuania",
                        "pt_BR": "Lituânia",
                        "zh_Hans": "立陶宛"
                      },
                      "value": "LT"
                    },
                    {
                      "label": {
                        "en_US": "Luxembourg",
                        "pt_BR": "Luxemburgo",
                        "zh_Hans": "卢森堡"
                      },
                      "value": "LU"
                    },
                    {
                      "label": {
                        "en_US": "Macao",
                        "pt_BR": "Macau",
                        "zh_Hans": "澳门"
                      },
                      "value": "MO"
                    },
                    {
                      "label": {
                        "en_US": "Macedonia, the Former Yugosalv Republic of",
                        "pt_BR": "Macedônia, Ex-República Iugoslava da",
                        "zh_Hans": "前南斯拉夫马其顿共和国"
                      },
                      "value": "MK"
                    },
                    {
                      "label": {
                        "en_US": "Madagascar",
                        "pt_BR": "Madagascar",
                        "zh_Hans": "马达加斯加"
                      },
                      "value": "MG"
                    },
                    {
                      "label": {
                        "en_US": "Malawi",
                        "pt_BR": "Malaui",
                        "zh_Hans": "马拉维"
                      },
                      "value": "MW"
                    },
                    {
                      "label": {
                        "en_US": "Malaysia",
                        "pt_BR": "Malásia",
                        "zh_Hans": "马来西亚"
                      },
                      "value": "MY"
                    },
                    {
                      "label": {
                        "en_US": "Maldives",
                        "pt_BR": "Maldivas",
                        "zh_Hans": "马尔代夫"
                      },
                      "value": "MV"
                    },
                    {
                      "label": {
                        "en_US": "Mali",
                        "pt_BR": "Mali",
                        "zh_Hans": "马里"
                      },
                      "value": "ML"
                    },
                    {
                      "label": {
                        "en_US": "Malta",
                        "pt_BR": "Malta",
                        "zh_Hans": "马耳他"
                      },
                      "value": "MT"
                    },
                    {
                      "label": {
                        "en_US": "Marshall Islands",
                        "pt_BR": "Ilhas Marshall",
                        "zh_Hans": "马绍尔群岛"
                      },
                      "value": "MH"
                    },
                    {
                      "label": {
                        "en_US": "Martinique",
                        "pt_BR": "Martinica",
                        "zh_Hans": "马提尼克"
                      },
                      "value": "MQ"
                    },
                    {
                      "label": {
                        "en_US": "Mauritania",
                        "pt_BR": "Mauritânia",
                        "zh_Hans": "毛里塔尼亚"
                      },
                      "value": "MR"
                    },
                    {
                      "label": {
                        "en_US": "Mauritius",
                        "pt_BR": "Maurício",
                        "zh_Hans": "毛里求斯"
                      },
                      "value": "MU"
                    },
                    {
                      "label": {
                        "en_US": "Mayotte",
                        "pt_BR": "Mayotte",
                        "zh_Hans": "马约特"
                      },
                      "value": "YT"
                    },
                    {
                      "label": {
                        "en_US": "Mexico",
                        "pt_BR": "México",
                        "zh_Hans": "墨西哥"
                      },
                      "value": "MX"
                    },
                    {
                      "label": {
                        "en_US": "Micronesia, Federated States of",
                        "pt_BR": "Micronésia, Estados Federados da",
                        "zh_Hans": "密克罗尼西亚联邦"
                      },
                      "value": "FM"
                    },
                    {
                      "label": {
                        "en_US": "Moldova, Republic of",
                        "pt_BR": "Moldávia, República da",
                        "zh_Hans": "摩尔多瓦共和国"
                      },
                      "value": "MD"
                    },
                    {
                      "label": {
                        "en_US": "Monaco",
                        "pt_BR": "Mônaco",
                        "zh_Hans": "摩纳哥"
                      },
                      "value": "MC"
                    },
                    {
                      "label": {
                        "en_US": "Mongolia",
                        "pt_BR": "Mongólia",
                        "zh_Hans": "蒙古"
                      },
                      "value": "MN"
                    },
                    {
                      "label": {
                        "en_US": "Montserrat",
                        "pt_BR": "Montserrat",
                        "zh_Hans": "蒙特塞拉特"
                      },
                      "value": "MS"
                    },
                    {
                      "label": {
                        "en_US": "Morocco",
                        "pt_BR": "Marrocos",
                        "zh_Hans": "摩洛哥"
                      },
                      "value": "MA"
                    },
                    {
                      "label": {
                        "en_US": "Mozambique",
                        "pt_BR": "Moçambique",
                        "zh_Hans": "莫桑比克"
                      },
                      "value": "MZ"
                    },
                    {
                      "label": {
                        "en_US": "Myanmar",
                        "pt_BR": "Mianmar",
                        "zh_Hans": "缅甸"
                      },
                      "value": "MM"
                    },
                    {
                      "label": {
                        "en_US": "Namibia",
                        "pt_BR": "Namíbia",
                        "zh_Hans": "纳米比亚"
                      },
                      "value": "NA"
                    },
                    {
                      "label": {
                        "en_US": "Nauru",
                        "pt_BR": "Nauru",
                        "zh_Hans": "瑙鲁"
                      },
                      "value": "NR"
                    },
                    {
                      "label": {
                        "en_US": "Nepal",
                        "pt_BR": "Nepal",
                        "zh_Hans": "尼泊尔"
                      },
                      "value": "NP"
                    },
                    {
                      "label": {
                        "en_US": "Netherlands",
                        "pt_BR": "Países Baixos",
                        "zh_Hans": "荷兰"
                      },
                      "value": "NL"
                    },
                    {
                      "label": {
                        "en_US": "Netherlands Antilles",
                        "pt_BR": "Antilhas Holandesas",
                        "zh_Hans": "荷属安的列斯"
                      },
                      "value": "AN"
                    },
                    {
                      "label": {
                        "en_US": "New Caledonia",
                        "pt_BR": "Nova Caledônia",
                        "zh_Hans": "新喀里多尼亚"
                      },
                      "value": "NC"
                    },
                    {
                      "label": {
                        "en_US": "New Zealand",
                        "pt_BR": "Nova Zelândia",
                        "zh_Hans": "新西兰"
                      },
                      "value": "NZ"
                    },
                    {
                      "label": {
                        "en_US": "Nicaragua",
                        "pt_BR": "Nicarágua",
                        "zh_Hans": "尼加拉瓜"
                      },
                      "value": "NI"
                    },
                    {
                      "label": {
                        "en_US": "Niger",
                        "pt_BR": "Níger",
                        "zh_Hans": "尼日尔"
                      },
                      "value": "NE"
                    },
                    {
                      "label": {
                        "en_US": "Nigeria",
                        "pt_BR": "Nigéria",
                        "zh_Hans": "尼日利亚"
                      },
                      "value": "NG"
                    },
                    {
                      "label": {
                        "en_US": "Niue",
                        "pt_BR": "Niue",
                        "zh_Hans": "纽埃"
                      },
                      "value": "NU"
                    },
                    {
                      "label": {
                        "en_US": "Norfolk Island",
                        "pt_BR": "Ilha Norfolk",
                        "zh_Hans": "诺福克岛"
                      },
                      "value": "NF"
                    },
                    {
                      "label": {
                        "en_US": "Northern Mariana Islands",
                        "pt_BR": "Ilhas Marianas do Norte",
                        "zh_Hans": "北马里亚纳群岛"
                      },
                      "value": "MP"
                    },
                    {
                      "label": {
                        "en_US": "Norway",
                        "pt_BR": "Noruega",
                        "zh_Hans": "挪威"
                      },
                      "value": "NO"
                    },
                    {
                      "label": {
                        "en_US": "Oman",
                        "pt_BR": "Omã",
                        "zh_Hans": "阿曼"
                      },
                      "value": "OM"
                    },
                    {
                      "label": {
                        "en_US": "Pakistan",
                        "pt_BR": "Paquistão",
                        "zh_Hans": "巴基斯坦"
                      },
                      "value": "PK"
                    },
                    {
                      "label": {
                        "en_US": "Palau",
                        "pt_BR": "Palau",
                        "zh_Hans": "帕劳"
                      },
                      "value": "PW"
                    },
                    {
                      "label": {
                        "en_US": "Palestinian Territory, Occupied",
                        "pt_BR": "Palestina, Território Ocupado",
                        "zh_Hans": "巴勒斯坦领土"
                      },
                      "value": "PS"
                    },
                    {
                      "label": {
                        "en_US": "Panama",
                        "pt_BR": "Panamá",
                        "zh_Hans": "巴拿马"
                      },
                      "value": "PA"
                    },
                    {
                      "label": {
                        "en_US": "Papua New Guinea",
                        "pt_BR": "Papua Nova Guiné",
                        "zh_Hans": "巴布亚新几内亚"
                      },
                      "value": "PG"
                    },
                    {
                      "label": {
                        "en_US": "Paraguay",
                        "pt_BR": "Paraguai",
                        "zh_Hans": "巴拉圭"
                      },
                      "value": "PY"
                    },
                    {
                      "label": {
                        "en_US": "Peru",
                        "pt_BR": "Peru",
                        "zh_Hans": "秘鲁"
                      },
                      "value": "PE"
                    },
                    {
                      "label": {
                        "en_US": "Philippines",
                        "pt_BR": "Filipinas",
                        "zh_Hans": "菲律宾"
                      },
                      "value": "PH"
                    },
                    {
                      "label": {
                        "en_US": "Pitcairn",
                        "pt_BR": "Pitcairn",
                        "zh_Hans": "皮特凯恩岛"
                      },
                      "value": "PN"
                    },
                    {
                      "label": {
                        "en_US": "Poland",
                        "pt_BR": "Polônia",
                        "zh_Hans": "波兰"
                      },
                      "value": "PL"
                    },
                    {
                      "label": {
                        "en_US": "Portugal",
                        "pt_BR": "Portugal",
                        "zh_Hans": "葡萄牙"
                      },
                      "value": "PT"
                    },
                    {
                      "label": {
                        "en_US": "Puerto Rico",
                        "pt_BR": "Porto Rico",
                        "zh_Hans": "波多黎各"
                      },
                      "value": "PR"
                    },
                    {
                      "label": {
                        "en_US": "Qatar",
                        "pt_BR": "Catar",
                        "zh_Hans": "卡塔尔"
                      },
                      "value": "QA"
                    },
                    {
                      "label": {
                        "en_US": "Reunion",
                        "pt_BR": "Reunião",
                        "zh_Hans": "留尼旺"
                      },
                      "value": "RE"
                    },
                    {
                      "label": {
                        "en_US": "Romania",
                        "pt_BR": "Romênia",
                        "zh_Hans": "罗马尼亚"
                      },
                      "value": "RO"
                    },
                    {
                      "label": {
                        "en_US": "Russian Federation",
                        "pt_BR": "Rússia",
                        "zh_Hans": "俄罗斯联邦"
                      },
                      "value": "RU"
                    },
                    {
                      "label": {
                        "en_US": "Rwanda",
                        "pt_BR": "Ruanda",
                        "zh_Hans": "卢旺达"
                      },
                      "value": "RW"
                    },
                    {
                      "label": {
                        "en_US": "Saint Helena",
                        "pt_BR": "Santa Helena",
                        "zh_Hans": "圣赫勒拿"
                      },
                      "value": "SH"
                    },
                    {
                      "label": {
                        "en_US": "Saint Kitts and Nevis",
                        "pt_BR": "São Cristóvão e Nevis",
                        "zh_Hans": "圣基茨和尼维斯"
                      },
                      "value": "KN"
                    },
                    {
                      "label": {
                        "en_US": "Saint Lucia",
                        "pt_BR": "Santa Lúcia",
                        "zh_Hans": "圣卢西亚"
                      },
                      "value": "LC"
                    },
                    {
                      "label": {
                        "en_US": "Saint Pierre and Miquelon",
                        "pt_BR": "São Pedro e Miquelon",
                        "zh_Hans": "圣皮埃尔和密克隆"
                      },
                      "value": "PM"
                    },
                    {
                      "label": {
                        "en_US": "Saint Vincent and the Grenadines",
                        "pt_BR": "São Vicente e Granadinas",
                        "zh_Hans": "圣文森特和格林纳丁斯"
                      },
                      "value": "VC"
                    },
                    {
                      "label": {
                        "en_US": "Samoa",
                        "pt_BR": "Samoa",
                        "zh_Hans": "萨摩亚"
                      },
                      "value": "WS"
                    },
                    {
                      "label": {
                        "en_US": "San Marino",
                        "pt_BR": "San Marino",
                        "zh_Hans": "圣马力诺"
                      },
                      "value": "SM"
                    },
                    {
                      "label": {
                        "en_US": "Sao Tome and Principe",
                        "pt_BR": "São Tomé e Príncipe",
                        "zh_Hans": "圣多美和普林西比"
                      },
                      "value": "ST"
                    },
                    {
                      "label": {
                        "en_US": "Saudi Arabia",
                        "pt_BR": "Arábia Saudita",
                        "zh_Hans": "沙特阿拉伯"
                      },
                      "value": "SA"
                    },
                    {
                      "label": {
                        "en_US": "Senegal",
                        "pt_BR": "Senegal",
                        "zh_Hans": "塞内加尔"
                      },
                      "value": "SN"
                    },
                    {
                      "label": {
                        "en_US": "Serbia and Montenegro",
                        "pt_BR": "Sérvia e Montenegro",
                        "zh_Hans": "塞尔维亚和黑山"
                      },
                      "value": "RS"
                    },
                    {
                      "label": {
                        "en_US": "Seychelles",
                        "pt_BR": "Seicheles",
                        "zh_Hans": "塞舌尔"
                      },
                      "value": "SC"
                    },
                    {
                      "label": {
                        "en_US": "Sierra Leone",
                        "pt_BR": "Serra Leoa",
                        "zh_Hans": "塞拉利昂"
                      },
                      "value": "SL"
                    },
                    {
                      "label": {
                        "en_US": "Singapore",
                        "pt_BR": "Singapura",
                        "zh_Hans": "新加坡"
                      },
                      "value": "SG"
                    },
                    {
                      "label": {
                        "en_US": "Slovakia",
                        "pt_BR": "Eslováquia",
                        "zh_Hans": "斯洛伐克"
                      },
                      "value": "SK"
                    },
                    {
                      "label": {
                        "en_US": "Slovenia",
                        "pt_BR": "Eslovênia",
                        "zh_Hans": "斯洛文尼亚"
                      },
                      "value": "SI"
                    },
                    {
                      "label": {
                        "en_US": "Solomon Islands",
                        "pt_BR": "Ilhas Salomão",
                        "zh_Hans": "所罗门群岛"
                      },
                      "value": "SB"
                    },
                    {
                      "label": {
                        "en_US": "Somalia",
                        "pt_BR": "Somália",
                        "zh_Hans": "索马里"
                      },
                      "value": "SO"
                    },
                    {
                      "label": {
                        "en_US": "South Africa",
                        "pt_BR": "África do Sul",
                        "zh_Hans": "南非"
                      },
                      "value": "ZA"
                    },
                    {
                      "label": {
                        "en_US": "South Georgia and the South Sandwich Islands",
                        "pt_BR": "Geórgia do Sul e Ilhas Sandwich do Sul",
                        "zh_Hans": "南乔治亚和南桑威奇群岛"
                      },
                      "value": "GS"
                    },
                    {
                      "label": {
                        "en_US": "Spain",
                        "pt_BR": "Espanha",
                        "zh_Hans": "西班牙"
                      },
                      "value": "ES"
                    },
                    {
                      "label": {
                        "en_US": "Sri Lanka",
                        "pt_BR": "Sri Lanka",
                        "zh_Hans": "斯里兰卡"
                      },
                      "value": "LK"
                    },
                    {
                      "label": {
                        "en_US": "Sudan",
                        "pt_BR": "Sudão",
                        "zh_Hans": "苏丹"
                      },
                      "value": "SD"
                    },
                    {
                      "label": {
                        "en_US": "Suriname",
                        "pt_BR": "Suriname",
                        "zh_Hans": "苏里南"
                      },
                      "value": "SR"
                    },
                    {
                      "label": {
                        "en_US": "Svalbard and Jan Mayen",
                        "pt_BR": "Svalbard e Jan Mayen",
                        "zh_Hans": "斯瓦尔巴特和扬马延岛"
                      },
                      "value": "SJ"
                    },
                    {
                      "label": {
                        "en_US": "Swaziland",
                        "pt_BR": "Essuatíni",
                        "zh_Hans": "斯威士兰"
                      },
                      "value": "SZ"
                    },
                    {
                      "label": {
                        "en_US": "Sweden",
                        "pt_BR": "Suécia",
                        "zh_Hans": "瑞典"
                      },
                      "value": "SE"
                    },
                    {
                      "label": {
                        "en_US": "Switzerland",
                        "pt_BR": "Suíça",
                        "zh_Hans": "瑞士"
                      },
                      "value": "CH"
                    },
                    {
                      "label": {
                        "en_US": "Syrian Arab Republic",
                        "pt_BR": "Síria",
                        "zh_Hans": "叙利亚"
                      },
                      "value": "SY"
                    },
                    {
                      "label": {
                        "en_US": "Taiwan, Province of China",
                        "pt_BR": "Taiwan",
                        "zh_Hans": "台湾"
                      },
                      "value": "TW"
                    },
                    {
                      "label": {
                        "en_US": "Tajikistan",
                        "pt_BR": "Tajiquistão",
                        "zh_Hans": "塔吉克斯坦"
                      },
                      "value": "TJ"
                    },
                    {
                      "label": {
                        "en_US": "Tanzania, United Republic of",
                        "pt_BR": "Tanzânia",
                        "zh_Hans": "坦桑尼亚联合共和国"
                      },
                      "value": "TZ"
                    },
                    {
                      "label": {
                        "en_US": "Thailand",
                        "pt_BR": "Tailândia",
                        "zh_Hans": "泰国"
                      },
                      "value": "TH"
                    },
                    {
                      "label": {
                        "en_US": "Timor-Leste",
                        "pt_BR": "Timor-Leste",
                        "zh_Hans": "东帝汶"
                      },
                      "value": "TL"
                    },
                    {
                      "label": {
                        "en_US": "Togo",
                        "pt_BR": "Togo",
                        "zh_Hans": "多哥"
                      },
                      "value": "TG"
                    },
                    {
                      "label": {
                        "en_US": "Tokelau",
                        "pt_BR": "Toquelau",
                        "zh_Hans": "托克劳"
                      },
                      "value": "TK"
                    },
                    {
                      "label": {
                        "en_US": "Tonga",
                        "pt_BR": "Tonga",
                        "zh_Hans": "汤加"
                      },
                      "value": "TO"
                    },
                    {
                      "label": {
                        "en_US": "Trinidad and Tobago",
                        "pt_BR": "Trindade e Tobago",
                        "zh_Hans": "特立尼达和多巴哥"
                      },
                      "value": "TT"
                    },
                    {
                      "label": {
                        "en_US": "Tunisia",
                        "pt_BR": "Tunísia",
                        "zh_Hans": "突尼斯"
                      },
                      "value": "TN"
                    },
                    {
                      "label": {
                        "en_US": "Turkey",
                        "pt_BR": "Turquia",
                        "zh_Hans": "土耳其"
                      },
                      "value": "TR"
                    },
                    {
                      "label": {
                        "en_US": "Turkmenistan",
                        "pt_BR": "Turcomenistão",
                        "zh_Hans": "土库曼斯坦"
                      },
                      "value": "TM"
                    },
                    {
                      "label": {
                        "en_US": "Turks and Caicos Islands",
                        "pt_BR": "Ilhas Turks e Caicos",
                        "zh_Hans": "特克斯和凯科斯群岛"
                      },
                      "value": "TC"
                    },
                    {
                      "label": {
                        "en_US": "Tuvalu",
                        "pt_BR": "Tuvalu",
                        "zh_Hans": "图瓦卢"
                      },
                      "value": "TV"
                    },
                    {
                      "label": {
                        "en_US": "Uganda",
                        "pt_BR": "Uganda",
                        "zh_Hans": "乌干达"
                      },
                      "value": "UG"
                    },
                    {
                      "label": {
                        "en_US": "Ukraine",
                        "pt_BR": "Ucrânia",
                        "zh_Hans": "乌克兰"
                      },
                      "value": "UA"
                    },
                    {
                      "label": {
                        "en_US": "United Arab Emirates",
                        "pt_BR": "Emirados Árabes Unidos",
                        "zh_Hans": "阿联酋"
                      },
                      "value": "AE"
                    },
                    {
                      "label": {
                        "en_US": "United Kingdom",
                        "pt_BR": "Reino Unido",
                        "zh_Hans": "英国"
                      },
                      "value": "UK"
                    },
                    {
                      "label": {
                        "en_US": "United Kingdom",
                        "pt_BR": "Reino Unido",
                        "zh_Hans": "英国"
                      },
                      "value": "GB"
                    },
                    {
                      "label": {
                        "en_US": "United States",
                        "pt_BR": "Estados Unidos",
                        "zh_Hans": "美国"
                      },
                      "value": "US"
                    },
                    {
                      "label": {
                        "en_US": "United States Minor Outlying Islands",
                        "pt_BR": "Ilhas Menores Distantes dos Estados Unidos",
                        "zh_Hans": "美国本土外小岛屿"
                      },
                      "value": "UM"
                    },
                    {
                      "label": {
                        "en_US": "Uruguay",
                        "pt_BR": "Uruguai",
                        "zh_Hans": "乌拉圭"
                      },
                      "value": "UY"
                    },
                    {
                      "label": {
                        "en_US": "Uzbekistan",
                        "pt_BR": "Uzbequistão",
                        "zh_Hans": "乌兹别克斯坦"
                      },
                      "value": "UZ"
                    },
                    {
                      "label": {
                        "en_US": "Vanuatu",
                        "pt_BR": "Vanuatu",
                        "zh_Hans": "瓦努阿图"
                      },
                      "value": "VU"
                    },
                    {
                      "label": {
                        "en_US": "Venezuela",
                        "pt_BR": "Venezuela",
                        "zh_Hans": "委内瑞拉"
                      },
                      "value": "VE"
                    },
                    {
                      "label": {
                        "en_US": "Viet Nam",
                        "pt_BR": "Vietnã",
                        "zh_Hans": "越南"
                      },
                      "value": "VN"
                    },
                    {
                      "label": {
                        "en_US": "Virgin Islands, British",
                        "pt_BR": "Ilhas Virgens Britânicas",
                        "zh_Hans": "英属维尔京群岛"
                      },
                      "value": "VG"
                    },
                    {
                      "label": {
                        "en_US": "Virgin Islands, U.S.",
                        "pt_BR": "Ilhas Virgens dos EUA",
                        "zh_Hans": "美属维尔京群岛"
                      },
                      "value": "VI"
                    },
                    {
                      "label": {
                        "en_US": "Wallis and Futuna",
                        "pt_BR": "Wallis e Futuna",
                        "zh_Hans": "瓦利斯和富图纳群岛"
                      },
                      "value": "WF"
                    },
                    {
                      "label": {
                        "en_US": "Western Sahara",
                        "pt_BR": "Saara Ocidental",
                        "zh_Hans": "西撒哈拉"
                      },
                      "value": "EH"
                    },
                    {
                      "label": {
                        "en_US": "Yemen",
                        "pt_BR": "Iémen",
                        "zh_Hans": "也门"
                      },
                      "value": "YE"
                    },
                    {
                      "label": {
                        "en_US": "Zambia",
                        "pt_BR": "Zâmbia",
                        "zh_Hans": "赞比亚"
                      },
                      "value": "ZM"
                    },
                    {
                      "label": {
                        "en_US": "Zimbabwe",
                        "pt_BR": "Zimbábue",
                        "zh_Hans": "津巴布韦"
                      },
                      "value": "ZW"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "en",
                  "form": "form",
                  "human_description": {
                    "en_US": "Defines the interface language of the search. Default is \"en\".",
                    "zh_Hans": "定义搜索的界面语言。默认为“en”。"
                  },
                  "label": {
                    "en_US": "Language",
                    "zh_Hans": "语言"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "hl",
                  "options": [
                    {
                      "label": {
                        "en_US": "Afrikaans",
                        "zh_Hans": "南非语"
                      },
                      "value": "af"
                    },
                    {
                      "label": {
                        "en_US": "Akan",
                        "zh_Hans": "阿坎语"
                      },
                      "value": "ak"
                    },
                    {
                      "label": {
                        "en_US": "Albanian",
                        "zh_Hans": "阿尔巴尼亚语"
                      },
                      "value": "sq"
                    },
                    {
                      "label": {
                        "en_US": "Samoa",
                        "zh_Hans": "萨摩亚语"
                      },
                      "value": "ws"
                    },
                    {
                      "label": {
                        "en_US": "Amharic",
                        "zh_Hans": "阿姆哈拉语"
                      },
                      "value": "am"
                    },
                    {
                      "label": {
                        "en_US": "Arabic",
                        "zh_Hans": "阿拉伯语"
                      },
                      "value": "ar"
                    },
                    {
                      "label": {
                        "en_US": "Armenian",
                        "zh_Hans": "亚美尼亚语"
                      },
                      "value": "hy"
                    },
                    {
                      "label": {
                        "en_US": "Azerbaijani",
                        "zh_Hans": "阿塞拜疆语"
                      },
                      "value": "az"
                    },
                    {
                      "label": {
                        "en_US": "Basque",
                        "zh_Hans": "巴斯克语"
                      },
                      "value": "eu"
                    },
                    {
                      "label": {
                        "en_US": "Belarusian",
                        "zh_Hans": "白俄罗斯语"
                      },
                      "value": "be"
                    },
                    {
                      "label": {
                        "en_US": "Bemba",
                        "zh_Hans": "班巴语"
                      },
                      "value": "bem"
                    },
                    {
                      "label": {
                        "en_US": "Bengali",
                        "zh_Hans": "孟加拉语"
                      },
                      "value": "bn"
                    },
                    {
                      "label": {
                        "en_US": "Bihari",
                        "zh_Hans": "比哈尔语"
                      },
                      "value": "bh"
                    },
                    {
                      "label": {
                        "en_US": "Bork, bork, bork!",
                        "zh_Hans": "博克语"
                      },
                      "value": "xx-bork"
                    },
                    {
                      "label": {
                        "en_US": "Bosnian",
                        "zh_Hans": "波斯尼亚语"
                      },
                      "value": "bs"
                    },
                    {
                      "label": {
                        "en_US": "Breton",
                        "zh_Hans": "布列塔尼语"
                      },
                      "value": "br"
                    },
                    {
                      "label": {
                        "en_US": "Bulgarian",
                        "zh_Hans": "保加利亚语"
                      },
                      "value": "bg"
                    },
                    {
                      "label": {
                        "en_US": "Bhutanese",
                        "zh_Hans": "不丹语"
                      },
                      "value": "bt"
                    },
                    {
                      "label": {
                        "en_US": "Cambodian",
                        "zh_Hans": "高棉语"
                      },
                      "value": "km"
                    },
                    {
                      "label": {
                        "en_US": "Catalan",
                        "zh_Hans": "加泰罗尼亚语"
                      },
                      "value": "ca"
                    },
                    {
                      "label": {
                        "en_US": "Cherokee",
                        "zh_Hans": "切罗基语"
                      },
                      "value": "chr"
                    },
                    {
                      "label": {
                        "en_US": "Chichewa",
                        "zh_Hans": "齐切瓦语"
                      },
                      "value": "ny"
                    },
                    {
                      "label": {
                        "en_US": "Chinese (Simplified)",
                        "zh_Hans": "中文（简体）"
                      },
                      "value": "zh-cn"
                    },
                    {
                      "label": {
                        "en_US": "Chinese (Traditional)",
                        "zh_Hans": "中文（繁体）"
                      },
                      "value": "zh-tw"
                    },
                    {
                      "label": {
                        "en_US": "Corsican",
                        "zh_Hans": "科西嘉语"
                      },
                      "value": "co"
                    },
                    {
                      "label": {
                        "en_US": "Croatian",
                        "zh_Hans": "克罗地亚语"
                      },
                      "value": "hr"
                    },
                    {
                      "label": {
                        "en_US": "Czech",
                        "zh_Hans": "捷克语"
                      },
                      "value": "cs"
                    },
                    {
                      "label": {
                        "en_US": "Danish",
                        "zh_Hans": "丹麦语"
                      },
                      "value": "da"
                    },
                    {
                      "label": {
                        "en_US": "Dutch",
                        "zh_Hans": "荷兰语"
                      },
                      "value": "nl"
                    },
                    {
                      "label": {
                        "en_US": "Elmer Fudd",
                        "zh_Hans": "艾尔默福德语"
                      },
                      "value": "xx-elmer"
                    },
                    {
                      "label": {
                        "en_US": "English",
                        "zh_Hans": "英语"
                      },
                      "value": "en"
                    },
                    {
                      "label": {
                        "en_US": "Esperanto",
                        "zh_Hans": "世界语"
                      },
                      "value": "eo"
                    },
                    {
                      "label": {
                        "en_US": "Estonian",
                        "zh_Hans": "爱沙尼亚语"
                      },
                      "value": "et"
                    },
                    {
                      "label": {
                        "en_US": "Ewe",
                        "zh_Hans": "埃维语"
                      },
                      "value": "ee"
                    },
                    {
                      "label": {
                        "en_US": "Faroese",
                        "zh_Hans": "法罗语"
                      },
                      "value": "fo"
                    },
                    {
                      "label": {
                        "en_US": "Filipino",
                        "zh_Hans": "菲律宾语"
                      },
                      "value": "tl"
                    },
                    {
                      "label": {
                        "en_US": "Finnish",
                        "zh_Hans": "芬兰语"
                      },
                      "value": "fi"
                    },
                    {
                      "label": {
                        "en_US": "French",
                        "zh_Hans": "法语"
                      },
                      "value": "fr"
                    },
                    {
                      "label": {
                        "en_US": "Frisian",
                        "zh_Hans": "弗里西亚语"
                      },
                      "value": "fy"
                    },
                    {
                      "label": {
                        "en_US": "Ga",
                        "zh_Hans": "加语"
                      },
                      "value": "gaa"
                    },
                    {
                      "label": {
                        "en_US": "Galician",
                        "zh_Hans": "加利西亚语"
                      },
                      "value": "gl"
                    },
                    {
                      "label": {
                        "en_US": "Georgian",
                        "zh_Hans": "格鲁吉亚语"
                      },
                      "value": "ka"
                    },
                    {
                      "label": {
                        "en_US": "German",
                        "zh_Hans": "德语"
                      },
                      "value": "de"
                    },
                    {
                      "label": {
                        "en_US": "Greek",
                        "zh_Hans": "希腊语"
                      },
                      "value": "el"
                    },
                    {
                      "label": {
                        "en_US": "Greenlandic",
                        "zh_Hans": "格陵兰语"
                      },
                      "value": "kl"
                    },
                    {
                      "label": {
                        "en_US": "Guarani",
                        "zh_Hans": "瓜拉尼语"
                      },
                      "value": "gn"
                    },
                    {
                      "label": {
                        "en_US": "Gujarati",
                        "zh_Hans": "古吉拉特语"
                      },
                      "value": "gu"
                    },
                    {
                      "label": {
                        "en_US": "Hacker",
                        "zh_Hans": "黑客语"
                      },
                      "value": "xx-hacker"
                    },
                    {
                      "label": {
                        "en_US": "Haitian Creole",
                        "zh_Hans": "海地克里奥尔语"
                      },
                      "value": "ht"
                    },
                    {
                      "label": {
                        "en_US": "Hausa",
                        "zh_Hans": "豪萨语"
                      },
                      "value": "ha"
                    },
                    {
                      "label": {
                        "en_US": "Hawaiian",
                        "zh_Hans": "夏威夷语"
                      },
                      "value": "haw"
                    },
                    {
                      "label": {
                        "en_US": "Hebrew",
                        "zh_Hans": "希伯来语"
                      },
                      "value": "iw"
                    },
                    {
                      "label": {
                        "en_US": "Hindi",
                        "zh_Hans": "印地语"
                      },
                      "value": "hi"
                    },
                    {
                      "label": {
                        "en_US": "Hungarian",
                        "zh_Hans": "匈牙利语"
                      },
                      "value": "hu"
                    },
                    {
                      "label": {
                        "en_US": "Icelandic",
                        "zh_Hans": "冰岛语"
                      },
                      "value": "is"
                    },
                    {
                      "label": {
                        "en_US": "Igbo",
                        "zh_Hans": "伊博语"
                      },
                      "value": "ig"
                    },
                    {
                      "label": {
                        "en_US": "Indonesian",
                        "zh_Hans": "印尼语"
                      },
                      "value": "id"
                    },
                    {
                      "label": {
                        "en_US": "Interlingua",
                        "zh_Hans": "国际语"
                      },
                      "value": "ia"
                    },
                    {
                      "label": {
                        "en_US": "Irish",
                        "zh_Hans": "爱尔兰语"
                      },
                      "value": "ga"
                    },
                    {
                      "label": {
                        "en_US": "Italian",
                        "zh_Hans": "意大利语"
                      },
                      "value": "it"
                    },
                    {
                      "label": {
                        "en_US": "Japanese",
                        "zh_Hans": "日语"
                      },
                      "value": "ja"
                    },
                    {
                      "label": {
                        "en_US": "Javanese",
                        "zh_Hans": "爪哇语"
                      },
                      "value": "jw"
                    },
                    {
                      "label": {
                        "en_US": "Kannada",
                        "zh_Hans": "卡纳达语"
                      },
                      "value": "kn"
                    },
                    {
                      "label": {
                        "en_US": "Kazakh",
                        "zh_Hans": "哈萨克语"
                      },
                      "value": "kk"
                    },
                    {
                      "label": {
                        "en_US": "Kinyarwanda",
                        "zh_Hans": "基尼亚卢旺达语"
                      },
                      "value": "rw"
                    },
                    {
                      "label": {
                        "en_US": "Kirundi",
                        "zh_Hans": "基隆迪语"
                      },
                      "value": "rn"
                    },
                    {
                      "label": {
                        "en_US": "Klingon",
                        "zh_Hans": "克林贡语"
                      },
                      "value": "xx-klingon"
                    },
                    {
                      "label": {
                        "en_US": "Kongo",
                        "zh_Hans": "刚果语"
                      },
                      "value": "kg"
                    },
                    {
                      "label": {
                        "en_US": "Korean",
                        "zh_Hans": "韩语"
                      },
                      "value": "ko"
                    },
                    {
                      "label": {
                        "en_US": "Krio (Sierra Leone)",
                        "zh_Hans": "塞拉利昂克里奥尔语"
                      },
                      "value": "kri"
                    },
                    {
                      "label": {
                        "en_US": "Kurdish",
                        "zh_Hans": "库尔德语"
                      },
                      "value": "ku"
                    },
                    {
                      "label": {
                        "en_US": "Kurdish (Soranî)",
                        "zh_Hans": "库尔德语（索拉尼）"
                      },
                      "value": "ckb"
                    },
                    {
                      "label": {
                        "en_US": "Kyrgyz",
                        "zh_Hans": "吉尔吉斯语"
                      },
                      "value": "ky"
                    },
                    {
                      "label": {
                        "en_US": "Laothian",
                        "zh_Hans": "老挝语"
                      },
                      "value": "lo"
                    },
                    {
                      "label": {
                        "en_US": "Latin",
                        "zh_Hans": "拉丁语"
                      },
                      "value": "la"
                    },
                    {
                      "label": {
                        "en_US": "Latvian",
                        "zh_Hans": "拉脱维亚语"
                      },
                      "value": "lv"
                    },
                    {
                      "label": {
                        "en_US": "Lingala",
                        "zh_Hans": "林加拉语"
                      },
                      "value": "ln"
                    },
                    {
                      "label": {
                        "en_US": "Lithuanian",
                        "zh_Hans": "立陶宛语"
                      },
                      "value": "lt"
                    },
                    {
                      "label": {
                        "en_US": "Lozi",
                        "zh_Hans": "洛齐语"
                      },
                      "value": "loz"
                    },
                    {
                      "label": {
                        "en_US": "Luganda",
                        "zh_Hans": "卢干达语"
                      },
                      "value": "lg"
                    },
                    {
                      "label": {
                        "en_US": "Luo",
                        "zh_Hans": "卢奥语"
                      },
                      "value": "ach"
                    },
                    {
                      "label": {
                        "en_US": "Macedonian",
                        "zh_Hans": "马其顿语"
                      },
                      "value": "mk"
                    },
                    {
                      "label": {
                        "en_US": "Malagasy",
                        "zh_Hans": "马尔加什语"
                      },
                      "value": "mg"
                    },
                    {
                      "label": {
                        "en_US": "Malay",
                        "zh_Hans": "马来语"
                      },
                      "value": "my"
                    },
                    {
                      "label": {
                        "en_US": "Malayalam",
                        "zh_Hans": "马拉雅拉姆语"
                      },
                      "value": "ml"
                    },
                    {
                      "label": {
                        "en_US": "Maltese",
                        "zh_Hans": "马耳他语"
                      },
                      "value": "mt"
                    },
                    {
                      "label": {
                        "en_US": "Maldives",
                        "zh_Hans": "马尔代夫语"
                      },
                      "value": "mv"
                    },
                    {
                      "label": {
                        "en_US": "Maori",
                        "zh_Hans": "毛利语"
                      },
                      "value": "mi"
                    },
                    {
                      "label": {
                        "en_US": "Marathi",
                        "zh_Hans": "马拉地语"
                      },
                      "value": "mr"
                    },
                    {
                      "label": {
                        "en_US": "Mauritian Creole",
                        "zh_Hans": "毛里求斯克里奥尔语"
                      },
                      "value": "mfe"
                    },
                    {
                      "label": {
                        "en_US": "Moldavian",
                        "zh_Hans": "摩尔达维亚语"
                      },
                      "value": "mo"
                    },
                    {
                      "label": {
                        "en_US": "Mongolian",
                        "zh_Hans": "蒙古语"
                      },
                      "value": "mn"
                    },
                    {
                      "label": {
                        "en_US": "Montenegrin",
                        "zh_Hans": "黑山语"
                      },
                      "value": "sr-me"
                    },
                    {
                      "label": {
                        "en_US": "Nepali",
                        "zh_Hans": "尼泊尔语"
                      },
                      "value": "ne"
                    },
                    {
                      "label": {
                        "en_US": "Nigerian Pidgin",
                        "zh_Hans": "尼日利亚皮钦语"
                      },
                      "value": "pcm"
                    },
                    {
                      "label": {
                        "en_US": "Northern Sotho",
                        "zh_Hans": "北索托语"
                      },
                      "value": "nso"
                    },
                    {
                      "label": {
                        "en_US": "Norwegian",
                        "zh_Hans": "挪威语"
                      },
                      "value": "no"
                    },
                    {
                      "label": {
                        "en_US": "Norwegian (Nynorsk)",
                        "zh_Hans": "挪威语（尼诺斯克语）"
                      },
                      "value": "nn"
                    },
                    {
                      "label": {
                        "en_US": "Occitan",
                        "zh_Hans": "奥克语"
                      },
                      "value": "oc"
                    },
                    {
                      "label": {
                        "en_US": "Oriya",
                        "zh_Hans": "奥里亚语"
                      },
                      "value": "or"
                    },
                    {
                      "label": {
                        "en_US": "Oromo",
                        "zh_Hans": "奥罗莫语"
                      },
                      "value": "om"
                    },
                    {
                      "label": {
                        "en_US": "Pashto",
                        "zh_Hans": "普什图语"
                      },
                      "value": "ps"
                    },
                    {
                      "label": {
                        "en_US": "Persian",
                        "zh_Hans": "波斯语"
                      },
                      "value": "fa"
                    },
                    {
                      "label": {
                        "en_US": "Pirate",
                        "zh_Hans": "海盗语"
                      },
                      "value": "xx-pirate"
                    },
                    {
                      "label": {
                        "en_US": "Polish",
                        "zh_Hans": "波兰语"
                      },
                      "value": "pl"
                    },
                    {
                      "label": {
                        "en_US": "Portuguese",
                        "zh_Hans": "葡萄牙语"
                      },
                      "value": "pt"
                    },
                    {
                      "label": {
                        "en_US": "Portuguese (Brazil)",
                        "zh_Hans": "葡萄牙语（巴西）"
                      },
                      "value": "pt-br"
                    },
                    {
                      "label": {
                        "en_US": "Portuguese (Portugal)",
                        "zh_Hans": "葡萄牙语（葡萄牙）"
                      },
                      "value": "pt-pt"
                    },
                    {
                      "label": {
                        "en_US": "Punjabi",
                        "zh_Hans": "旁遮普语"
                      },
                      "value": "pa"
                    },
                    {
                      "label": {
                        "en_US": "Quechua",
                        "zh_Hans": "克丘亚语"
                      },
                      "value": "qu"
                    },
                    {
                      "label": {
                        "en_US": "Romanian",
                        "zh_Hans": "罗马尼亚语"
                      },
                      "value": "ro"
                    },
                    {
                      "label": {
                        "en_US": "Romansh",
                        "zh_Hans": "罗曼什语"
                      },
                      "value": "rm"
                    },
                    {
                      "label": {
                        "en_US": "Runyakitara",
                        "zh_Hans": "卢尼亚基塔拉语"
                      },
                      "value": "nyn"
                    },
                    {
                      "label": {
                        "en_US": "Russian",
                        "zh_Hans": "俄语"
                      },
                      "value": "ru"
                    },
                    {
                      "label": {
                        "en_US": "Scots Gaelic",
                        "zh_Hans": "苏格兰盖尔语"
                      },
                      "value": "gd"
                    },
                    {
                      "label": {
                        "en_US": "Serbian",
                        "zh_Hans": "塞尔维亚语"
                      },
                      "value": "sr"
                    },
                    {
                      "label": {
                        "en_US": "Serbo-Croatian",
                        "zh_Hans": "塞尔维亚-克罗地亚语"
                      },
                      "value": "sh"
                    },
                    {
                      "label": {
                        "en_US": "Sesotho",
                        "zh_Hans": "塞索托语"
                      },
                      "value": "st"
                    },
                    {
                      "label": {
                        "en_US": "Setswana",
                        "zh_Hans": "塞茨瓦纳语"
                      },
                      "value": "tn"
                    },
                    {
                      "label": {
                        "en_US": "Seychellois Creole",
                        "zh_Hans": "塞舌尔克里奥尔语"
                      },
                      "value": "crs"
                    },
                    {
                      "label": {
                        "en_US": "Shona",
                        "zh_Hans": "绍纳语"
                      },
                      "value": "sn"
                    },
                    {
                      "label": {
                        "en_US": "Sindhi",
                        "zh_Hans": "信德语"
                      },
                      "value": "sd"
                    },
                    {
                      "label": {
                        "en_US": "Sinhalese",
                        "zh_Hans": "僧伽罗语"
                      },
                      "value": "si"
                    },
                    {
                      "label": {
                        "en_US": "Slovak",
                        "zh_Hans": "斯洛伐克语"
                      },
                      "value": "sk"
                    },
                    {
                      "label": {
                        "en_US": "Slovenian",
                        "zh_Hans": "斯洛文尼亚语"
                      },
                      "value": "sl"
                    },
                    {
                      "label": {
                        "en_US": "Somali",
                        "zh_Hans": "索马里语"
                      },
                      "value": "so"
                    },
                    {
                      "label": {
                        "en_US": "Spanish",
                        "zh_Hans": "西班牙语"
                      },
                      "value": "es"
                    },
                    {
                      "label": {
                        "en_US": "Spanish (Latin American)",
                        "zh_Hans": "西班牙语（拉丁美洲）"
                      },
                      "value": "es-419"
                    },
                    {
                      "label": {
                        "en_US": "Sundanese",
                        "zh_Hans": "巽他语"
                      },
                      "value": "su"
                    },
                    {
                      "label": {
                        "en_US": "Swahili",
                        "zh_Hans": "斯瓦希里语"
                      },
                      "value": "sw"
                    },
                    {
                      "label": {
                        "en_US": "Swedish",
                        "zh_Hans": "瑞典语"
                      },
                      "value": "sv"
                    },
                    {
                      "label": {
                        "en_US": "Tajik",
                        "zh_Hans": "塔吉克语"
                      },
                      "value": "tg"
                    },
                    {
                      "label": {
                        "en_US": "Tamil",
                        "zh_Hans": "泰米尔语"
                      },
                      "value": "ta"
                    },
                    {
                      "label": {
                        "en_US": "Tatar",
                        "zh_Hans": "鞑靼语"
                      },
                      "value": "tt"
                    },
                    {
                      "label": {
                        "en_US": "Telugu",
                        "zh_Hans": "泰卢固语"
                      },
                      "value": "te"
                    },
                    {
                      "label": {
                        "en_US": "Thai",
                        "zh_Hans": "泰语"
                      },
                      "value": "th"
                    },
                    {
                      "label": {
                        "en_US": "Tigrinya",
                        "zh_Hans": "提格利尼亚语"
                      },
                      "value": "ti"
                    },
                    {
                      "label": {
                        "en_US": "Tonga",
                        "zh_Hans": "汤加语"
                      },
                      "value": "to"
                    },
                    {
                      "label": {
                        "en_US": "Tshiluba",
                        "zh_Hans": "卢巴语"
                      },
                      "value": "lua"
                    },
                    {
                      "label": {
                        "en_US": "Tumbuka",
                        "zh_Hans": "图布卡语"
                      },
                      "value": "tum"
                    },
                    {
                      "label": {
                        "en_US": "Turkish",
                        "zh_Hans": "土耳其语"
                      },
                      "value": "tr"
                    },
                    {
                      "label": {
                        "en_US": "Turkmen",
                        "zh_Hans": "土库曼语"
                      },
                      "value": "tk"
                    },
                    {
                      "label": {
                        "en_US": "Twi",
                        "zh_Hans": "契维语"
                      },
                      "value": "tw"
                    },
                    {
                      "label": {
                        "en_US": "Uighur",
                        "zh_Hans": "维吾尔语"
                      },
                      "value": "ug"
                    },
                    {
                      "label": {
                        "en_US": "Ukrainian",
                        "zh_Hans": "乌克兰语"
                      },
                      "value": "uk"
                    },
                    {
                      "label": {
                        "en_US": "Urdu",
                        "zh_Hans": "乌尔都语"
                      },
                      "value": "ur"
                    },
                    {
                      "label": {
                        "en_US": "Uzbek",
                        "zh_Hans": "乌兹别克语"
                      },
                      "value": "uz"
                    },
                    {
                      "label": {
                        "en_US": "Vanuatu",
                        "zh_Hans": "瓦努阿图语"
                      },
                      "value": "vu"
                    },
                    {
                      "label": {
                        "en_US": "Vietnamese",
                        "zh_Hans": "越南语"
                      },
                      "value": "vi"
                    },
                    {
                      "label": {
                        "en_US": "Welsh",
                        "zh_Hans": "威尔士语"
                      },
                      "value": "cy"
                    },
                    {
                      "label": {
                        "en_US": "Wolof",
                        "zh_Hans": "沃洛夫语"
                      },
                      "value": "wo"
                    },
                    {
                      "label": {
                        "en_US": "Xhosa",
                        "zh_Hans": "科萨语"
                      },
                      "value": "xh"
                    },
                    {
                      "label": {
                        "en_US": "Yiddish",
                        "zh_Hans": "意第绪语"
                      },
                      "value": "yi"
                    },
                    {
                      "label": {
                        "en_US": "Yoruba",
                        "zh_Hans": "约鲁巴语"
                      },
                      "value": "yo"
                    },
                    {
                      "label": {
                        "en_US": "Zulu",
                        "zh_Hans": "祖鲁语"
                      },
                      "value": "zu"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Defines the Google domain of the search. Default is \"google.com\".",
                    "zh_Hans": "定义搜索的 Google 域。默认为“google.com”。"
                  },
                  "label": {
                    "en_US": "google_domain",
                    "zh_Hans": "google_domain"
                  },
                  "llm_description": "Defines Google domain in which you want to search.",
                  "max": null,
                  "min": null,
                  "name": "google_domain",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Specifies the number of results to display per page. Default is 10. Max number - 100, min - 1.",
                    "pt_BR": "Specifies the number of results to display per page. Default is 10. Max number - 100, min - 1.",
                    "zh_Hans": "指定每页显示的结果数。默认值为 10。最大数量 - 100，最小数量 - 1。"
                  },
                  "label": {
                    "en_US": "num",
                    "zh_Hans": "num"
                  },
                  "llm_description": "Specifies the num of results to display per page.",
                  "max": null,
                  "min": null,
                  "name": "num",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool to retrieve transcripts from the specific YouTube video.",
                  "zh_Hans": "一种从特定 YouTube 视频检索文字记录的工具。"
                },
                "llm": "A tool to retrieve transcripts from the specific YouTube video."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "SearchApi",
                "label": {
                  "en_US": "YouTube Transcripts API",
                  "zh_Hans": "YouTube 脚本 API"
                },
                "name": "youtube_transcripts_api"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Used to define the video you want to search. You can find the video id's in YouTube page that appears in URL. For example - https://www.youtube.com/watch?v=video_id.",
                    "zh_Hans": "用于定义要搜索的视频。您可以在 URL 中显示的 YouTube 页面中找到视频 ID。例如 - https://www.youtube.com/watch?v=video_id。"
                  },
                  "label": {
                    "en_US": "video_id",
                    "zh_Hans": "视频ID"
                  },
                  "llm_description": "Used to define the video you want to search.",
                  "max": null,
                  "min": null,
                  "name": "video_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Used to set the language for transcripts. The default value is \"en\". You can find all supported languages in SearchApi documentation.",
                    "zh_Hans": "用于设置成绩单的语言。默认值为“en”。您可以在 SearchApi 文档中找到所有支持的语言。"
                  },
                  "label": {
                    "en_US": "language",
                    "zh_Hans": "语言"
                  },
                  "llm_description": "Used to set the language for transcripts.",
                  "max": null,
                  "min": null,
                  "name": "language",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool to retrieve answer boxes, knowledge graphs, snippets, and webpages from Google Search engine.",
                  "zh_Hans": "一种从 Google 搜索引擎检索答案框、知识图、片段和网页的工具。"
                },
                "llm": "A tool to retrieve answer boxes, knowledge graphs, snippets, and webpages from Google Search engine."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "SearchApi",
                "label": {
                  "en_US": "Google Search API",
                  "zh_Hans": "Google Search API"
                },
                "name": "google_search_api"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Defines the query you want to search.",
                    "zh_Hans": "定义您要搜索的查询。"
                  },
                  "label": {
                    "en_US": "Query",
                    "zh_Hans": "询问"
                  },
                  "llm_description": "Defines the search query you want to search.",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "text",
                  "form": "form",
                  "human_description": {
                    "en_US": "used for selecting the result type, text or link",
                    "zh_Hans": "用于选择结果类型，使用文本还是链接进行展示"
                  },
                  "label": {
                    "en_US": "Result type",
                    "zh_Hans": "结果类型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "result_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "text",
                        "zh_Hans": "文本"
                      },
                      "value": "text"
                    },
                    {
                      "label": {
                        "en_US": "link",
                        "zh_Hans": "链接"
                      },
                      "value": "link"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Defines from where you want the search to originate. (For example - New York)",
                    "zh_Hans": "定义您想要搜索的起始位置。 （例如 - 纽约）"
                  },
                  "label": {
                    "en_US": "Location",
                    "zh_Hans": "询问"
                  },
                  "llm_description": "Defines from where you want the search to originate. (For example - New York)",
                  "max": null,
                  "min": null,
                  "name": "location",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "US",
                  "form": "form",
                  "human_description": {
                    "en_US": "Defines the country of the search. Default is \"US\".",
                    "zh_Hans": "定义搜索的国家/地区。默认为“美国”。"
                  },
                  "label": {
                    "en_US": "Country",
                    "zh_Hans": "国家"
                  },
                  "llm_description": "Defines the gl parameter of the Google search.",
                  "max": null,
                  "min": null,
                  "name": "gl",
                  "options": [
                    {
                      "label": {
                        "en_US": "Afghanistan",
                        "pt_BR": "Afeganistão",
                        "zh_Hans": "阿富汗"
                      },
                      "value": "AF"
                    },
                    {
                      "label": {
                        "en_US": "Albania",
                        "pt_BR": "Albânia",
                        "zh_Hans": "阿尔巴尼亚"
                      },
                      "value": "AL"
                    },
                    {
                      "label": {
                        "en_US": "Algeria",
                        "pt_BR": "Argélia",
                        "zh_Hans": "阿尔及利亚"
                      },
                      "value": "DZ"
                    },
                    {
                      "label": {
                        "en_US": "American Samoa",
                        "pt_BR": "Samoa Americana",
                        "zh_Hans": "美属萨摩亚"
                      },
                      "value": "AS"
                    },
                    {
                      "label": {
                        "en_US": "Andorra",
                        "pt_BR": "Andorra",
                        "zh_Hans": "安道尔"
                      },
                      "value": "AD"
                    },
                    {
                      "label": {
                        "en_US": "Angola",
                        "pt_BR": "Angola",
                        "zh_Hans": "安哥拉"
                      },
                      "value": "AO"
                    },
                    {
                      "label": {
                        "en_US": "Anguilla",
                        "pt_BR": "Anguilla",
                        "zh_Hans": "安圭拉"
                      },
                      "value": "AI"
                    },
                    {
                      "label": {
                        "en_US": "Antarctica",
                        "pt_BR": "Antártica",
                        "zh_Hans": "南极洲"
                      },
                      "value": "AQ"
                    },
                    {
                      "label": {
                        "en_US": "Antigua and Barbuda",
                        "pt_BR": "Antígua e Barbuda",
                        "zh_Hans": "安提瓜和巴布达"
                      },
                      "value": "AG"
                    },
                    {
                      "label": {
                        "en_US": "Argentina",
                        "pt_BR": "Argentina",
                        "zh_Hans": "阿根廷"
                      },
                      "value": "AR"
                    },
                    {
                      "label": {
                        "en_US": "Armenia",
                        "pt_BR": "Armênia",
                        "zh_Hans": "亚美尼亚"
                      },
                      "value": "AM"
                    },
                    {
                      "label": {
                        "en_US": "Aruba",
                        "pt_BR": "Aruba",
                        "zh_Hans": "阿鲁巴"
                      },
                      "value": "AW"
                    },
                    {
                      "label": {
                        "en_US": "Australia",
                        "pt_BR": "Austrália",
                        "zh_Hans": "澳大利亚"
                      },
                      "value": "AU"
                    },
                    {
                      "label": {
                        "en_US": "Austria",
                        "pt_BR": "Áustria",
                        "zh_Hans": "奥地利"
                      },
                      "value": "AT"
                    },
                    {
                      "label": {
                        "en_US": "Azerbaijan",
                        "pt_BR": "Azerbaijão",
                        "zh_Hans": "阿塞拜疆"
                      },
                      "value": "AZ"
                    },
                    {
                      "label": {
                        "en_US": "Bahamas",
                        "pt_BR": "Bahamas",
                        "zh_Hans": "巴哈马"
                      },
                      "value": "BS"
                    },
                    {
                      "label": {
                        "en_US": "Bahrain",
                        "pt_BR": "Bahrein",
                        "zh_Hans": "巴林"
                      },
                      "value": "BH"
                    },
                    {
                      "label": {
                        "en_US": "Bangladesh",
                        "pt_BR": "Bangladesh",
                        "zh_Hans": "孟加拉国"
                      },
                      "value": "BD"
                    },
                    {
                      "label": {
                        "en_US": "Barbados",
                        "pt_BR": "Barbados",
                        "zh_Hans": "巴巴多斯"
                      },
                      "value": "BB"
                    },
                    {
                      "label": {
                        "en_US": "Belarus",
                        "pt_BR": "Bielorrússia",
                        "zh_Hans": "白俄罗斯"
                      },
                      "value": "BY"
                    },
                    {
                      "label": {
                        "en_US": "Belgium",
                        "pt_BR": "Bélgica",
                        "zh_Hans": "比利时"
                      },
                      "value": "BE"
                    },
                    {
                      "label": {
                        "en_US": "Belize",
                        "pt_BR": "Belize",
                        "zh_Hans": "伯利兹"
                      },
                      "value": "BZ"
                    },
                    {
                      "label": {
                        "en_US": "Benin",
                        "pt_BR": "Benim",
                        "zh_Hans": "贝宁"
                      },
                      "value": "BJ"
                    },
                    {
                      "label": {
                        "en_US": "Bermuda",
                        "pt_BR": "Bermudas",
                        "zh_Hans": "百慕大"
                      },
                      "value": "BM"
                    },
                    {
                      "label": {
                        "en_US": "Bhutan",
                        "pt_BR": "Butão",
                        "zh_Hans": "不丹"
                      },
                      "value": "BT"
                    },
                    {
                      "label": {
                        "en_US": "Bolivia",
                        "pt_BR": "Bolívia",
                        "zh_Hans": "玻利维亚"
                      },
                      "value": "BO"
                    },
                    {
                      "label": {
                        "en_US": "Bosnia and Herzegovina",
                        "pt_BR": "Bósnia e Herzegovina",
                        "zh_Hans": "波斯尼亚和黑塞哥维那"
                      },
                      "value": "BA"
                    },
                    {
                      "label": {
                        "en_US": "Botswana",
                        "pt_BR": "Botsuana",
                        "zh_Hans": "博茨瓦纳"
                      },
                      "value": "BW"
                    },
                    {
                      "label": {
                        "en_US": "Bouvet Island",
                        "pt_BR": "Ilha Bouvet",
                        "zh_Hans": "布韦岛"
                      },
                      "value": "BV"
                    },
                    {
                      "label": {
                        "en_US": "Brazil",
                        "pt_BR": "Brasil",
                        "zh_Hans": "巴西"
                      },
                      "value": "BR"
                    },
                    {
                      "label": {
                        "en_US": "British Indian Ocean Territory",
                        "pt_BR": "Território Britânico do Oceano Índico",
                        "zh_Hans": "英属印度洋领地"
                      },
                      "value": "IO"
                    },
                    {
                      "label": {
                        "en_US": "Brunei Darussalam",
                        "pt_BR": "Brunei Darussalam",
                        "zh_Hans": "文莱"
                      },
                      "value": "BN"
                    },
                    {
                      "label": {
                        "en_US": "Bulgaria",
                        "pt_BR": "Bulgária",
                        "zh_Hans": "保加利亚"
                      },
                      "value": "BG"
                    },
                    {
                      "label": {
                        "en_US": "Burkina Faso",
                        "pt_BR": "Burkina Faso",
                        "zh_Hans": "布基纳法索"
                      },
                      "value": "BF"
                    },
                    {
                      "label": {
                        "en_US": "Burundi",
                        "pt_BR": "Burundi",
                        "zh_Hans": "布隆迪"
                      },
                      "value": "BI"
                    },
                    {
                      "label": {
                        "en_US": "Cambodia",
                        "pt_BR": "Camboja",
                        "zh_Hans": "柬埔寨"
                      },
                      "value": "KH"
                    },
                    {
                      "label": {
                        "en_US": "Cameroon",
                        "pt_BR": "Camarões",
                        "zh_Hans": "喀麦隆"
                      },
                      "value": "CM"
                    },
                    {
                      "label": {
                        "en_US": "Canada",
                        "pt_BR": "Canadá",
                        "zh_Hans": "加拿大"
                      },
                      "value": "CA"
                    },
                    {
                      "label": {
                        "en_US": "Cape Verde",
                        "pt_BR": "Cabo Verde",
                        "zh_Hans": "佛得角"
                      },
                      "value": "CV"
                    },
                    {
                      "label": {
                        "en_US": "Cayman Islands",
                        "pt_BR": "Ilhas Cayman",
                        "zh_Hans": "开曼群岛"
                      },
                      "value": "KY"
                    },
                    {
                      "label": {
                        "en_US": "Central African Republic",
                        "pt_BR": "República Centro-Africana",
                        "zh_Hans": "中非共和国"
                      },
                      "value": "CF"
                    },
                    {
                      "label": {
                        "en_US": "Chad",
                        "pt_BR": "Chade",
                        "zh_Hans": "乍得"
                      },
                      "value": "TD"
                    },
                    {
                      "label": {
                        "en_US": "Chile",
                        "pt_BR": "Chile",
                        "zh_Hans": "智利"
                      },
                      "value": "CL"
                    },
                    {
                      "label": {
                        "en_US": "China",
                        "pt_BR": "China",
                        "zh_Hans": "中国"
                      },
                      "value": "CN"
                    },
                    {
                      "label": {
                        "en_US": "Christmas Island",
                        "pt_BR": "Ilha do Natal",
                        "zh_Hans": "圣诞岛"
                      },
                      "value": "CX"
                    },
                    {
                      "label": {
                        "en_US": "Cocos (Keeling) Islands",
                        "pt_BR": "Ilhas Cocos (Keeling)",
                        "zh_Hans": "科科斯（基林）群岛"
                      },
                      "value": "CC"
                    },
                    {
                      "label": {
                        "en_US": "Colombia",
                        "pt_BR": "Colômbia",
                        "zh_Hans": "哥伦比亚"
                      },
                      "value": "CO"
                    },
                    {
                      "label": {
                        "en_US": "Comoros",
                        "pt_BR": "Comores",
                        "zh_Hans": "科摩罗"
                      },
                      "value": "KM"
                    },
                    {
                      "label": {
                        "en_US": "Congo",
                        "pt_BR": "Congo",
                        "zh_Hans": "刚果"
                      },
                      "value": "CG"
                    },
                    {
                      "label": {
                        "en_US": "Congo, the Democratic Republic of the",
                        "pt_BR": "Congo, República Democrática do",
                        "zh_Hans": "刚果民主共和国"
                      },
                      "value": "CD"
                    },
                    {
                      "label": {
                        "en_US": "Cook Islands",
                        "pt_BR": "Ilhas Cook",
                        "zh_Hans": "库克群岛"
                      },
                      "value": "CK"
                    },
                    {
                      "label": {
                        "en_US": "Costa Rica",
                        "pt_BR": "Costa Rica",
                        "zh_Hans": "哥斯达黎加"
                      },
                      "value": "CR"
                    },
                    {
                      "label": {
                        "en_US": "Cote D'ivoire",
                        "pt_BR": "Costa do Marfim",
                        "zh_Hans": "科特迪瓦"
                      },
                      "value": "CI"
                    },
                    {
                      "label": {
                        "en_US": "Croatia",
                        "pt_BR": "Croácia",
                        "zh_Hans": "克罗地亚"
                      },
                      "value": "HR"
                    },
                    {
                      "label": {
                        "en_US": "Cuba",
                        "pt_BR": "Cuba",
                        "zh_Hans": "古巴"
                      },
                      "value": "CU"
                    },
                    {
                      "label": {
                        "en_US": "Cyprus",
                        "pt_BR": "Chipre",
                        "zh_Hans": "塞浦路斯"
                      },
                      "value": "CY"
                    },
                    {
                      "label": {
                        "en_US": "Czech Republic",
                        "pt_BR": "República Tcheca",
                        "zh_Hans": "捷克共和国"
                      },
                      "value": "CZ"
                    },
                    {
                      "label": {
                        "en_US": "Denmark",
                        "pt_BR": "Dinamarca",
                        "zh_Hans": "丹麦"
                      },
                      "value": "DK"
                    },
                    {
                      "label": {
                        "en_US": "Djibouti",
                        "pt_BR": "Djibuti",
                        "zh_Hans": "吉布提"
                      },
                      "value": "DJ"
                    },
                    {
                      "label": {
                        "en_US": "Dominica",
                        "pt_BR": "Dominica",
                        "zh_Hans": "多米尼克"
                      },
                      "value": "DM"
                    },
                    {
                      "label": {
                        "en_US": "Dominican Republic",
                        "pt_BR": "República Dominicana",
                        "zh_Hans": "多米尼加共和国"
                      },
                      "value": "DO"
                    },
                    {
                      "label": {
                        "en_US": "Ecuador",
                        "pt_BR": "Equador",
                        "zh_Hans": "厄瓜多尔"
                      },
                      "value": "EC"
                    },
                    {
                      "label": {
                        "en_US": "Egypt",
                        "pt_BR": "Egito",
                        "zh_Hans": "埃及"
                      },
                      "value": "EG"
                    },
                    {
                      "label": {
                        "en_US": "El Salvador",
                        "pt_BR": "El Salvador",
                        "zh_Hans": "萨尔瓦多"
                      },
                      "value": "SV"
                    },
                    {
                      "label": {
                        "en_US": "Equatorial Guinea",
                        "pt_BR": "Guiné Equatorial",
                        "zh_Hans": "赤道几内亚"
                      },
                      "value": "GQ"
                    },
                    {
                      "label": {
                        "en_US": "Eritrea",
                        "pt_BR": "Eritreia",
                        "zh_Hans": "厄立特里亚"
                      },
                      "value": "ER"
                    },
                    {
                      "label": {
                        "en_US": "Estonia",
                        "pt_BR": "Estônia",
                        "zh_Hans": "爱沙尼亚"
                      },
                      "value": "EE"
                    },
                    {
                      "label": {
                        "en_US": "Ethiopia",
                        "pt_BR": "Etiópia",
                        "zh_Hans": "埃塞俄比亚"
                      },
                      "value": "ET"
                    },
                    {
                      "label": {
                        "en_US": "Falkland Islands (Malvinas)",
                        "pt_BR": "Ilhas Falkland (Malvinas)",
                        "zh_Hans": "福克兰群岛（马尔维纳斯）"
                      },
                      "value": "FK"
                    },
                    {
                      "label": {
                        "en_US": "Faroe Islands",
                        "pt_BR": "Ilhas Faroe",
                        "zh_Hans": "法罗群岛"
                      },
                      "value": "FO"
                    },
                    {
                      "label": {
                        "en_US": "Fiji",
                        "pt_BR": "Fiji",
                        "zh_Hans": "斐济"
                      },
                      "value": "FJ"
                    },
                    {
                      "label": {
                        "en_US": "Finland",
                        "pt_BR": "Finlândia",
                        "zh_Hans": "芬兰"
                      },
                      "value": "FI"
                    },
                    {
                      "label": {
                        "en_US": "France",
                        "pt_BR": "França",
                        "zh_Hans": "法国"
                      },
                      "value": "FR"
                    },
                    {
                      "label": {
                        "en_US": "French Guiana",
                        "pt_BR": "Guiana Francesa",
                        "zh_Hans": "法属圭亚那"
                      },
                      "value": "GF"
                    },
                    {
                      "label": {
                        "en_US": "French Polynesia",
                        "pt_BR": "Polinésia Francesa",
                        "zh_Hans": "法属波利尼西亚"
                      },
                      "value": "PF"
                    },
                    {
                      "label": {
                        "en_US": "French Southern Territories",
                        "pt_BR": "Territórios Franceses do Sul",
                        "zh_Hans": "法属南部领地"
                      },
                      "value": "TF"
                    },
                    {
                      "label": {
                        "en_US": "Gabon",
                        "pt_BR": "Gabão",
                        "zh_Hans": "加蓬"
                      },
                      "value": "GA"
                    },
                    {
                      "label": {
                        "en_US": "Gambia",
                        "pt_BR": "Gâmbia",
                        "zh_Hans": "冈比亚"
                      },
                      "value": "GM"
                    },
                    {
                      "label": {
                        "en_US": "Georgia",
                        "pt_BR": "Geórgia",
                        "zh_Hans": "格鲁吉亚"
                      },
                      "value": "GE"
                    },
                    {
                      "label": {
                        "en_US": "Germany",
                        "pt_BR": "Alemanha",
                        "zh_Hans": "德国"
                      },
                      "value": "DE"
                    },
                    {
                      "label": {
                        "en_US": "Ghana",
                        "pt_BR": "Gana",
                        "zh_Hans": "加纳"
                      },
                      "value": "GH"
                    },
                    {
                      "label": {
                        "en_US": "Gibraltar",
                        "pt_BR": "Gibraltar",
                        "zh_Hans": "直布罗陀"
                      },
                      "value": "GI"
                    },
                    {
                      "label": {
                        "en_US": "Greece",
                        "pt_BR": "Grécia",
                        "zh_Hans": "希腊"
                      },
                      "value": "GR"
                    },
                    {
                      "label": {
                        "en_US": "Greenland",
                        "pt_BR": "Groenlândia",
                        "zh_Hans": "格陵兰"
                      },
                      "value": "GL"
                    },
                    {
                      "label": {
                        "en_US": "Grenada",
                        "pt_BR": "Granada",
                        "zh_Hans": "格林纳达"
                      },
                      "value": "GD"
                    },
                    {
                      "label": {
                        "en_US": "Guadeloupe",
                        "pt_BR": "Guadalupe",
                        "zh_Hans": "瓜德罗普"
                      },
                      "value": "GP"
                    },
                    {
                      "label": {
                        "en_US": "Guam",
                        "pt_BR": "Guam",
                        "zh_Hans": "关岛"
                      },
                      "value": "GU"
                    },
                    {
                      "label": {
                        "en_US": "Guatemala",
                        "pt_BR": "Guatemala",
                        "zh_Hans": "危地马拉"
                      },
                      "value": "GT"
                    },
                    {
                      "label": {
                        "en_US": "Guinea",
                        "pt_BR": "Guiné",
                        "zh_Hans": "几内亚"
                      },
                      "value": "GN"
                    },
                    {
                      "label": {
                        "en_US": "Guinea-Bissau",
                        "pt_BR": "Guiné-Bissau",
                        "zh_Hans": "几内亚比绍"
                      },
                      "value": "GW"
                    },
                    {
                      "label": {
                        "en_US": "Guyana",
                        "pt_BR": "Guiana",
                        "zh_Hans": "圭亚那"
                      },
                      "value": "GY"
                    },
                    {
                      "label": {
                        "en_US": "Haiti",
                        "pt_BR": "Haiti",
                        "zh_Hans": "海地"
                      },
                      "value": "HT"
                    },
                    {
                      "label": {
                        "en_US": "Heard Island and McDonald Islands",
                        "pt_BR": "Ilha Heard e Ilhas McDonald",
                        "zh_Hans": "赫德岛和麦克唐纳群岛"
                      },
                      "value": "HM"
                    },
                    {
                      "label": {
                        "en_US": "Holy See (Vatican City State)",
                        "pt_BR": "Santa Sé (Estado da Cidade do Vaticano)",
                        "zh_Hans": "教廷（梵蒂冈城国）"
                      },
                      "value": "VA"
                    },
                    {
                      "label": {
                        "en_US": "Honduras",
                        "pt_BR": "Honduras",
                        "zh_Hans": "洪都拉斯"
                      },
                      "value": "HN"
                    },
                    {
                      "label": {
                        "en_US": "Hong Kong",
                        "pt_BR": "Hong Kong",
                        "zh_Hans": "香港"
                      },
                      "value": "HK"
                    },
                    {
                      "label": {
                        "en_US": "Hungary",
                        "pt_BR": "Hungria",
                        "zh_Hans": "匈牙利"
                      },
                      "value": "HU"
                    },
                    {
                      "label": {
                        "en_US": "Iceland",
                        "pt_BR": "Islândia",
                        "zh_Hans": "冰岛"
                      },
                      "value": "IS"
                    },
                    {
                      "label": {
                        "en_US": "India",
                        "pt_BR": "Índia",
                        "zh_Hans": "印度"
                      },
                      "value": "IN"
                    },
                    {
                      "label": {
                        "en_US": "Indonesia",
                        "pt_BR": "Indonésia",
                        "zh_Hans": "印度尼西亚"
                      },
                      "value": "ID"
                    },
                    {
                      "label": {
                        "en_US": "Iran, Islamic Republic of",
                        "pt_BR": "Irã",
                        "zh_Hans": "伊朗"
                      },
                      "value": "IR"
                    },
                    {
                      "label": {
                        "en_US": "Iraq",
                        "pt_BR": "Iraque",
                        "zh_Hans": "伊拉克"
                      },
                      "value": "IQ"
                    },
                    {
                      "label": {
                        "en_US": "Ireland",
                        "pt_BR": "Irlanda",
                        "zh_Hans": "爱尔兰"
                      },
                      "value": "IE"
                    },
                    {
                      "label": {
                        "en_US": "Israel",
                        "pt_BR": "Israel",
                        "zh_Hans": "以色列"
                      },
                      "value": "IL"
                    },
                    {
                      "label": {
                        "en_US": "Italy",
                        "pt_BR": "Itália",
                        "zh_Hans": "意大利"
                      },
                      "value": "IT"
                    },
                    {
                      "label": {
                        "en_US": "Jamaica",
                        "pt_BR": "Jamaica",
                        "zh_Hans": "牙买加"
                      },
                      "value": "JM"
                    },
                    {
                      "label": {
                        "en_US": "Japan",
                        "pt_BR": "Japão",
                        "zh_Hans": "日本"
                      },
                      "value": "JP"
                    },
                    {
                      "label": {
                        "en_US": "Jordan",
                        "pt_BR": "Jordânia",
                        "zh_Hans": "约旦"
                      },
                      "value": "JO"
                    },
                    {
                      "label": {
                        "en_US": "Kazakhstan",
                        "pt_BR": "Cazaquistão",
                        "zh_Hans": "哈萨克斯坦"
                      },
                      "value": "KZ"
                    },
                    {
                      "label": {
                        "en_US": "Kenya",
                        "pt_BR": "Quênia",
                        "zh_Hans": "肯尼亚"
                      },
                      "value": "KE"
                    },
                    {
                      "label": {
                        "en_US": "Kiribati",
                        "pt_BR": "Kiribati",
                        "zh_Hans": "基里巴斯"
                      },
                      "value": "KI"
                    },
                    {
                      "label": {
                        "en_US": "Korea, Democratic People's Republic of",
                        "pt_BR": "Coreia, República Democrática Popular da",
                        "zh_Hans": "朝鲜"
                      },
                      "value": "KP"
                    },
                    {
                      "label": {
                        "en_US": "Korea, Republic of",
                        "pt_BR": "Coreia, República da",
                        "zh_Hans": "韩国"
                      },
                      "value": "KR"
                    },
                    {
                      "label": {
                        "en_US": "Kuwait",
                        "pt_BR": "Kuwait",
                        "zh_Hans": "科威特"
                      },
                      "value": "KW"
                    },
                    {
                      "label": {
                        "en_US": "Kyrgyzstan",
                        "pt_BR": "Quirguistão",
                        "zh_Hans": "吉尔吉斯斯坦"
                      },
                      "value": "KG"
                    },
                    {
                      "label": {
                        "en_US": "Lao People's Democratic Republic",
                        "pt_BR": "República Democrática Popular do Laos",
                        "zh_Hans": "老挝"
                      },
                      "value": "LA"
                    },
                    {
                      "label": {
                        "en_US": "Latvia",
                        "pt_BR": "Letônia",
                        "zh_Hans": "拉脱维亚"
                      },
                      "value": "LV"
                    },
                    {
                      "label": {
                        "en_US": "Lebanon",
                        "pt_BR": "Líbano",
                        "zh_Hans": "黎巴嫩"
                      },
                      "value": "LB"
                    },
                    {
                      "label": {
                        "en_US": "Lesotho",
                        "pt_BR": "Lesoto",
                        "zh_Hans": "莱索托"
                      },
                      "value": "LS"
                    },
                    {
                      "label": {
                        "en_US": "Liberia",
                        "pt_BR": "Libéria",
                        "zh_Hans": "利比里亚"
                      },
                      "value": "LR"
                    },
                    {
                      "label": {
                        "en_US": "Libyan Arab Jamahiriya",
                        "pt_BR": "Líbia",
                        "zh_Hans": "利比亚"
                      },
                      "value": "LY"
                    },
                    {
                      "label": {
                        "en_US": "Liechtenstein",
                        "pt_BR": "Liechtenstein",
                        "zh_Hans": "列支敦士登"
                      },
                      "value": "LI"
                    },
                    {
                      "label": {
                        "en_US": "Lithuania",
                        "pt_BR": "Lituânia",
                        "zh_Hans": "立陶宛"
                      },
                      "value": "LT"
                    },
                    {
                      "label": {
                        "en_US": "Luxembourg",
                        "pt_BR": "Luxemburgo",
                        "zh_Hans": "卢森堡"
                      },
                      "value": "LU"
                    },
                    {
                      "label": {
                        "en_US": "Macao",
                        "pt_BR": "Macau",
                        "zh_Hans": "澳门"
                      },
                      "value": "MO"
                    },
                    {
                      "label": {
                        "en_US": "Macedonia, the Former Yugosalv Republic of",
                        "pt_BR": "Macedônia, Ex-República Iugoslava da",
                        "zh_Hans": "前南斯拉夫马其顿共和国"
                      },
                      "value": "MK"
                    },
                    {
                      "label": {
                        "en_US": "Madagascar",
                        "pt_BR": "Madagascar",
                        "zh_Hans": "马达加斯加"
                      },
                      "value": "MG"
                    },
                    {
                      "label": {
                        "en_US": "Malawi",
                        "pt_BR": "Malaui",
                        "zh_Hans": "马拉维"
                      },
                      "value": "MW"
                    },
                    {
                      "label": {
                        "en_US": "Malaysia",
                        "pt_BR": "Malásia",
                        "zh_Hans": "马来西亚"
                      },
                      "value": "MY"
                    },
                    {
                      "label": {
                        "en_US": "Maldives",
                        "pt_BR": "Maldivas",
                        "zh_Hans": "马尔代夫"
                      },
                      "value": "MV"
                    },
                    {
                      "label": {
                        "en_US": "Mali",
                        "pt_BR": "Mali",
                        "zh_Hans": "马里"
                      },
                      "value": "ML"
                    },
                    {
                      "label": {
                        "en_US": "Malta",
                        "pt_BR": "Malta",
                        "zh_Hans": "马耳他"
                      },
                      "value": "MT"
                    },
                    {
                      "label": {
                        "en_US": "Marshall Islands",
                        "pt_BR": "Ilhas Marshall",
                        "zh_Hans": "马绍尔群岛"
                      },
                      "value": "MH"
                    },
                    {
                      "label": {
                        "en_US": "Martinique",
                        "pt_BR": "Martinica",
                        "zh_Hans": "马提尼克"
                      },
                      "value": "MQ"
                    },
                    {
                      "label": {
                        "en_US": "Mauritania",
                        "pt_BR": "Mauritânia",
                        "zh_Hans": "毛里塔尼亚"
                      },
                      "value": "MR"
                    },
                    {
                      "label": {
                        "en_US": "Mauritius",
                        "pt_BR": "Maurício",
                        "zh_Hans": "毛里求斯"
                      },
                      "value": "MU"
                    },
                    {
                      "label": {
                        "en_US": "Mayotte",
                        "pt_BR": "Mayotte",
                        "zh_Hans": "马约特"
                      },
                      "value": "YT"
                    },
                    {
                      "label": {
                        "en_US": "Mexico",
                        "pt_BR": "México",
                        "zh_Hans": "墨西哥"
                      },
                      "value": "MX"
                    },
                    {
                      "label": {
                        "en_US": "Micronesia, Federated States of",
                        "pt_BR": "Micronésia, Estados Federados da",
                        "zh_Hans": "密克罗尼西亚联邦"
                      },
                      "value": "FM"
                    },
                    {
                      "label": {
                        "en_US": "Moldova, Republic of",
                        "pt_BR": "Moldávia, República da",
                        "zh_Hans": "摩尔多瓦共和国"
                      },
                      "value": "MD"
                    },
                    {
                      "label": {
                        "en_US": "Monaco",
                        "pt_BR": "Mônaco",
                        "zh_Hans": "摩纳哥"
                      },
                      "value": "MC"
                    },
                    {
                      "label": {
                        "en_US": "Mongolia",
                        "pt_BR": "Mongólia",
                        "zh_Hans": "蒙古"
                      },
                      "value": "MN"
                    },
                    {
                      "label": {
                        "en_US": "Montserrat",
                        "pt_BR": "Montserrat",
                        "zh_Hans": "蒙特塞拉特"
                      },
                      "value": "MS"
                    },
                    {
                      "label": {
                        "en_US": "Morocco",
                        "pt_BR": "Marrocos",
                        "zh_Hans": "摩洛哥"
                      },
                      "value": "MA"
                    },
                    {
                      "label": {
                        "en_US": "Mozambique",
                        "pt_BR": "Moçambique",
                        "zh_Hans": "莫桑比克"
                      },
                      "value": "MZ"
                    },
                    {
                      "label": {
                        "en_US": "Myanmar",
                        "pt_BR": "Mianmar",
                        "zh_Hans": "缅甸"
                      },
                      "value": "MM"
                    },
                    {
                      "label": {
                        "en_US": "Namibia",
                        "pt_BR": "Namíbia",
                        "zh_Hans": "纳米比亚"
                      },
                      "value": "NA"
                    },
                    {
                      "label": {
                        "en_US": "Nauru",
                        "pt_BR": "Nauru",
                        "zh_Hans": "瑙鲁"
                      },
                      "value": "NR"
                    },
                    {
                      "label": {
                        "en_US": "Nepal",
                        "pt_BR": "Nepal",
                        "zh_Hans": "尼泊尔"
                      },
                      "value": "NP"
                    },
                    {
                      "label": {
                        "en_US": "Netherlands",
                        "pt_BR": "Países Baixos",
                        "zh_Hans": "荷兰"
                      },
                      "value": "NL"
                    },
                    {
                      "label": {
                        "en_US": "Netherlands Antilles",
                        "pt_BR": "Antilhas Holandesas",
                        "zh_Hans": "荷属安的列斯"
                      },
                      "value": "AN"
                    },
                    {
                      "label": {
                        "en_US": "New Caledonia",
                        "pt_BR": "Nova Caledônia",
                        "zh_Hans": "新喀里多尼亚"
                      },
                      "value": "NC"
                    },
                    {
                      "label": {
                        "en_US": "New Zealand",
                        "pt_BR": "Nova Zelândia",
                        "zh_Hans": "新西兰"
                      },
                      "value": "NZ"
                    },
                    {
                      "label": {
                        "en_US": "Nicaragua",
                        "pt_BR": "Nicarágua",
                        "zh_Hans": "尼加拉瓜"
                      },
                      "value": "NI"
                    },
                    {
                      "label": {
                        "en_US": "Niger",
                        "pt_BR": "Níger",
                        "zh_Hans": "尼日尔"
                      },
                      "value": "NE"
                    },
                    {
                      "label": {
                        "en_US": "Nigeria",
                        "pt_BR": "Nigéria",
                        "zh_Hans": "尼日利亚"
                      },
                      "value": "NG"
                    },
                    {
                      "label": {
                        "en_US": "Niue",
                        "pt_BR": "Niue",
                        "zh_Hans": "纽埃"
                      },
                      "value": "NU"
                    },
                    {
                      "label": {
                        "en_US": "Norfolk Island",
                        "pt_BR": "Ilha Norfolk",
                        "zh_Hans": "诺福克岛"
                      },
                      "value": "NF"
                    },
                    {
                      "label": {
                        "en_US": "Northern Mariana Islands",
                        "pt_BR": "Ilhas Marianas do Norte",
                        "zh_Hans": "北马里亚纳群岛"
                      },
                      "value": "MP"
                    },
                    {
                      "label": {
                        "en_US": "Norway",
                        "pt_BR": "Noruega",
                        "zh_Hans": "挪威"
                      },
                      "value": "NO"
                    },
                    {
                      "label": {
                        "en_US": "Oman",
                        "pt_BR": "Omã",
                        "zh_Hans": "阿曼"
                      },
                      "value": "OM"
                    },
                    {
                      "label": {
                        "en_US": "Pakistan",
                        "pt_BR": "Paquistão",
                        "zh_Hans": "巴基斯坦"
                      },
                      "value": "PK"
                    },
                    {
                      "label": {
                        "en_US": "Palau",
                        "pt_BR": "Palau",
                        "zh_Hans": "帕劳"
                      },
                      "value": "PW"
                    },
                    {
                      "label": {
                        "en_US": "Palestinian Territory, Occupied",
                        "pt_BR": "Palestina, Território Ocupado",
                        "zh_Hans": "巴勒斯坦领土"
                      },
                      "value": "PS"
                    },
                    {
                      "label": {
                        "en_US": "Panama",
                        "pt_BR": "Panamá",
                        "zh_Hans": "巴拿马"
                      },
                      "value": "PA"
                    },
                    {
                      "label": {
                        "en_US": "Papua New Guinea",
                        "pt_BR": "Papua Nova Guiné",
                        "zh_Hans": "巴布亚新几内亚"
                      },
                      "value": "PG"
                    },
                    {
                      "label": {
                        "en_US": "Paraguay",
                        "pt_BR": "Paraguai",
                        "zh_Hans": "巴拉圭"
                      },
                      "value": "PY"
                    },
                    {
                      "label": {
                        "en_US": "Peru",
                        "pt_BR": "Peru",
                        "zh_Hans": "秘鲁"
                      },
                      "value": "PE"
                    },
                    {
                      "label": {
                        "en_US": "Philippines",
                        "pt_BR": "Filipinas",
                        "zh_Hans": "菲律宾"
                      },
                      "value": "PH"
                    },
                    {
                      "label": {
                        "en_US": "Pitcairn",
                        "pt_BR": "Pitcairn",
                        "zh_Hans": "皮特凯恩岛"
                      },
                      "value": "PN"
                    },
                    {
                      "label": {
                        "en_US": "Poland",
                        "pt_BR": "Polônia",
                        "zh_Hans": "波兰"
                      },
                      "value": "PL"
                    },
                    {
                      "label": {
                        "en_US": "Portugal",
                        "pt_BR": "Portugal",
                        "zh_Hans": "葡萄牙"
                      },
                      "value": "PT"
                    },
                    {
                      "label": {
                        "en_US": "Puerto Rico",
                        "pt_BR": "Porto Rico",
                        "zh_Hans": "波多黎各"
                      },
                      "value": "PR"
                    },
                    {
                      "label": {
                        "en_US": "Qatar",
                        "pt_BR": "Catar",
                        "zh_Hans": "卡塔尔"
                      },
                      "value": "QA"
                    },
                    {
                      "label": {
                        "en_US": "Reunion",
                        "pt_BR": "Reunião",
                        "zh_Hans": "留尼旺"
                      },
                      "value": "RE"
                    },
                    {
                      "label": {
                        "en_US": "Romania",
                        "pt_BR": "Romênia",
                        "zh_Hans": "罗马尼亚"
                      },
                      "value": "RO"
                    },
                    {
                      "label": {
                        "en_US": "Russian Federation",
                        "pt_BR": "Rússia",
                        "zh_Hans": "俄罗斯联邦"
                      },
                      "value": "RU"
                    },
                    {
                      "label": {
                        "en_US": "Rwanda",
                        "pt_BR": "Ruanda",
                        "zh_Hans": "卢旺达"
                      },
                      "value": "RW"
                    },
                    {
                      "label": {
                        "en_US": "Saint Helena",
                        "pt_BR": "Santa Helena",
                        "zh_Hans": "圣赫勒拿"
                      },
                      "value": "SH"
                    },
                    {
                      "label": {
                        "en_US": "Saint Kitts and Nevis",
                        "pt_BR": "São Cristóvão e Nevis",
                        "zh_Hans": "圣基茨和尼维斯"
                      },
                      "value": "KN"
                    },
                    {
                      "label": {
                        "en_US": "Saint Lucia",
                        "pt_BR": "Santa Lúcia",
                        "zh_Hans": "圣卢西亚"
                      },
                      "value": "LC"
                    },
                    {
                      "label": {
                        "en_US": "Saint Pierre and Miquelon",
                        "pt_BR": "São Pedro e Miquelon",
                        "zh_Hans": "圣皮埃尔和密克隆"
                      },
                      "value": "PM"
                    },
                    {
                      "label": {
                        "en_US": "Saint Vincent and the Grenadines",
                        "pt_BR": "São Vicente e Granadinas",
                        "zh_Hans": "圣文森特和格林纳丁斯"
                      },
                      "value": "VC"
                    },
                    {
                      "label": {
                        "en_US": "Samoa",
                        "pt_BR": "Samoa",
                        "zh_Hans": "萨摩亚"
                      },
                      "value": "WS"
                    },
                    {
                      "label": {
                        "en_US": "San Marino",
                        "pt_BR": "San Marino",
                        "zh_Hans": "圣马力诺"
                      },
                      "value": "SM"
                    },
                    {
                      "label": {
                        "en_US": "Sao Tome and Principe",
                        "pt_BR": "São Tomé e Príncipe",
                        "zh_Hans": "圣多美和普林西比"
                      },
                      "value": "ST"
                    },
                    {
                      "label": {
                        "en_US": "Saudi Arabia",
                        "pt_BR": "Arábia Saudita",
                        "zh_Hans": "沙特阿拉伯"
                      },
                      "value": "SA"
                    },
                    {
                      "label": {
                        "en_US": "Senegal",
                        "pt_BR": "Senegal",
                        "zh_Hans": "塞内加尔"
                      },
                      "value": "SN"
                    },
                    {
                      "label": {
                        "en_US": "Serbia and Montenegro",
                        "pt_BR": "Sérvia e Montenegro",
                        "zh_Hans": "塞尔维亚和黑山"
                      },
                      "value": "RS"
                    },
                    {
                      "label": {
                        "en_US": "Seychelles",
                        "pt_BR": "Seicheles",
                        "zh_Hans": "塞舌尔"
                      },
                      "value": "SC"
                    },
                    {
                      "label": {
                        "en_US": "Sierra Leone",
                        "pt_BR": "Serra Leoa",
                        "zh_Hans": "塞拉利昂"
                      },
                      "value": "SL"
                    },
                    {
                      "label": {
                        "en_US": "Singapore",
                        "pt_BR": "Singapura",
                        "zh_Hans": "新加坡"
                      },
                      "value": "SG"
                    },
                    {
                      "label": {
                        "en_US": "Slovakia",
                        "pt_BR": "Eslováquia",
                        "zh_Hans": "斯洛伐克"
                      },
                      "value": "SK"
                    },
                    {
                      "label": {
                        "en_US": "Slovenia",
                        "pt_BR": "Eslovênia",
                        "zh_Hans": "斯洛文尼亚"
                      },
                      "value": "SI"
                    },
                    {
                      "label": {
                        "en_US": "Solomon Islands",
                        "pt_BR": "Ilhas Salomão",
                        "zh_Hans": "所罗门群岛"
                      },
                      "value": "SB"
                    },
                    {
                      "label": {
                        "en_US": "Somalia",
                        "pt_BR": "Somália",
                        "zh_Hans": "索马里"
                      },
                      "value": "SO"
                    },
                    {
                      "label": {
                        "en_US": "South Africa",
                        "pt_BR": "África do Sul",
                        "zh_Hans": "南非"
                      },
                      "value": "ZA"
                    },
                    {
                      "label": {
                        "en_US": "South Georgia and the South Sandwich Islands",
                        "pt_BR": "Geórgia do Sul e Ilhas Sandwich do Sul",
                        "zh_Hans": "南乔治亚和南桑威奇群岛"
                      },
                      "value": "GS"
                    },
                    {
                      "label": {
                        "en_US": "Spain",
                        "pt_BR": "Espanha",
                        "zh_Hans": "西班牙"
                      },
                      "value": "ES"
                    },
                    {
                      "label": {
                        "en_US": "Sri Lanka",
                        "pt_BR": "Sri Lanka",
                        "zh_Hans": "斯里兰卡"
                      },
                      "value": "LK"
                    },
                    {
                      "label": {
                        "en_US": "Sudan",
                        "pt_BR": "Sudão",
                        "zh_Hans": "苏丹"
                      },
                      "value": "SD"
                    },
                    {
                      "label": {
                        "en_US": "Suriname",
                        "pt_BR": "Suriname",
                        "zh_Hans": "苏里南"
                      },
                      "value": "SR"
                    },
                    {
                      "label": {
                        "en_US": "Svalbard and Jan Mayen",
                        "pt_BR": "Svalbard e Jan Mayen",
                        "zh_Hans": "斯瓦尔巴特和扬马延岛"
                      },
                      "value": "SJ"
                    },
                    {
                      "label": {
                        "en_US": "Swaziland",
                        "pt_BR": "Essuatíni",
                        "zh_Hans": "斯威士兰"
                      },
                      "value": "SZ"
                    },
                    {
                      "label": {
                        "en_US": "Sweden",
                        "pt_BR": "Suécia",
                        "zh_Hans": "瑞典"
                      },
                      "value": "SE"
                    },
                    {
                      "label": {
                        "en_US": "Switzerland",
                        "pt_BR": "Suíça",
                        "zh_Hans": "瑞士"
                      },
                      "value": "CH"
                    },
                    {
                      "label": {
                        "en_US": "Syrian Arab Republic",
                        "pt_BR": "Síria",
                        "zh_Hans": "叙利亚"
                      },
                      "value": "SY"
                    },
                    {
                      "label": {
                        "en_US": "Taiwan, Province of China",
                        "pt_BR": "Taiwan",
                        "zh_Hans": "台湾"
                      },
                      "value": "TW"
                    },
                    {
                      "label": {
                        "en_US": "Tajikistan",
                        "pt_BR": "Tajiquistão",
                        "zh_Hans": "塔吉克斯坦"
                      },
                      "value": "TJ"
                    },
                    {
                      "label": {
                        "en_US": "Tanzania, United Republic of",
                        "pt_BR": "Tanzânia",
                        "zh_Hans": "坦桑尼亚联合共和国"
                      },
                      "value": "TZ"
                    },
                    {
                      "label": {
                        "en_US": "Thailand",
                        "pt_BR": "Tailândia",
                        "zh_Hans": "泰国"
                      },
                      "value": "TH"
                    },
                    {
                      "label": {
                        "en_US": "Timor-Leste",
                        "pt_BR": "Timor-Leste",
                        "zh_Hans": "东帝汶"
                      },
                      "value": "TL"
                    },
                    {
                      "label": {
                        "en_US": "Togo",
                        "pt_BR": "Togo",
                        "zh_Hans": "多哥"
                      },
                      "value": "TG"
                    },
                    {
                      "label": {
                        "en_US": "Tokelau",
                        "pt_BR": "Toquelau",
                        "zh_Hans": "托克劳"
                      },
                      "value": "TK"
                    },
                    {
                      "label": {
                        "en_US": "Tonga",
                        "pt_BR": "Tonga",
                        "zh_Hans": "汤加"
                      },
                      "value": "TO"
                    },
                    {
                      "label": {
                        "en_US": "Trinidad and Tobago",
                        "pt_BR": "Trindade e Tobago",
                        "zh_Hans": "特立尼达和多巴哥"
                      },
                      "value": "TT"
                    },
                    {
                      "label": {
                        "en_US": "Tunisia",
                        "pt_BR": "Tunísia",
                        "zh_Hans": "突尼斯"
                      },
                      "value": "TN"
                    },
                    {
                      "label": {
                        "en_US": "Turkey",
                        "pt_BR": "Turquia",
                        "zh_Hans": "土耳其"
                      },
                      "value": "TR"
                    },
                    {
                      "label": {
                        "en_US": "Turkmenistan",
                        "pt_BR": "Turcomenistão",
                        "zh_Hans": "土库曼斯坦"
                      },
                      "value": "TM"
                    },
                    {
                      "label": {
                        "en_US": "Turks and Caicos Islands",
                        "pt_BR": "Ilhas Turks e Caicos",
                        "zh_Hans": "特克斯和凯科斯群岛"
                      },
                      "value": "TC"
                    },
                    {
                      "label": {
                        "en_US": "Tuvalu",
                        "pt_BR": "Tuvalu",
                        "zh_Hans": "图瓦卢"
                      },
                      "value": "TV"
                    },
                    {
                      "label": {
                        "en_US": "Uganda",
                        "pt_BR": "Uganda",
                        "zh_Hans": "乌干达"
                      },
                      "value": "UG"
                    },
                    {
                      "label": {
                        "en_US": "Ukraine",
                        "pt_BR": "Ucrânia",
                        "zh_Hans": "乌克兰"
                      },
                      "value": "UA"
                    },
                    {
                      "label": {
                        "en_US": "United Arab Emirates",
                        "pt_BR": "Emirados Árabes Unidos",
                        "zh_Hans": "阿联酋"
                      },
                      "value": "AE"
                    },
                    {
                      "label": {
                        "en_US": "United Kingdom",
                        "pt_BR": "Reino Unido",
                        "zh_Hans": "英国"
                      },
                      "value": "UK"
                    },
                    {
                      "label": {
                        "en_US": "United Kingdom",
                        "pt_BR": "Reino Unido",
                        "zh_Hans": "英国"
                      },
                      "value": "GB"
                    },
                    {
                      "label": {
                        "en_US": "United States",
                        "pt_BR": "Estados Unidos",
                        "zh_Hans": "美国"
                      },
                      "value": "US"
                    },
                    {
                      "label": {
                        "en_US": "United States Minor Outlying Islands",
                        "pt_BR": "Ilhas Menores Distantes dos Estados Unidos",
                        "zh_Hans": "美国本土外小岛屿"
                      },
                      "value": "UM"
                    },
                    {
                      "label": {
                        "en_US": "Uruguay",
                        "pt_BR": "Uruguai",
                        "zh_Hans": "乌拉圭"
                      },
                      "value": "UY"
                    },
                    {
                      "label": {
                        "en_US": "Uzbekistan",
                        "pt_BR": "Uzbequistão",
                        "zh_Hans": "乌兹别克斯坦"
                      },
                      "value": "UZ"
                    },
                    {
                      "label": {
                        "en_US": "Vanuatu",
                        "pt_BR": "Vanuatu",
                        "zh_Hans": "瓦努阿图"
                      },
                      "value": "VU"
                    },
                    {
                      "label": {
                        "en_US": "Venezuela",
                        "pt_BR": "Venezuela",
                        "zh_Hans": "委内瑞拉"
                      },
                      "value": "VE"
                    },
                    {
                      "label": {
                        "en_US": "Viet Nam",
                        "pt_BR": "Vietnã",
                        "zh_Hans": "越南"
                      },
                      "value": "VN"
                    },
                    {
                      "label": {
                        "en_US": "Virgin Islands, British",
                        "pt_BR": "Ilhas Virgens Britânicas",
                        "zh_Hans": "英属维尔京群岛"
                      },
                      "value": "VG"
                    },
                    {
                      "label": {
                        "en_US": "Virgin Islands, U.S.",
                        "pt_BR": "Ilhas Virgens dos EUA",
                        "zh_Hans": "美属维尔京群岛"
                      },
                      "value": "VI"
                    },
                    {
                      "label": {
                        "en_US": "Wallis and Futuna",
                        "pt_BR": "Wallis e Futuna",
                        "zh_Hans": "瓦利斯和富图纳群岛"
                      },
                      "value": "WF"
                    },
                    {
                      "label": {
                        "en_US": "Western Sahara",
                        "pt_BR": "Saara Ocidental",
                        "zh_Hans": "西撒哈拉"
                      },
                      "value": "EH"
                    },
                    {
                      "label": {
                        "en_US": "Yemen",
                        "pt_BR": "Iémen",
                        "zh_Hans": "也门"
                      },
                      "value": "YE"
                    },
                    {
                      "label": {
                        "en_US": "Zambia",
                        "pt_BR": "Zâmbia",
                        "zh_Hans": "赞比亚"
                      },
                      "value": "ZM"
                    },
                    {
                      "label": {
                        "en_US": "Zimbabwe",
                        "pt_BR": "Zimbábue",
                        "zh_Hans": "津巴布韦"
                      },
                      "value": "ZW"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "en",
                  "form": "form",
                  "human_description": {
                    "en_US": "Defines the interface language of the search. Default is \"en\".",
                    "zh_Hans": "定义搜索的界面语言。默认为“en”。"
                  },
                  "label": {
                    "en_US": "Language",
                    "zh_Hans": "语言"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "hl",
                  "options": [
                    {
                      "label": {
                        "en_US": "Afrikaans",
                        "zh_Hans": "南非语"
                      },
                      "value": "af"
                    },
                    {
                      "label": {
                        "en_US": "Akan",
                        "zh_Hans": "阿坎语"
                      },
                      "value": "ak"
                    },
                    {
                      "label": {
                        "en_US": "Albanian",
                        "zh_Hans": "阿尔巴尼亚语"
                      },
                      "value": "sq"
                    },
                    {
                      "label": {
                        "en_US": "Samoa",
                        "zh_Hans": "萨摩亚语"
                      },
                      "value": "ws"
                    },
                    {
                      "label": {
                        "en_US": "Amharic",
                        "zh_Hans": "阿姆哈拉语"
                      },
                      "value": "am"
                    },
                    {
                      "label": {
                        "en_US": "Arabic",
                        "zh_Hans": "阿拉伯语"
                      },
                      "value": "ar"
                    },
                    {
                      "label": {
                        "en_US": "Armenian",
                        "zh_Hans": "亚美尼亚语"
                      },
                      "value": "hy"
                    },
                    {
                      "label": {
                        "en_US": "Azerbaijani",
                        "zh_Hans": "阿塞拜疆语"
                      },
                      "value": "az"
                    },
                    {
                      "label": {
                        "en_US": "Basque",
                        "zh_Hans": "巴斯克语"
                      },
                      "value": "eu"
                    },
                    {
                      "label": {
                        "en_US": "Belarusian",
                        "zh_Hans": "白俄罗斯语"
                      },
                      "value": "be"
                    },
                    {
                      "label": {
                        "en_US": "Bemba",
                        "zh_Hans": "班巴语"
                      },
                      "value": "bem"
                    },
                    {
                      "label": {
                        "en_US": "Bengali",
                        "zh_Hans": "孟加拉语"
                      },
                      "value": "bn"
                    },
                    {
                      "label": {
                        "en_US": "Bihari",
                        "zh_Hans": "比哈尔语"
                      },
                      "value": "bh"
                    },
                    {
                      "label": {
                        "en_US": "Bork, bork, bork!",
                        "zh_Hans": "博克语"
                      },
                      "value": "xx-bork"
                    },
                    {
                      "label": {
                        "en_US": "Bosnian",
                        "zh_Hans": "波斯尼亚语"
                      },
                      "value": "bs"
                    },
                    {
                      "label": {
                        "en_US": "Breton",
                        "zh_Hans": "布列塔尼语"
                      },
                      "value": "br"
                    },
                    {
                      "label": {
                        "en_US": "Bulgarian",
                        "zh_Hans": "保加利亚语"
                      },
                      "value": "bg"
                    },
                    {
                      "label": {
                        "en_US": "Bhutanese",
                        "zh_Hans": "不丹语"
                      },
                      "value": "bt"
                    },
                    {
                      "label": {
                        "en_US": "Cambodian",
                        "zh_Hans": "高棉语"
                      },
                      "value": "km"
                    },
                    {
                      "label": {
                        "en_US": "Catalan",
                        "zh_Hans": "加泰罗尼亚语"
                      },
                      "value": "ca"
                    },
                    {
                      "label": {
                        "en_US": "Cherokee",
                        "zh_Hans": "切罗基语"
                      },
                      "value": "chr"
                    },
                    {
                      "label": {
                        "en_US": "Chichewa",
                        "zh_Hans": "齐切瓦语"
                      },
                      "value": "ny"
                    },
                    {
                      "label": {
                        "en_US": "Chinese (Simplified)",
                        "zh_Hans": "中文（简体）"
                      },
                      "value": "zh-cn"
                    },
                    {
                      "label": {
                        "en_US": "Chinese (Traditional)",
                        "zh_Hans": "中文（繁体）"
                      },
                      "value": "zh-tw"
                    },
                    {
                      "label": {
                        "en_US": "Corsican",
                        "zh_Hans": "科西嘉语"
                      },
                      "value": "co"
                    },
                    {
                      "label": {
                        "en_US": "Croatian",
                        "zh_Hans": "克罗地亚语"
                      },
                      "value": "hr"
                    },
                    {
                      "label": {
                        "en_US": "Czech",
                        "zh_Hans": "捷克语"
                      },
                      "value": "cs"
                    },
                    {
                      "label": {
                        "en_US": "Danish",
                        "zh_Hans": "丹麦语"
                      },
                      "value": "da"
                    },
                    {
                      "label": {
                        "en_US": "Dutch",
                        "zh_Hans": "荷兰语"
                      },
                      "value": "nl"
                    },
                    {
                      "label": {
                        "en_US": "Elmer Fudd",
                        "zh_Hans": "艾尔默福德语"
                      },
                      "value": "xx-elmer"
                    },
                    {
                      "label": {
                        "en_US": "English",
                        "zh_Hans": "英语"
                      },
                      "value": "en"
                    },
                    {
                      "label": {
                        "en_US": "Esperanto",
                        "zh_Hans": "世界语"
                      },
                      "value": "eo"
                    },
                    {
                      "label": {
                        "en_US": "Estonian",
                        "zh_Hans": "爱沙尼亚语"
                      },
                      "value": "et"
                    },
                    {
                      "label": {
                        "en_US": "Ewe",
                        "zh_Hans": "埃维语"
                      },
                      "value": "ee"
                    },
                    {
                      "label": {
                        "en_US": "Faroese",
                        "zh_Hans": "法罗语"
                      },
                      "value": "fo"
                    },
                    {
                      "label": {
                        "en_US": "Filipino",
                        "zh_Hans": "菲律宾语"
                      },
                      "value": "tl"
                    },
                    {
                      "label": {
                        "en_US": "Finnish",
                        "zh_Hans": "芬兰语"
                      },
                      "value": "fi"
                    },
                    {
                      "label": {
                        "en_US": "French",
                        "zh_Hans": "法语"
                      },
                      "value": "fr"
                    },
                    {
                      "label": {
                        "en_US": "Frisian",
                        "zh_Hans": "弗里西亚语"
                      },
                      "value": "fy"
                    },
                    {
                      "label": {
                        "en_US": "Ga",
                        "zh_Hans": "加语"
                      },
                      "value": "gaa"
                    },
                    {
                      "label": {
                        "en_US": "Galician",
                        "zh_Hans": "加利西亚语"
                      },
                      "value": "gl"
                    },
                    {
                      "label": {
                        "en_US": "Georgian",
                        "zh_Hans": "格鲁吉亚语"
                      },
                      "value": "ka"
                    },
                    {
                      "label": {
                        "en_US": "German",
                        "zh_Hans": "德语"
                      },
                      "value": "de"
                    },
                    {
                      "label": {
                        "en_US": "Greek",
                        "zh_Hans": "希腊语"
                      },
                      "value": "el"
                    },
                    {
                      "label": {
                        "en_US": "Greenlandic",
                        "zh_Hans": "格陵兰语"
                      },
                      "value": "kl"
                    },
                    {
                      "label": {
                        "en_US": "Guarani",
                        "zh_Hans": "瓜拉尼语"
                      },
                      "value": "gn"
                    },
                    {
                      "label": {
                        "en_US": "Gujarati",
                        "zh_Hans": "古吉拉特语"
                      },
                      "value": "gu"
                    },
                    {
                      "label": {
                        "en_US": "Hacker",
                        "zh_Hans": "黑客语"
                      },
                      "value": "xx-hacker"
                    },
                    {
                      "label": {
                        "en_US": "Haitian Creole",
                        "zh_Hans": "海地克里奥尔语"
                      },
                      "value": "ht"
                    },
                    {
                      "label": {
                        "en_US": "Hausa",
                        "zh_Hans": "豪萨语"
                      },
                      "value": "ha"
                    },
                    {
                      "label": {
                        "en_US": "Hawaiian",
                        "zh_Hans": "夏威夷语"
                      },
                      "value": "haw"
                    },
                    {
                      "label": {
                        "en_US": "Hebrew",
                        "zh_Hans": "希伯来语"
                      },
                      "value": "iw"
                    },
                    {
                      "label": {
                        "en_US": "Hindi",
                        "zh_Hans": "印地语"
                      },
                      "value": "hi"
                    },
                    {
                      "label": {
                        "en_US": "Hungarian",
                        "zh_Hans": "匈牙利语"
                      },
                      "value": "hu"
                    },
                    {
                      "label": {
                        "en_US": "Icelandic",
                        "zh_Hans": "冰岛语"
                      },
                      "value": "is"
                    },
                    {
                      "label": {
                        "en_US": "Igbo",
                        "zh_Hans": "伊博语"
                      },
                      "value": "ig"
                    },
                    {
                      "label": {
                        "en_US": "Indonesian",
                        "zh_Hans": "印尼语"
                      },
                      "value": "id"
                    },
                    {
                      "label": {
                        "en_US": "Interlingua",
                        "zh_Hans": "国际语"
                      },
                      "value": "ia"
                    },
                    {
                      "label": {
                        "en_US": "Irish",
                        "zh_Hans": "爱尔兰语"
                      },
                      "value": "ga"
                    },
                    {
                      "label": {
                        "en_US": "Italian",
                        "zh_Hans": "意大利语"
                      },
                      "value": "it"
                    },
                    {
                      "label": {
                        "en_US": "Japanese",
                        "zh_Hans": "日语"
                      },
                      "value": "ja"
                    },
                    {
                      "label": {
                        "en_US": "Javanese",
                        "zh_Hans": "爪哇语"
                      },
                      "value": "jw"
                    },
                    {
                      "label": {
                        "en_US": "Kannada",
                        "zh_Hans": "卡纳达语"
                      },
                      "value": "kn"
                    },
                    {
                      "label": {
                        "en_US": "Kazakh",
                        "zh_Hans": "哈萨克语"
                      },
                      "value": "kk"
                    },
                    {
                      "label": {
                        "en_US": "Kinyarwanda",
                        "zh_Hans": "基尼亚卢旺达语"
                      },
                      "value": "rw"
                    },
                    {
                      "label": {
                        "en_US": "Kirundi",
                        "zh_Hans": "基隆迪语"
                      },
                      "value": "rn"
                    },
                    {
                      "label": {
                        "en_US": "Klingon",
                        "zh_Hans": "克林贡语"
                      },
                      "value": "xx-klingon"
                    },
                    {
                      "label": {
                        "en_US": "Kongo",
                        "zh_Hans": "刚果语"
                      },
                      "value": "kg"
                    },
                    {
                      "label": {
                        "en_US": "Korean",
                        "zh_Hans": "韩语"
                      },
                      "value": "ko"
                    },
                    {
                      "label": {
                        "en_US": "Krio (Sierra Leone)",
                        "zh_Hans": "塞拉利昂克里奥尔语"
                      },
                      "value": "kri"
                    },
                    {
                      "label": {
                        "en_US": "Kurdish",
                        "zh_Hans": "库尔德语"
                      },
                      "value": "ku"
                    },
                    {
                      "label": {
                        "en_US": "Kurdish (Soranî)",
                        "zh_Hans": "库尔德语（索拉尼）"
                      },
                      "value": "ckb"
                    },
                    {
                      "label": {
                        "en_US": "Kyrgyz",
                        "zh_Hans": "吉尔吉斯语"
                      },
                      "value": "ky"
                    },
                    {
                      "label": {
                        "en_US": "Laothian",
                        "zh_Hans": "老挝语"
                      },
                      "value": "lo"
                    },
                    {
                      "label": {
                        "en_US": "Latin",
                        "zh_Hans": "拉丁语"
                      },
                      "value": "la"
                    },
                    {
                      "label": {
                        "en_US": "Latvian",
                        "zh_Hans": "拉脱维亚语"
                      },
                      "value": "lv"
                    },
                    {
                      "label": {
                        "en_US": "Lingala",
                        "zh_Hans": "林加拉语"
                      },
                      "value": "ln"
                    },
                    {
                      "label": {
                        "en_US": "Lithuanian",
                        "zh_Hans": "立陶宛语"
                      },
                      "value": "lt"
                    },
                    {
                      "label": {
                        "en_US": "Lozi",
                        "zh_Hans": "洛齐语"
                      },
                      "value": "loz"
                    },
                    {
                      "label": {
                        "en_US": "Luganda",
                        "zh_Hans": "卢干达语"
                      },
                      "value": "lg"
                    },
                    {
                      "label": {
                        "en_US": "Luo",
                        "zh_Hans": "卢奥语"
                      },
                      "value": "ach"
                    },
                    {
                      "label": {
                        "en_US": "Macedonian",
                        "zh_Hans": "马其顿语"
                      },
                      "value": "mk"
                    },
                    {
                      "label": {
                        "en_US": "Malagasy",
                        "zh_Hans": "马尔加什语"
                      },
                      "value": "mg"
                    },
                    {
                      "label": {
                        "en_US": "Malay",
                        "zh_Hans": "马来语"
                      },
                      "value": "my"
                    },
                    {
                      "label": {
                        "en_US": "Malayalam",
                        "zh_Hans": "马拉雅拉姆语"
                      },
                      "value": "ml"
                    },
                    {
                      "label": {
                        "en_US": "Maltese",
                        "zh_Hans": "马耳他语"
                      },
                      "value": "mt"
                    },
                    {
                      "label": {
                        "en_US": "Maldives",
                        "zh_Hans": "马尔代夫语"
                      },
                      "value": "mv"
                    },
                    {
                      "label": {
                        "en_US": "Maori",
                        "zh_Hans": "毛利语"
                      },
                      "value": "mi"
                    },
                    {
                      "label": {
                        "en_US": "Marathi",
                        "zh_Hans": "马拉地语"
                      },
                      "value": "mr"
                    },
                    {
                      "label": {
                        "en_US": "Mauritian Creole",
                        "zh_Hans": "毛里求斯克里奥尔语"
                      },
                      "value": "mfe"
                    },
                    {
                      "label": {
                        "en_US": "Moldavian",
                        "zh_Hans": "摩尔达维亚语"
                      },
                      "value": "mo"
                    },
                    {
                      "label": {
                        "en_US": "Mongolian",
                        "zh_Hans": "蒙古语"
                      },
                      "value": "mn"
                    },
                    {
                      "label": {
                        "en_US": "Montenegrin",
                        "zh_Hans": "黑山语"
                      },
                      "value": "sr-me"
                    },
                    {
                      "label": {
                        "en_US": "Nepali",
                        "zh_Hans": "尼泊尔语"
                      },
                      "value": "ne"
                    },
                    {
                      "label": {
                        "en_US": "Nigerian Pidgin",
                        "zh_Hans": "尼日利亚皮钦语"
                      },
                      "value": "pcm"
                    },
                    {
                      "label": {
                        "en_US": "Northern Sotho",
                        "zh_Hans": "北索托语"
                      },
                      "value": "nso"
                    },
                    {
                      "label": {
                        "en_US": "Norwegian",
                        "zh_Hans": "挪威语"
                      },
                      "value": "no"
                    },
                    {
                      "label": {
                        "en_US": "Norwegian (Nynorsk)",
                        "zh_Hans": "挪威语（尼诺斯克语）"
                      },
                      "value": "nn"
                    },
                    {
                      "label": {
                        "en_US": "Occitan",
                        "zh_Hans": "奥克语"
                      },
                      "value": "oc"
                    },
                    {
                      "label": {
                        "en_US": "Oriya",
                        "zh_Hans": "奥里亚语"
                      },
                      "value": "or"
                    },
                    {
                      "label": {
                        "en_US": "Oromo",
                        "zh_Hans": "奥罗莫语"
                      },
                      "value": "om"
                    },
                    {
                      "label": {
                        "en_US": "Pashto",
                        "zh_Hans": "普什图语"
                      },
                      "value": "ps"
                    },
                    {
                      "label": {
                        "en_US": "Persian",
                        "zh_Hans": "波斯语"
                      },
                      "value": "fa"
                    },
                    {
                      "label": {
                        "en_US": "Pirate",
                        "zh_Hans": "海盗语"
                      },
                      "value": "xx-pirate"
                    },
                    {
                      "label": {
                        "en_US": "Polish",
                        "zh_Hans": "波兰语"
                      },
                      "value": "pl"
                    },
                    {
                      "label": {
                        "en_US": "Portuguese",
                        "zh_Hans": "葡萄牙语"
                      },
                      "value": "pt"
                    },
                    {
                      "label": {
                        "en_US": "Portuguese (Brazil)",
                        "zh_Hans": "葡萄牙语（巴西）"
                      },
                      "value": "pt-br"
                    },
                    {
                      "label": {
                        "en_US": "Portuguese (Portugal)",
                        "zh_Hans": "葡萄牙语（葡萄牙）"
                      },
                      "value": "pt-pt"
                    },
                    {
                      "label": {
                        "en_US": "Punjabi",
                        "zh_Hans": "旁遮普语"
                      },
                      "value": "pa"
                    },
                    {
                      "label": {
                        "en_US": "Quechua",
                        "zh_Hans": "克丘亚语"
                      },
                      "value": "qu"
                    },
                    {
                      "label": {
                        "en_US": "Romanian",
                        "zh_Hans": "罗马尼亚语"
                      },
                      "value": "ro"
                    },
                    {
                      "label": {
                        "en_US": "Romansh",
                        "zh_Hans": "罗曼什语"
                      },
                      "value": "rm"
                    },
                    {
                      "label": {
                        "en_US": "Runyakitara",
                        "zh_Hans": "卢尼亚基塔拉语"
                      },
                      "value": "nyn"
                    },
                    {
                      "label": {
                        "en_US": "Russian",
                        "zh_Hans": "俄语"
                      },
                      "value": "ru"
                    },
                    {
                      "label": {
                        "en_US": "Scots Gaelic",
                        "zh_Hans": "苏格兰盖尔语"
                      },
                      "value": "gd"
                    },
                    {
                      "label": {
                        "en_US": "Serbian",
                        "zh_Hans": "塞尔维亚语"
                      },
                      "value": "sr"
                    },
                    {
                      "label": {
                        "en_US": "Serbo-Croatian",
                        "zh_Hans": "塞尔维亚-克罗地亚语"
                      },
                      "value": "sh"
                    },
                    {
                      "label": {
                        "en_US": "Sesotho",
                        "zh_Hans": "塞索托语"
                      },
                      "value": "st"
                    },
                    {
                      "label": {
                        "en_US": "Setswana",
                        "zh_Hans": "塞茨瓦纳语"
                      },
                      "value": "tn"
                    },
                    {
                      "label": {
                        "en_US": "Seychellois Creole",
                        "zh_Hans": "塞舌尔克里奥尔语"
                      },
                      "value": "crs"
                    },
                    {
                      "label": {
                        "en_US": "Shona",
                        "zh_Hans": "绍纳语"
                      },
                      "value": "sn"
                    },
                    {
                      "label": {
                        "en_US": "Sindhi",
                        "zh_Hans": "信德语"
                      },
                      "value": "sd"
                    },
                    {
                      "label": {
                        "en_US": "Sinhalese",
                        "zh_Hans": "僧伽罗语"
                      },
                      "value": "si"
                    },
                    {
                      "label": {
                        "en_US": "Slovak",
                        "zh_Hans": "斯洛伐克语"
                      },
                      "value": "sk"
                    },
                    {
                      "label": {
                        "en_US": "Slovenian",
                        "zh_Hans": "斯洛文尼亚语"
                      },
                      "value": "sl"
                    },
                    {
                      "label": {
                        "en_US": "Somali",
                        "zh_Hans": "索马里语"
                      },
                      "value": "so"
                    },
                    {
                      "label": {
                        "en_US": "Spanish",
                        "zh_Hans": "西班牙语"
                      },
                      "value": "es"
                    },
                    {
                      "label": {
                        "en_US": "Spanish (Latin American)",
                        "zh_Hans": "西班牙语（拉丁美洲）"
                      },
                      "value": "es-419"
                    },
                    {
                      "label": {
                        "en_US": "Sundanese",
                        "zh_Hans": "巽他语"
                      },
                      "value": "su"
                    },
                    {
                      "label": {
                        "en_US": "Swahili",
                        "zh_Hans": "斯瓦希里语"
                      },
                      "value": "sw"
                    },
                    {
                      "label": {
                        "en_US": "Swedish",
                        "zh_Hans": "瑞典语"
                      },
                      "value": "sv"
                    },
                    {
                      "label": {
                        "en_US": "Tajik",
                        "zh_Hans": "塔吉克语"
                      },
                      "value": "tg"
                    },
                    {
                      "label": {
                        "en_US": "Tamil",
                        "zh_Hans": "泰米尔语"
                      },
                      "value": "ta"
                    },
                    {
                      "label": {
                        "en_US": "Tatar",
                        "zh_Hans": "鞑靼语"
                      },
                      "value": "tt"
                    },
                    {
                      "label": {
                        "en_US": "Telugu",
                        "zh_Hans": "泰卢固语"
                      },
                      "value": "te"
                    },
                    {
                      "label": {
                        "en_US": "Thai",
                        "zh_Hans": "泰语"
                      },
                      "value": "th"
                    },
                    {
                      "label": {
                        "en_US": "Tigrinya",
                        "zh_Hans": "提格利尼亚语"
                      },
                      "value": "ti"
                    },
                    {
                      "label": {
                        "en_US": "Tonga",
                        "zh_Hans": "汤加语"
                      },
                      "value": "to"
                    },
                    {
                      "label": {
                        "en_US": "Tshiluba",
                        "zh_Hans": "卢巴语"
                      },
                      "value": "lua"
                    },
                    {
                      "label": {
                        "en_US": "Tumbuka",
                        "zh_Hans": "图布卡语"
                      },
                      "value": "tum"
                    },
                    {
                      "label": {
                        "en_US": "Turkish",
                        "zh_Hans": "土耳其语"
                      },
                      "value": "tr"
                    },
                    {
                      "label": {
                        "en_US": "Turkmen",
                        "zh_Hans": "土库曼语"
                      },
                      "value": "tk"
                    },
                    {
                      "label": {
                        "en_US": "Twi",
                        "zh_Hans": "契维语"
                      },
                      "value": "tw"
                    },
                    {
                      "label": {
                        "en_US": "Uighur",
                        "zh_Hans": "维吾尔语"
                      },
                      "value": "ug"
                    },
                    {
                      "label": {
                        "en_US": "Ukrainian",
                        "zh_Hans": "乌克兰语"
                      },
                      "value": "uk"
                    },
                    {
                      "label": {
                        "en_US": "Urdu",
                        "zh_Hans": "乌尔都语"
                      },
                      "value": "ur"
                    },
                    {
                      "label": {
                        "en_US": "Uzbek",
                        "zh_Hans": "乌兹别克语"
                      },
                      "value": "uz"
                    },
                    {
                      "label": {
                        "en_US": "Vanuatu",
                        "zh_Hans": "瓦努阿图语"
                      },
                      "value": "vu"
                    },
                    {
                      "label": {
                        "en_US": "Vietnamese",
                        "zh_Hans": "越南语"
                      },
                      "value": "vi"
                    },
                    {
                      "label": {
                        "en_US": "Welsh",
                        "zh_Hans": "威尔士语"
                      },
                      "value": "cy"
                    },
                    {
                      "label": {
                        "en_US": "Wolof",
                        "zh_Hans": "沃洛夫语"
                      },
                      "value": "wo"
                    },
                    {
                      "label": {
                        "en_US": "Xhosa",
                        "zh_Hans": "科萨语"
                      },
                      "value": "xh"
                    },
                    {
                      "label": {
                        "en_US": "Yiddish",
                        "zh_Hans": "意第绪语"
                      },
                      "value": "yi"
                    },
                    {
                      "label": {
                        "en_US": "Yoruba",
                        "zh_Hans": "约鲁巴语"
                      },
                      "value": "yo"
                    },
                    {
                      "label": {
                        "en_US": "Zulu",
                        "zh_Hans": "祖鲁语"
                      },
                      "value": "zu"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Defines the Google domain of the search. Default is \"google.com\".",
                    "zh_Hans": "定义搜索的 Google 域。默认为“google.com”。"
                  },
                  "label": {
                    "en_US": "google_domain",
                    "zh_Hans": "google_domain"
                  },
                  "llm_description": "Defines Google domain in which you want to search.",
                  "max": null,
                  "min": null,
                  "name": "google_domain",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Specifies the number of results to display per page. Default is 10. Max number - 100, min - 1.",
                    "zh_Hans": "指定每页显示的结果数。默认值为 10。最大数量 - 100，最小数量 - 1。"
                  },
                  "label": {
                    "en_US": "num",
                    "zh_Hans": "num"
                  },
                  "llm_description": "Specifies the num of results to display per page.",
                  "max": null,
                  "min": null,
                  "name": "num",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:10:16Z",
        "version_updated_at": "2025-02-17T07:10:16Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Convert Markdown content to PowerPoint presentations",
          "ja_JP": "Markdownコンテンツをパワーポイントプレゼンテーションに変換",
          "pt_BR": "Converter conteúdo Markdown para apresentações PowerPoint",
          "zh_Hans": "将Markdown内容转换为PowerPoint演示文稿"
        },
        "category": "tool",
        "created_at": "2025-03-20T15:42:50Z",
        "endpoint": {},
        "icon": "stvlynn/packages/ppt/_assets/icon.svg",
        "index_id": "stvlynn___ppt",
        "install_count": 3794,
        "introduction": "# Markdown to PPTX Converter\n\n**Author:** [Steven Lynn](https://github.com/stvlynn)\n**Version:** 0.0.1\n**Type:** tool\n**Repository:** https://github.com/stvlynn/PPT-Dify-Plugin\n\n---\n\nA Dify plugin that converts Markdown text content into PowerPoint presentations.\n\nThis plugin incorporates some content from [md2pptx](https://github.com/MartinPacker/md2pptx).\n\n## Installation\n\n1. Install the plugin from [Dify Marketplace](https://marketplace.dify.ai/plugins/stvlynn/ppt)\n2. Navigate to **Plugins** section in your Dify workspace\n3. Find the \"PPT\" plugin and click \"Install\"\n4. Once installed, you can use the plugin in your applications\n\n### Adding to Applications\n\n1. Create or edit a Chatflow or Workflow application\n2. In the tool selection panel, select \"PPT\" tool\n3. Configure the tool in your application flow as needed\n4. Save and publish your application\n\n![](./_assets/ppt-1.png)\n\n\n## Usage\n\nThis plugin allows you to convert Markdown content into PowerPoint presentations by simply providing the Markdown text.\n\n> For any questions about text formatting, please refer to md2pptx's [user guide](https://github.com/MartinPacker/md2pptx/blob/master/docs/user-guide.md).\n\n### Parameters\n\n- `markdown_content` (required): The Markdown content to be converted to a PowerPoint presentation\n- `title` (optional): The title of the presentation\n- `theme` (optional): The theme/design to use for the presentation\n\n## Example Markdown\n\n```markdown\n# Presentation Title\n\n## First Slide\n\n- Point 1\n- Point 2\n  - Subpoint A\n  - Subpoint B\n- Point 3\n\n## Second Slide\n\nThis is a paragraph with some text.\n\n## Slide with Code\n\n```python\ndef hello_world():\n    print(\"Hello, World!\")\n```\n\n## Slide with Table\n\n```\n| Header 1 | Header 2 |\n|----------|----------|\n| Cell 1   | Cell 2   |\n| Cell 3   | Cell 4   |\n```\n\n## LLM system prompt (for reference)\n\n```\n# Professional Presentation (PPT) Markdown Assistant\n\n## Purpose\nYou are a professional PPT presentation creation assistant who transforms user requirements into a clear, focused Markdown-formatted presentation text.\n\n## Markdown PPT Formatting Guidelines\n\n### Title and Structure\n- Use `#` for the title slide (typically one slide)\n- Use `##` for slide titles\n- Use `###` for subtitles (if needed)\n- Use horizontal rule `---` to separate slides\n\n### Content Formatting\n- Use unordered lists (`*` or `-`) for key points\n- Use ordered lists (`1.`, `2.`) for sequential steps\n- Separate paragraphs with blank lines\n- Use code blocks with triple backticks\n- Optional: Include tables and image links\n\n## Processing Workflow\n\n### 1. Understand User Requirements\n- Carefully read all provided information\n- Note:\n  * Presentation topic\n  * Target audience\n  * Key messages\n  * Presentation duration\n  * Specific style or format requirements\n\n### 2. Extract Core Content\n- Identify the most important points\n- Remember: PPT supports the speech, not replaces it\n\n### 3. Organize Content Structure\nTypical structure includes:\n- Title Slide\n- Introduction/Agenda\n- Body (multiple sections)\n- Summary/Conclusion\n- Optional Q&A section\n\n### 4. Create Markdown Presentation\n- Ensure each slide focuses on one main point\n- Use concise, powerful language\n- Emphasize points with bullet points\n- Use appropriate title hierarchy\n\n### 5. Review and Optimize\n- Check for completeness\n- Refine text formatting\n- Ensure readability\n\n## Important Guidelines\n- Do not guess or add information not provided\n- Ask clarifying questions if needed\n- Simplify detailed or lengthy information\n- Highlight Markdown advantages (easy editing, version control)\n\n## Input Processing Rules\n- Carefully analyze user input\n- Extract key presentation elements\n- Transform input into structured Markdown format\n- Maintain clarity and logical flow\n\n## Example User Input\n\"Help me create a presentation about 'How to Improve Team Collaboration Efficiency' for project managers. Cover: defining team goals, establishing communication mechanisms, using collaboration tools like Slack and Microsoft Teams, and regular reviews and feedback. Presentation length is about 15 minutes.\"\n\n## Expected Output Format\n\n# Presentation Title\n\n---\n\n## Agenda\n\n- Key Point 1\n- Key Point 2\n- Key Point 3\n\n---\n\n## Detailed Slide Content\n\n- Specific bullet points\n- Explanatory details\n- Key takeaways\n\n---\n\n\n## Response Guidelines\n- Provide a complete, ready-to-use Markdown presentation\n- Ensure professional and clear formatting\n- Adapt to user's specific context and requirements\n```\n\n## Feedback and Issues\n\nIf you encounter any problems or have suggestions for improvements:\n\n1. Please open an issue in the [plugin's GitHub repository](https://github.com/stvlynn/PPT-Dify-Plugin/issues)\n\n2. Provide details about your problem, including error messages and steps to reproduce\n\n3. **Do not** submit issues to the main [Dify](https://github.com/langgenius/dify) repository for plugin-specific problems\n\n## License\n\n[MIT](./LICENSE)\n\n\n\n",
        "label": {
          "en_US": "PPT",
          "ja_JP": "PPT",
          "pt_BR": "PPT",
          "zh_Hans": "PPT"
        },
        "latest_package_identifier": "stvlynn/ppt:0.0.1@fbf0073c3a584d79200a56776d1b60e3956d493956dcadfc75c87098b5e1fd95",
        "latest_version": "0.0.1",
        "model": {},
        "name": "ppt",
        "org": "stvlynn",
        "plugin_id": "stvlynn/ppt",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/ppt.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "storage": {
              "enabled": true,
              "size": 1048576
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "stvlynn",
            "description": {
              "en_US": "Convert Markdown content to PowerPoint presentations",
              "pt_BR": "Converter conteúdo Markdown para apresentações PowerPoint",
              "zh_Hans": "将Markdown内容转换为PowerPoint演示文稿"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "PPT",
              "pt_BR": "PPT",
              "zh_Hans": "PPT"
            },
            "name": "ppt",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Convert Markdown content to a PPTX (PowerPoint) presentation",
                  "pt_BR": "Converter conteúdo Markdown para uma apresentação PPTX (PowerPoint)",
                  "zh_Hans": "将Markdown内容转换为PPTX（PowerPoint）演示文稿"
                },
                "llm": "A tool that converts Markdown formatted text into Microsoft PowerPoint PPTX format presentations, maintaining formatting, structure, and supporting basic slide layouts."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "stvlynn",
                "label": {
                  "en_US": "Markdown to PPTX Converter",
                  "pt_BR": "Conversor de Markdown para PPTX",
                  "zh_Hans": "Markdown转PPTX转换器"
                },
                "name": "markdown_to_pptx_converter"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The Markdown content to be converted to PowerPoint presentation",
                    "pt_BR": "O conteúdo Markdown a ser convertido para apresentação PowerPoint",
                    "zh_Hans": "要转换为PowerPoint演示文稿的Markdown内容"
                  },
                  "label": {
                    "en_US": "Markdown Content",
                    "pt_BR": "Conteúdo Markdown",
                    "zh_Hans": "Markdown内容"
                  },
                  "llm_description": "The Markdown content that will be converted to a PowerPoint presentation",
                  "max": null,
                  "min": null,
                  "name": "markdown_content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The title of the PowerPoint presentation",
                    "pt_BR": "O título da apresentação PowerPoint",
                    "zh_Hans": "PowerPoint演示文稿的标题"
                  },
                  "label": {
                    "en_US": "Presentation Title",
                    "pt_BR": "Título da Apresentação",
                    "zh_Hans": "演示文稿标题"
                  },
                  "llm_description": "The title that will be used for the PowerPoint presentation",
                  "max": null,
                  "min": null,
                  "name": "title",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The theme/design to use for the presentation (default is 'default')",
                    "pt_BR": "O tema/design a ser usado para a apresentação (padrão é 'default')",
                    "zh_Hans": "演示文稿使用的主题/设计（默认为'default'）"
                  },
                  "label": {
                    "en_US": "Presentation Theme",
                    "pt_BR": "Tema da Apresentação",
                    "zh_Hans": "演示文稿主题"
                  },
                  "llm_description": "The visual theme to apply to the presentation slides",
                  "max": null,
                  "min": null,
                  "name": "theme",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-20T15:42:58Z",
        "version_updated_at": "2025-03-20T15:42:58Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Use LLM to Extract knowledge & summary from large text.",
          "zh_Hans": "利用 LLM 从大文本中提取知识 & 总结摘要。"
        },
        "category": "tool",
        "created_at": "2025-03-21T08:11:33Z",
        "endpoint": {},
        "icon": "junjiem/packages/knowledge_extractor/_assets/icon.svg",
        "index_id": "junjiem___knowledge_extractor",
        "install_count": 3657,
        "introduction": "## Dify 1.0 Plugin Knowledge Extractor Tool\n\n\n**Author:** [Junjie.M](https://github.com/junjiem)   \n**Type:** tool  \n**Github Repo:** [https://github.com/junjiem/dify-plugin-tools-knowledge_extractor](https://github.com/junjiem/dify-plugin-tools-knowledge_extractor)   \n**Github Issues:** [issues](https://github.com/junjiem/dify-plugin-tools-knowledge_extractor/issues)  \n\n\n---\n\n\n### Description\n\nUse LLM to Extract knowledge & summary from large text.\n\n利用 LLM 从大文本中提取知识 & 总结摘要。\n\n![knowledge_extractor](_assets/knowledge_extractor.png)\n\n![knowledge_extractor_workflow](_assets/knowledge_extractor_workflow.png)\n\n\n\n### Installing Plugins via GitHub  通过 GitHub 安装插件\n\nCan install the plugin using the GitHub repository address. Visit the Dify platform's plugin management page, choose to install via GitHub, enter the repository address, select version number and package file to complete installation.\n\n可以通过 GitHub 仓库地址安装该插件。访问 Dify 平台的插件管理页，选择通过 GitHub 安装插件，输入仓库地址后，选择版本号和包文件完成安装。\n\n![install_plugin_via_github](_assets/install_plugin_via_github.png)\n\n\n---\n\n\n\n### FAQ\n\n#### How to Handle Errors When Installing Plugins? 安装插件时遇到异常应如何处理？\n\n**Issue**: If you encounter the error message: plugin verification has been enabled, and the plugin you want to install has a bad signature, how to handle the issue?\n\n**Solution**: Add the following line to the end of your .env configuration file: FORCE_VERIFYING_SIGNATURE=false\nOnce this field is added, the Dify platform will allow the installation of all plugins that are not listed (and thus not verified) in the Dify Marketplace.\n\n**问题描述**：安装插件时遇到异常信息：plugin verification has been enabled, and the plugin you want to install has a bad signature，应该如何处理？\n\n**解决办法**：在 .env 配置文件的末尾添加 FORCE_VERIFYING_SIGNATURE=false 字段即可解决该问题。\n添加该字段后，Dify 平台将允许安装所有未在 Dify Marketplace 上架（审核）的插件，可能存在安全隐患。\n\n",
        "label": {
          "en_US": "Knowledge Extractor",
          "zh_Hans": "知识提取器"
        },
        "latest_package_identifier": "junjiem/knowledge_extractor:0.0.2@77399dc8efd6dd630a022b69d409c163fa4bc22447b4128ac35cac343198cc7f",
        "latest_version": "0.0.2",
        "model": {},
        "name": "knowledge_extractor",
        "org": "junjiem",
        "plugin_id": "junjiem/knowledge_extractor",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/knowledge_extractor.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "junjiem",
            "description": {
              "en_US": "Use LLM to Extract knowledge & summary from large text.",
              "zh_Hans": "利用 LLM 从大文本中提取知识 & 总结摘要。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Knowledge Extractor",
              "zh_Hans": "知识提取器"
            },
            "name": "knowledge_extractor",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Use LLM to Extract knowledge & summary from large text.",
                  "zh_Hans": "利用 LLM 从大文本中提取知识 & 总结摘要。"
                },
                "llm": "Use LLM to Extract knowledge & summary from large text."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "junjiem",
                "label": {
                  "en_US": "Knowledge Extractor",
                  "zh_Hans": "知识提取器"
                },
                "name": "knowledge_extractor"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Choose the model.",
                    "zh_Hans": "选择模型。"
                  },
                  "label": {
                    "en_US": "Model",
                    "zh_Hans": "模型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": "llm",
                  "template": null,
                  "type": "model-selector"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Input large text",
                    "zh_Hans": "输入大文本"
                  },
                  "label": {
                    "en_US": "Text",
                    "zh_Hans": "文本"
                  },
                  "llm_description": "Input large text",
                  "max": null,
                  "min": null,
                  "name": "text",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": {
                    "type": "prompt_instruction"
                  },
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Input additional instructions to help the knowledge extractor understand how to extract knowledge.",
                    "zh_Hans": "你可以输入额外的附加指令，帮助知识提取器理解如何提炼知识。"
                  },
                  "label": {
                    "en_US": "Instruction",
                    "zh_Hans": "指令"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "instruction",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": {
                    "enabled": true
                  },
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "English",
                  "form": "form",
                  "human_description": {
                    "en_US": "Output language",
                    "zh_Hans": "输出的语言"
                  },
                  "label": {
                    "en_US": "language",
                    "zh_Hans": "语言"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "language",
                  "options": [
                    {
                      "label": {
                        "en_US": "English",
                        "zh_Hans": "英语"
                      },
                      "value": "English"
                    },
                    {
                      "label": {
                        "en_US": "Chinese",
                        "zh_Hans": "中文"
                      },
                      "value": "Chinese"
                    },
                    {
                      "label": {
                        "en_US": "Japanese",
                        "zh_Hans": "日语"
                      },
                      "value": "Japanese"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 8192,
                  "form": "form",
                  "human_description": {
                    "en_US": "Maximum chunk length should be less than 32768.",
                    "zh_Hans": "分段最大长度不能大于 32768。"
                  },
                  "label": {
                    "en_US": "Maximum Chunk Length",
                    "zh_Hans": "分段最大长度"
                  },
                  "llm_description": "",
                  "max": 32768,
                  "min": 1,
                  "name": "chunk_size",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 0,
                  "form": "form",
                  "human_description": {
                    "en_US": "Setting the chunk overlap can maintain the semantic relevance between them. It is recommended to set 10%-25% of the maximum chunk size.",
                    "zh_Hans": "设置分段之间的重叠长度可以保留分段之间的语义关系。建议设置为最大分段长度的10%-25%。"
                  },
                  "label": {
                    "en_US": "Chunk Overlap",
                    "zh_Hans": "分段重叠长度"
                  },
                  "llm_description": "",
                  "max": 512,
                  "min": 0,
                  "name": "chunk_overlap",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "\\\\s*(?>\\\\R)\\\\s*(?>\\\\R)\\\\s*",
                  "form": "form",
                  "human_description": {
                    "en_US": "A delimiter is the character used to separate text. \\\\n\\\\n and \\\\n are commonly used delimiters for separating paragraphs and lines. Combined with commas (\\\\n\\\\n,\\\\n), paragraphs will be segmented by lines when exceeding the maximum chunk length. You can also use special delimiters defined by yourself (e.g. ***).",
                    "zh_Hans": "分隔符是用于分隔文本的字符。\\\\n\\\\n 和 \\\\n 是常用于分隔段落和行的分隔符。 用逗号连接分隔符（\\\\n\\\\n,\\\\n），当段落超过最大块长度时，会按行进行分割。你也可以使用自定义的特殊分隔符（例如 ***）。"
                  },
                  "label": {
                    "en_US": "Delimiter",
                    "zh_Hans": "分段标识符"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "separator",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-17T15:30:53Z",
        "version_updated_at": "2025-04-17T15:30:53Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "xAI is a company working on building artificial intelligence to accelerate human scientific discovery. We are guided by our mission to advance our collective understanding of the universe."
        },
        "category": "model",
        "created_at": "2024-12-05T13:05:48Z",
        "endpoint": {},
        "icon": "langgenius/packages/x/_assets/x-ai-logo.svg",
        "index_id": "langgenius___x",
        "install_count": 3422,
        "introduction": "## Overview\n\nxAI is developing a family of Large Language Models (LLMs) called **Grok**. Grok models use next-token prediction to perform tasks, with a focus on providing helpful and insightful responses. Key models include `grok-2-vision-1212` and `grok-2-1212`. Depending on the model specifications, users can interact with Grok models to find answers, interpret images, and generate images. xAI offers an API interface for developers to programmatically interact with Grok models.\n\n## Configuration\n\nAfter installing the plugin, configure the API key and API base within the Model Provider settings. Obtain your API key from [here](https://x.ai/api). Once saved, you can begin using xAI to build your AI agents and agentic workflows.\n\n![](./_assets/x_ai_config.PNG)",
        "label": {
          "en_US": "xAI"
        },
        "latest_package_identifier": "langgenius/x:0.0.4@eaee70ddfad2258caf1de0fd980763f7da03ddd63d8ca211904738c6de403609",
        "latest_version": "0.0.4",
        "model": {
          "background": null,
          "configurate_methods": [
            "predefined-model"
          ],
          "description": {
            "en_US": "xAI is a company working on building artificial intelligence to accelerate human scientific discovery. We are guided by our mission to advance our collective understanding of the universe."
          },
          "help": {
            "title": {
              "en_US": "Get your token from xAI",
              "zh_Hans": "从 xAI 获取 token"
            },
            "url": {
              "en_US": "https://x.ai/api"
            }
          },
          "icon_large": {
            "en_US": "x-ai-logo.svg"
          },
          "icon_small": {
            "en_US": "x-ai-logo.svg"
          },
          "label": {
            "en_US": "xAI"
          },
          "model_credential_schema": null,
          "models": [
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "multi-tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "grok-2-1212"
              },
              "model": "grok-2-1212",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "zh_Hans": "采样温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Number between 0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.",
                    "zh_Hans": "介于0和2.0之间的数字。正值会根据新标记在文本中迄今为止的现有频率来惩罚它们，从而降低模型一字不差地重复同一句话的可能性。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 1,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "grok-2-vision-1212"
              },
              "model": "grok-2-vision-1212",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "zh_Hans": "采样温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Number between 0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.",
                    "zh_Hans": "介于0和2.0之间的数字。正值会根据新标记在文本中迄今为止的现有频率来惩罚它们，从而降低模型一字不差地重复同一句话的可能性。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 1,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "tool-call",
                "multi-tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "grok-3-beta"
              },
              "model": "grok-3-beta",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "zh_Hans": "采样温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Number between 0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.",
                    "zh_Hans": "介于0和2.0之间的数字。正值会根据新标记在文本中迄今为止的现有频率来惩罚它们，从而降低模型一字不差地重复同一句话的可能性。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 1,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "tool-call",
                "multi-tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "grok-3-fast-beta"
              },
              "model": "grok-3-fast-beta",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "zh_Hans": "采样温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Number between 0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.",
                    "zh_Hans": "介于0和2.0之间的数字。正值会根据新标记在文本中迄今为止的现有频率来惩罚它们，从而降低模型一字不差地重复同一句话的可能性。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 1,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "multi-tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "grok-3-mini-beta"
              },
              "model": "grok-3-mini-beta",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "zh_Hans": "采样温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Number between 0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.",
                    "zh_Hans": "介于0和2.0之间的数字。正值会根据新标记在文本中迄今为止的现有频率来惩罚它们，从而降低模型一字不差地重复同一句话的可能性。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 1,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "multi-tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "grok-3-mini-fast-beta"
              },
              "model": "grok-3-mini-fast-beta",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "zh_Hans": "采样温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Number between 0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.",
                    "zh_Hans": "介于0和2.0之间的数字。正值会根据新标记在文本中迄今为止的现有频率来惩罚它们，从而降低模型一字不差地重复同一句话的可能性。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 1,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "multi-tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Grok Beta"
              },
              "model": "grok-beta",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "zh_Hans": "采样温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Number between 0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.",
                    "zh_Hans": "介于0和2.0之间的数字。正值会根据新标记在文本中迄今为止的现有频率来惩罚它们，从而降低模型一字不差地重复同一句话的可能性。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 1,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Grok Vision Beta"
              },
              "model": "grok-vision-beta",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "zh_Hans": "采样温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Number between 0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.",
                    "zh_Hans": "介于0和2.0之间的数字。正值会根据新标记在文本中迄今为止的现有频率来惩罚它们，从而降低模型一字不差地重复同一句话的可能性。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 1,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                }
              ],
              "pricing": null
            }
          ],
          "position": {},
          "provider": "x",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              },
              {
                "default": "https://api.x.ai/v1",
                "label": {
                  "en_US": "API Base"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Base",
                  "zh_Hans": "在此输入您的 API Base"
                },
                "required": false,
                "show_on": [],
                "type": "text-input",
                "variable": "endpoint_url"
              }
            ]
          },
          "supported_model_types": [
            "llm"
          ]
        },
        "name": "x",
        "org": "langgenius",
        "plugin_id": "langgenius/x",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/x.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-11T06:26:14Z",
        "version_updated_at": "2025-04-11T06:26:14Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "MinerU is a tool that converts FILES into machine-readable formats (e.g., markdown, JSON), allowing for easy extraction into any format. MinerU was born during the pre-training process of InternLM. We focus on solving symbol conversion issues in scientific literature and hope to contribute to technological development in the era of large models.https://github.com/opendatalab/MinerU",
          "ja_JP": "MinerU は、FILES を機械可読な形式（例えば、マークダウン、JSON）に変換するツールで、どんな形式にも簡単に抽出することができます。MinerU は InternLM の事前トレーニングプロセス中に生まれました。私たちは科学文献における記号変換の問題を解決することに集中し、大規模モデルの時代における技術開発に貢献することを目指しています。https://github.com/opendatalab/MinerU",
          "zh_Hans": "MinerU是一款可以在本地部署的将FILES转化为机器可读格式的工具（如markdown、json），可以很方便地抽取为任意格式。MinerU诞生于书生-浦语的预训练过程中，我们将会集中精力解决科技文献中的符号转化问题，希望在大模型时代为科技发展做出贡献。https://github.com/opendatalab/MinerU"
        },
        "category": "tool",
        "created_at": "2025-03-18T14:46:11Z",
        "endpoint": {},
        "icon": "langgenius/packages/mineru/_assets/icon.svg",
        "index_id": "langgenius___mineru",
        "install_count": 3320,
        "introduction": "# MinerU Dify Plugin\n\n## What's New?\n\n- Support the **official API of MinerU**\n  ![](./_assets/mineru8.jpg)\n\n- Local Deplay corresponds to MinerU **release 1.3.6**\n\n- The supported input file types have been increased to include **PDF, DOC, DOCX, PPT, PPTX, PNG, JPG, and JPEG.**\n\n- Remove the \"Replace Markdown Image Path\" tool. Now, the image paths in the Markdown will be automatically replaced with previewable URLs (the validity period of the URL is determined by the FILES_ACCESS_TIMEOUT in dify.env).If you want to use this feature, please update the Dify's core code.![](./_assets/mineru2.jpg)\n\n- Supports more export formats (HTML, DOC, LaTeX). The download links for the additional formats will be stored in the `files` of the output variables.\n  \n  ![](./_assets/mineru1.jpg)\n\n## DEMO DSL\n\n**You can download the YAML file and import it into Dify. This demo includes a basic capability demonstration of the plugin.**\n\n[demo_dsl.yml](https://github.com/langgenius/dify-official-plugins/blob/main/tools/mineru/_assets/mineru_demo.yml)\n\n## GitHub\n\nMinerU is a tool that converts PDFs into machine-readable formats (e.g., markdown, JSON), allowing for easy extraction into any format.\n\nMinerU is a document parser that can parse complex document data for any downstream LLM use case (RAG, agents)\n\n[GitHub - opendatalab/MinerU: A high-quality tool for convert PDF to Markdown and JSON.](https://github.com/opendatalab/MinerU)\n\n## Key Features\n\n- Remove headers, footers, footnotes, page numbers, etc., to ensure semantic coherence.\n- Output text in human-readable order, suitable for single-column, multi-column, and complex layouts.\n- Preserve the structure of the original document, including headings, paragraphs, lists, etc.\n- Extract images, image descriptions, tables, table titles, and footnotes.\n- Automatically recognize and convert formulas in the document to LaTeX format.\n- Automatically recognize and convert tables in the document to HTML format.\n- Automatically detect scanned PDFs and garbled PDFs and enable OCR functionality.\n- OCR supports detection and recognition of 84 languages.\n- Supports multiple output formats, such as multimodal and NLP Markdown, JSON sorted by reading order, and rich intermediate formats.\n- Supports various visualization results, including layout visualization and span visualization, for efficient confirmation of output quality.\n- Supports running in a pure CPU environment, and also supports GPU(CUDA)/NPU(CANN)/MPS acceleration\n- Compatible with Windows, Linux, and Mac platforms.\n\n## Getting Started\n\n### 1. MinerU Officail API\n\nThe version 0.0.2 can now support the official API of MinerU.\n\n1. Configure the base URL of the MinerU API service (e.g., https://mineru.net), and select \"MinerU Official API\" for the server type.\n\n2. Configure the API token([Get your api token from MinerU](https://mineru.net/apiManage/token))\n\n### Input Parameters\n\n| parameter                  | type     | required | example         | description                                                                                                                                                                                                                                                                                                                                                                              |\n|:--------------------------:| -------- | -------- | --------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| enable formula recognition | bool     | false    | true            | Whether to enable formula recognition, the default is true                                                                                                                                                                                                                                                                                                                               |\n| enable table recognition   | bool     | false    | true            | Whether to enable table recognition, the default is true                                                                                                                                                                                                                                                                                                                                 |\n| layout model               | string   | false    | doclayout_yolo  | Optional value: doclayout_yolo, layoutlmv3, the default value is doclayout_yolo. doclayout_yolo is a self-developed model, the effect is better                                                                                                                                                                                                                                          |\n| document language          | string   | false    | ch              | Specify the document language, the default ch, can be set to auto, when it is auto, the model will automatically recognize the document language, see the list of other optional values for details：[](https://paddlepaddle.github.io/PaddleOCR/latest/ppocr/blog/multi_languages.html#5)[PaddleOCR ](https://paddlepaddle.github.io/PaddleOCR/latest/ppocr/blog/multi_languages.html#5) |\n| enable ocr recognition     | bool     | false    | true            | Whether to start the ocr function, the default is false                                                                                                                                                                                                                                                                                                                                  |\n| extra export formats       | [string] | false    | [\"docx\",\"html\"] | Markdown and json are the default export formats without setting. This parameter only supports one or more of the three formats of docx, html, and latex.                                                                                                                                                                                                                                |\n\n![](./_assets/mineru3.jpg)\n\n#### Output Variables\n\nThe plugin provides five types of output for each processed file:\n\n> text : The parsed Markdown text\n> \n> files:  The extra export formats files(html,docx,latex)\n> \n> json: The parsed content list \n> \n> full_zip_url: Only for Official API, the zip URL of the complete parsed result\n> \n> images: The images extracted from the PDF\n\n![](./_assets/mineru4.jpg)\n\n### 2. Local Deploy\n\nVersion 0.2.0 of the plugin corresponds to MinerU release 1.3.6.\n\n1. Deploy Derived Projects\n\n[MinerU/projects/web_api/README.md at magic_pdf-1.2.2-released · opendatalab/MinerU · GitHub](https://github.com/opendatalab/MinerU/blob/magic_pdf-1.2.2-released/projects/web_api/README.md)\n\n2. Configure the base URL of the locally deployed MinerU service (e.g., http://192.168.0.1:8888), and select \"Local Deployment\" for the server type.\n   \n   **Note:Ensure that the Dify service can access this base URL.**\n   \n   ![](./_Assets/mineru5.jpg)\n\n#### Input Parameters\n\n| Parameter    | Type   | Required | Default | Description                               |\n| ------------ | ------ | -------- | ------- | ----------------------------------------- |\n| file         | file   | Yes      | -       | File to be parsed                         |\n| parse_method | select | Yes      | auto    | Parsing method, can be auto, ocr, or txt. |\n\n**Note: Other parameters are invalid for the local deployment version. **\n\n#### Output Variables\n\nas above\n\n## FAQs\n\n1.\n![](./_assets/mineru6.jpg)\n\n![](./_assets/mineru7.jpg)\n\nhttps://github.com/langgenius/dify/issues/16327\n\n## Credits\n\nThis plugin is powered by [MinerU]([GitHub - opendatalab/MinerU: A high-quality tool for convert PDF to Markdown and JSON.](https://github.com/opendatalab/MinerU))\n",
        "label": {
          "en_US": "MinerU",
          "ja_JP": "MinerU",
          "zh_Hans": "MinerU"
        },
        "latest_package_identifier": "langgenius/mineru:0.2.0@98b3e5f620678944aac704ceccc04ffa3bd32baec6d72e0798b54ea9cb036148",
        "latest_version": "0.2.0",
        "model": {},
        "name": "mineru",
        "org": "langgenius",
        "plugin_id": "langgenius/mineru",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/mineru.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Base URL",
                "ja_JP": "MinerUのBase URL",
                "zh_Hans": "MinerU服务的Base URL"
              },
              "name": "base_url",
              "options": null,
              "placeholder": {
                "en_US": "Please input your MinerU server's Base URL",
                "ja_JP": "MinerUサーバのBase URLを入力してください",
                "zh_Hans": "请输入你的 MinerU 服务的 Base URL"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Token",
                "ja_JP": "トークン",
                "zh_Hans": "令牌"
              },
              "name": "token",
              "options": null,
              "placeholder": {
                "en_US": "Please input your MinerU server's token",
                "ja_JP": "MinerUサーバのトークンを入力してください",
                "zh_Hans": "请输入你的 MinerU 服务的令牌"
              },
              "required": false,
              "scope": null,
              "type": "secret-input",
              "url": "https://mineru.net/apiManage/token"
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Server Type",
                "ja_JP": "サーバータイプ",
                "zh_Hans": "服务类型"
              },
              "name": "server_type",
              "options": [
                {
                  "label": {
                    "en_US": "Local Deployment",
                    "ja_JP": "ローカルデプロイ",
                    "zh_Hans": "本地部署"
                  },
                  "value": "local"
                },
                {
                  "label": {
                    "en_US": "MinerU Official API",
                    "ja_JP": "MinerU公式API",
                    "zh_Hans": "MinerU官方API"
                  },
                  "value": "remote"
                }
              ],
              "placeholder": {
                "en_US": "Please select MinerU service type, local deployment or official API",
                "ja_JP": "MinerUサービスのタイプを選択してください、ローカルデプロイまたは公式API",
                "zh_Hans": "请选择MinerU服务类型,本地部署或官方API"
              },
              "required": true,
              "scope": null,
              "type": "select",
              "url": null
            }
          ],
          "identity": {
            "author": "langgenius",
            "description": {
              "en_US": "MinerU is a tool that converts FILES into machine-readable formats (e.g., markdown, JSON), allowing for easy extraction into any format. MinerU was born during the pre-training process of InternLM. We focus on solving symbol conversion issues in scientific literature and hope to contribute to technological development in the era of large models.https://github.com/opendatalab/MinerU",
              "ja_JP": "MinerU は、FILES を機械可読な形式（例えば、マークダウン、JSON）に変換するツールで、どんな形式にも簡単に抽出することができます。MinerU は InternLM の事前トレーニングプロセス中に生まれました。私たちは科学文献における記号変換の問題を解決することに集中し、大規模モデルの時代における技術開発に貢献することを目指しています。https://github.com/opendatalab/MinerU",
              "zh_Hans": "MinerU是一款可以在本地部署的将FILES转化为机器可读格式的工具（如markdown、json），可以很方便地抽取为任意格式。MinerU诞生于书生-浦语的预训练过程中，我们将会集中精力解决科技文献中的符号转化问题，希望在大模型时代为科技发展做出贡献。https://github.com/opendatalab/MinerU"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "MinerU",
              "ja_JP": "MinerU",
              "zh_Hans": "MinerU"
            },
            "name": "mineru",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "a tool for parsing text, tables, and images, supporting multiple formats such as pdf, pptx, docx, etc. supporting multiple languages such as English, Chinese, etc.",
                  "ja_JP": "テキスト、テーブル、画像を解析するツールです。pdf、pptx、docxなどの複数の形式をサポートしています。英語、中国語などの複数の言語をサポートしています。",
                  "zh_Hans": "一个用于解析文本，表格和图片的工具，支持pdf,pptx,docx等多种格式。支持英语，中文等多种语言"
                },
                "llm": "a tool for parsing text, tables, and images, supporting multiple formats such as pdf, pptx, docx, etc. supporting multiple languages such as English, Chinese, etc."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Parse File",
                  "ja_JP": "Parse File",
                  "zh_Hans": "Parse File"
                },
                "name": "parse-file"
              },
              "output_schema": {
                "properties": {
                  "full_zip_url": {
                    "description": "The zip URL of the complete parsed result",
                    "type": "string"
                  },
                  "images": {
                    "description": "The images extracted from the file",
                    "items": {
                      "type": "object"
                    },
                    "type": "array"
                  }
                },
                "type": "object"
              },
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "the file to be parsed(support pdf, ppt, pptx, doc, docx, png, jpg, jpeg)",
                    "ja_JP": "解析するファイル(pdf、ppt、pptx、doc、docx、png、jpg、jpegをサポート)",
                    "zh_Hans": "用于解析的文件(支持 pdf, ppt, pptx, doc, docx, png, jpg, jpeg)"
                  },
                  "label": {
                    "en_US": "file",
                    "ja_JP": "file",
                    "zh_Hans": "file"
                  },
                  "llm_description": "the file to be parsed (support pdf, ppt, pptx, doc, docx, png, jpg, jpeg)",
                  "max": null,
                  "min": null,
                  "name": "file",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "file"
                },
                {
                  "auto_generate": null,
                  "default": "auto",
                  "form": "form",
                  "human_description": {
                    "en_US": "(For local deployment service)Parsing method, can be auto, ocr, or txt. Default is auto. If results are not satisfactory, try ocr",
                    "ja_JP": "（ローカルデプロイメントサービス用）解析方法は、auto、ocr、またはtxtのいずれかです。デフォルトはautoです。結果が満足できない場合は、ocrを試してください",
                    "zh_Hans": "（用于本地部署服务）解析方法，可以是auto, ocr, 或 txt。默认是auto。如果结果不理想，请尝试ocr"
                  },
                  "label": {
                    "en_US": "parse method",
                    "ja_JP": "解析方法",
                    "zh_Hans": "解析方法"
                  },
                  "llm_description": "Parsing method, can be auto, ocr, or txt. Default is auto. If results are not satisfactory, try ocr",
                  "max": null,
                  "min": null,
                  "name": "parse_method",
                  "options": [
                    {
                      "label": {
                        "en_US": "auto",
                        "ja_JP": "auto",
                        "zh_Hans": "auto"
                      },
                      "value": "auto"
                    },
                    {
                      "label": {
                        "en_US": "ocr",
                        "ja_JP": "ocr",
                        "zh_Hans": "ocr"
                      },
                      "value": "ocr"
                    },
                    {
                      "label": {
                        "en_US": "txt",
                        "ja_JP": "txt",
                        "zh_Hans": "txt"
                      },
                      "value": "txt"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "(For official API) Whether to enable formula recognition",
                    "ja_JP": "（公式API用）数式認識を有効にするかどうか",
                    "zh_Hans": "（用于官方API）是否开启公式识别"
                  },
                  "label": {
                    "en_US": "Enable formula recognition",
                    "ja_JP": "数式認識を有効にする",
                    "zh_Hans": "开启公式识别"
                  },
                  "llm_description": "(For official API) Whether to enable formula recognition",
                  "max": null,
                  "min": null,
                  "name": "enable_formula",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "(For official API) Whether to enable table recognition",
                    "ja_JP": "（公式API用）表認識を有効にするかどうか",
                    "zh_Hans": "（用于官方API）是否开启表格识别"
                  },
                  "label": {
                    "en_US": "Enable table recognition",
                    "ja_JP": "表認識を有効にする",
                    "zh_Hans": "开启表格识别"
                  },
                  "llm_description": "(For official API) Whether to enable table recognition",
                  "max": null,
                  "min": null,
                  "name": "enable_table",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": "doclayout_yolo",
                  "form": "form",
                  "human_description": {
                    "en_US": "(For official API) Optional values: doclayout_yolo, layoutlmv3, default value is doclayout_yolo. doclayout_yolo is a self-developed model with better effect",
                    "ja_JP": "（公式API用）オプション値：doclayout_yolo、layoutlmv3、デフォルト値は doclayout_yolo。doclayout_yolo は自己開発モデルで、効果がより良い",
                    "zh_Hans": "（用于官方API）可选值：doclayout_yolo、layoutlmv3，默认值为 doclayout_yolo。doclayout_yolo 为自研模型，效果更好"
                  },
                  "label": {
                    "en_US": "Layout model",
                    "ja_JP": "レイアウト検出モデル",
                    "zh_Hans": "布局检测模型"
                  },
                  "llm_description": "(For official API) Optional values: doclayout_yolo, layoutlmv3, default value is doclayout_yolo. doclayout_yolo is a self-developed model withbetter effect",
                  "max": null,
                  "min": null,
                  "name": "layout_model",
                  "options": [
                    {
                      "label": {
                        "en_US": "doclayout_yolo",
                        "ja_JP": "doclayout_yolo",
                        "zh_Hans": "doclayout_yolo"
                      },
                      "value": "doclayout_yolo"
                    },
                    {
                      "label": {
                        "en_US": "layoutlmv3",
                        "ja_JP": "layoutlmv3",
                        "zh_Hans": "layoutlmv3"
                      },
                      "value": "layoutlmv3"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "auto",
                  "form": "form",
                  "human_description": {
                    "en_US": "(For official API) Specify document language, default ch, can be set to auto, when auto, the model will automatically identify document language, other optional value list see: https://paddlepaddle.github.io/PaddleOCR/latest/ppocr/blog/multi_languages.html#5",
                    "ja_JP": "（公式API用）ドキュメント言語を指定します。デフォルトはchで、autoに設定できます。autoの場合、モデルはドキュメント言語を自動的に識別します。他のオプション値リストについては、次を参照してください：https://paddlepaddle.github.io/PaddleOCR/latest/ppocr/blog/multi_languages.html#5",
                    "zh_Hans": "（用于官方API）指定文档语言，默认 ch，可以设置为auto，当为auto时模型会自动识别文档语言，其他可选值列表详见：https://paddlepaddle.github.io/PaddleOCR/latest/ppocr/blog/multi_languages.html#5"
                  },
                  "label": {
                    "en_US": "Document language",
                    "ja_JP": "ドキュメント言語",
                    "zh_Hans": "文档语言"
                  },
                  "llm_description": "(For official API) Specify document language, default ch, can be set to auto, when auto, the model will automatically identify document language, other optional value list see: https://paddlepaddle.github.io/PaddleOCR/latest/ppocr/blog/multi_languages.html#5",
                  "max": null,
                  "min": null,
                  "name": "language",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "(For official API) Whether to enable OCR recognition",
                    "ja_JP": "（公式API用）OCR認識を有効にするかどうか",
                    "zh_Hans": "（用于官方API）是否开启OCR识别"
                  },
                  "label": {
                    "en_US": "Enable OCR recognition",
                    "ja_JP": "OCR認識を有効にする",
                    "zh_Hans": "开启OCR识别"
                  },
                  "llm_description": "(For official API) Whether to enable OCR recognition",
                  "max": null,
                  "min": null,
                  "name": "enable_ocr",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": "[]",
                  "form": "form",
                  "human_description": {
                    "en_US": "(For official API) Example: [\"docx\",\"html\"], markdown, json are the default export formats, no need to set, this parameter only supports one or more of docx, html, latex",
                    "ja_JP": "（公式API用）例：[\"docx\",\"html\"]、markdown、jsonはデフォルトのエクスポート形式であり、設定する必要はありません。このパラメータは、docx、html、latexの3つの形式のいずれかまたは複数のみをサポートします",
                    "zh_Hans": "（用于官方API）示例：[\"docx\",\"html\"],markdown、json为默认导出格式，无须设置，该参数仅支持docx、html、latex三种格式中的一个或多个"
                  },
                  "label": {
                    "en_US": "Extra export formats",
                    "ja_JP": "追加のエクスポート形式",
                    "zh_Hans": "额外导出格式"
                  },
                  "llm_description": "(For official API) Example: [\"docx\",\"html\"], markdown, json are the default export formats, no need to set, this parameter only supports one or more of docx, html, latex",
                  "max": null,
                  "min": null,
                  "name": "extra_formats",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-22T13:11:53Z",
        "version_updated_at": "2025-04-22T13:11:53Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Azure AI Studio"
        },
        "category": "model",
        "created_at": "2024-12-13T13:51:58Z",
        "endpoint": {},
        "icon": "langgenius/packages/azure_ai_studio/_assets/icon_s_en.png",
        "index_id": "langgenius___azure_ai_studio",
        "install_count": 3318,
        "introduction": "## Overview\n\nAzure AI Foundry serves as a model provider for a variety of AI applications. Users can add rich models into this plugin, including LLMs and rerank models from several providers like Azure OpenAI, Meta (Llama), Cohere, and Mistral. Simply configure the parameters and you're good to go.\n\n## Configure\nWith the plugin installed, configure Azure AI Studio by providing the Model Type, Model Name, Azure AI Studio Endpoint, and API Key. Save in Model Provider.\n\n<img src=\"./_assets/azure_ai_studio-01.png\" width=\"400\" />\n",
        "label": {
          "en_US": "Azure AI Studio"
        },
        "latest_package_identifier": "langgenius/azure_ai_studio:0.0.3@64420f3dbdbdbde37c1c94491b8d6b1c45d10fcfbaa9adca7fd3984cc89518fd",
        "latest_version": "0.0.3",
        "model": {
          "background": "#93c5fd",
          "configurate_methods": [
            "customizable-model"
          ],
          "description": {
            "en_US": "Azure AI Studio",
            "zh_Hans": "Azure AI Studio"
          },
          "help": {
            "title": {
              "en_US": "How to deploy customized model on Azure AI Studio",
              "zh_Hans": "如何在Azure AI Studio上的私有化部署的模型"
            },
            "url": {
              "en_US": "https://learn.microsoft.com/en-us/azure/ai-studio/how-to/deploy-models",
              "zh_Hans": "https://learn.microsoft.com/zh-cn/azure/ai-studio/how-to/deploy-models"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.png"
          },
          "icon_small": {
            "en_US": "icon_s_en.png"
          },
          "label": {
            "en_US": "Azure AI Studio",
            "zh_Hans": "Azure AI Studio"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "Azure AI Studio Endpoint"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Endpoint, eg: https://example.com",
                  "zh_Hans": "请输入你的Azure AI Studio推理端点"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "endpoint"
              },
              {
                "default": null,
                "label": {
                  "en_US": "API Key",
                  "zh_Hans": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Azure AI Studio API Key",
                  "zh_Hans": "在此输入您的 Azure AI Studio API Key"
                },
                "required": true,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "secret-input",
                "variable": "api_key"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Select completion mode",
                  "zh_Hans": "选择对话类型"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Chat",
                      "zh_Hans": "对话"
                    },
                    "show_on": [],
                    "value": "chat"
                  },
                  {
                    "label": {
                      "en_US": "Completion",
                      "zh_Hans": "补全"
                    },
                    "show_on": [],
                    "value": "completion"
                  }
                ],
                "placeholder": {
                  "en_US": "Select completion model",
                  "zh_Hans": "选择对话类型"
                },
                "required": true,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "select",
                "variable": "mode"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Model context size",
                  "zh_Hans": "模型上下文长度"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Model context size",
                  "zh_Hans": "在此输入您的模型上下文长度"
                },
                "required": true,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "text-input",
                "variable": "context_size"
              },
              {
                "default": null,
                "label": {
                  "en_US": "JWT Token",
                  "zh_Hans": "JWT令牌"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Azure AI Studio JWT Token",
                  "zh_Hans": "在此输入您的 Azure AI Studio 推理 API Key"
                },
                "required": true,
                "show_on": [
                  {
                    "value": "rerank",
                    "variable": "__model_type"
                  }
                ],
                "type": "secret-input",
                "variable": "jwt_token"
              }
            ],
            "model": {
              "label": {
                "en_US": "Model Name",
                "zh_Hans": "模型名称"
              },
              "placeholder": {
                "en_US": "Enter your model name",
                "zh_Hans": "输入模型名称"
              }
            }
          },
          "models": [],
          "position": {},
          "provider": "azure_ai_studio",
          "provider_credential_schema": null,
          "supported_model_types": [
            "llm",
            "rerank"
          ]
        },
        "name": "azure_ai_studio",
        "org": "langgenius",
        "plugin_id": "langgenius/azure_ai_studio",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/azure_ai_studio.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": false,
              "llm": false,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-03-02T02:10:08Z",
        "version_updated_at": "2025-03-02T02:10:08Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Convert your Dify app's API to OpenAI compatible API",
          "ja_JP": "DifyアプリのAPIをOpenAI互換APIに変換する",
          "pt_BR": "Converta a API do seu aplicativo Dify para uma API compatível com OpenAI",
          "zh_Hans": "将您的Dify应用的API转换为OpenAI兼容API"
        },
        "category": "extension",
        "created_at": "2024-12-15T10:21:11Z",
        "endpoint": {
          "endpoints": [
            {
              "hidden": false,
              "method": "POST",
              "path": "/chat/completions"
            }
          ],
          "settings": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "API key",
                "ja_JP": "API key",
                "pt_BR": "API key",
                "zh_Hans": "API key"
              },
              "name": "api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your API key",
                "ja_JP": "API keyを入力してください",
                "pt_BR": "Please input your API key",
                "zh_Hans": "请输入你的 API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "App",
                "ja_JP": "App",
                "pt_BR": "App",
                "zh_Hans": "App"
              },
              "name": "app_id",
              "options": null,
              "placeholder": {
                "en_US": "Please select an app",
                "ja_JP": "アプリを選択してください",
                "pt_BR": "Please select an app",
                "zh_Hans": "请选择一个应用"
              },
              "required": true,
              "scope": "chat",
              "type": "app-selector",
              "url": null
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "Memory Mode",
                "ja_JP": "メモリーモード",
                "pt_BR": "Modo de Memória",
                "zh_Hans": "记忆模式"
              },
              "name": "memory_mode",
              "options": [
                {
                  "label": {
                    "en_US": "Last User Message",
                    "ja_JP": "最後のユーザーメッセージ",
                    "pt_BR": "Última Mensagem do Usuário",
                    "zh_Hans": "使用最后一条用户消息"
                  },
                  "value": "last_user_message"
                }
              ],
              "placeholder": {
                "en_US": "Please select a memory mode, it will decide how the Endpoint manage the context",
                "ja_JP": "メモリーモードを選択してください, それは Endpoint がコンテキストをどのように管理するかを決定します",
                "pt_BR": "Por favor, selecione um modo de memória, que decidirá como o Endpoint gerencia o contexto",
                "zh_Hans": "请选择一个上下文模式，它将决定该 Endpoint 使用哪种方式管理上下文"
              },
              "required": true,
              "scope": null,
              "type": "select",
              "url": null
            }
          ]
        },
        "icon": "langgenius/packages/oaicompat_dify_app/_assets/icon.svg",
        "index_id": "langgenius___oaicompat_dify_app",
        "install_count": 3245,
        "introduction": "### OpenAI Compatible\n\nThis extension converts your Dify app's API to OpenAI compatible API.\n\n- **Attention**: Only supports `last_user_message` memory mode for now and only `chat`, `agent` and `chatflow` apps are supported.\n- **History**: You can set a `messages` parameter to your app to get the complete history of a OpenAI compatible API.\n",
        "label": {
          "en_US": "OpenAI Compatible Dify App",
          "ja_JP": "OpenAI Compatible Dify App",
          "pt_BR": "OpenAI Compatible Dify App",
          "zh_Hans": "OpenAI Compatible Dify App"
        },
        "latest_package_identifier": "langgenius/oaicompat_dify_app:0.0.5@7a0c5ea03a7aacbe1d08c042e4b31b8a8ea82adb2df69ada39674f8712521be3",
        "latest_version": "0.0.5",
        "model": {},
        "name": "oaicompat_dify_app",
        "org": "langgenius",
        "plugin_id": "langgenius/oaicompat_dify_app",
        "plugins": {
          "agent_strategies": null,
          "endpoints": [
            "group/openai_compatible.yaml"
          ],
          "models": null,
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-03-03T12:21:14Z",
        "version_updated_at": "2025-03-03T12:21:14Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "GPUStack is an open-source GPU cluster manager for running AI models.",
          "zh_Hans": "GPUStack 是一个专为运行 AI 模型而设计的开源 GPU 集群管理器，致力于支持基于任何品牌的异构 GPU 构建统一管理的算力集群"
        },
        "category": "model",
        "created_at": "2024-12-05T12:02:00Z",
        "endpoint": {},
        "icon": "langgenius/packages/gpustack/_assets/icon_s_en.png",
        "index_id": "langgenius___gpustack",
        "install_count": 3225,
        "introduction": "## Overview\n\nGPUStack is an open-source GPU cluster manager for running AI models.\n\n## Key Features\n- Broad Hardware Compatibility: Run with different brands of GPUs in Apple Macs, Windows PCs, and Linux servers.\nBroad Model Support: From LLMs to diffusion models, audio, embedding, and reranker models.\n- Scales with Your GPU Inventory: Easily add more GPUs or nodes to scale up your operations.\n- Distributed Inference: Supports both single-node multi-GPU and multi-node inference and serving.\n- Multiple Inference Backends: Supports llama-box (llama.cpp & stable-diffusion.cpp), vox-box and vLLM as the inference backends.\n- Lightweight Python Package: Minimal dependencies and operational overhead.\n- OpenAI-compatible APIs: Serve APIs that are compatible with OpenAI standards.\n- User and API key management: Simplified management of users and API keys.\n- GPU metrics monitoring: Monitor GPU performance and utilization in real-time.\n- Token usage and rate metrics: Track token usage and manage rate limits effectively.\n\n## Quickstart\n\nYou need setup your own GPUStack server. Please refer to GPUStack official docs [quickstart](https://docs.gpustack.ai/latest/quickstart/)\n\n## Configure\n\nAfter setting up your GPUStack server, you will need the following to configure this plugin:\n\n- GPUStack Server URL (e.g., http://yourserveraddress:port)\n- GPUStack API Key\n\nObtain these from your GPUStack server, then enter them into the settings. Click \"Save\" to activate the plugin.",
        "label": {
          "en_US": "GPUStack"
        },
        "latest_package_identifier": "langgenius/gpustack:0.0.6@295fbd66c106022326dc8b92bd7135ee431b19228709db46f48489726f6464e4",
        "latest_version": "0.0.6",
        "model": {
          "background": null,
          "configurate_methods": [
            "customizable-model"
          ],
          "description": {
            "en_US": "GPUStack is an open-source GPU cluster manager for running AI models.",
            "zh_Hans": "GPUStack 是一个专为运行 AI 模型而设计的开源 GPU 集群管理器，致力于支持基于任何品牌的异构 GPU 构建统一管理的算力集群"
          },
          "help": null,
          "icon_large": {
            "en_US": "icon_l_en.png"
          },
          "icon_small": {
            "en_US": "icon_s_en.png"
          },
          "label": {
            "en_US": "GPUStack"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "Server URL",
                  "zh_Hans": "服务器地址"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter the GPUStack server URL, e.g. http://192.168.1.100",
                  "zh_Hans": "输入 GPUStack 的服务器地址，如 http://192.168.1.100"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "endpoint_url"
              },
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              },
              {
                "default": "chat",
                "label": {
                  "en_US": "Completion mode"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Completion",
                      "zh_Hans": "补全"
                    },
                    "show_on": [],
                    "value": "completion"
                  },
                  {
                    "label": {
                      "en_US": "Chat",
                      "zh_Hans": "对话"
                    },
                    "show_on": [],
                    "value": "chat"
                  }
                ],
                "placeholder": {
                  "en_US": "Select completion type",
                  "zh_Hans": "选择补全类型"
                },
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "select",
                "variable": "mode"
              },
              {
                "default": "8192",
                "label": {
                  "en_US": "Model context size",
                  "zh_Hans": "模型上下文长度"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Model context size",
                  "zh_Hans": "输入您的模型上下文长度"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "context_size"
              },
              {
                "default": "8192",
                "label": {
                  "en_US": "Upper bound for max tokens",
                  "zh_Hans": "最大 token 上限"
                },
                "max_length": 0,
                "options": [],
                "placeholder": null,
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "text-input",
                "variable": "max_tokens_to_sample"
              },
              {
                "default": "no_call",
                "label": {
                  "en_US": "Function calling"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Function Call",
                      "zh_Hans": "Function Call"
                    },
                    "show_on": [],
                    "value": "function_call"
                  },
                  {
                    "label": {
                      "en_US": "Tool Call",
                      "zh_Hans": "Tool Call"
                    },
                    "show_on": [],
                    "value": "tool_call"
                  },
                  {
                    "label": {
                      "en_US": "Not Support",
                      "zh_Hans": "不支持"
                    },
                    "show_on": [],
                    "value": "no_call"
                  }
                ],
                "placeholder": null,
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "select",
                "variable": "function_calling_type"
              },
              {
                "default": "not_support",
                "label": {
                  "en_US": "Stream Function Calling"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Supported",
                      "zh_Hans": "支持"
                    },
                    "show_on": [],
                    "value": "supported"
                  },
                  {
                    "label": {
                      "en_US": "Not Supported",
                      "zh_Hans": "不支持"
                    },
                    "show_on": [],
                    "value": "not_support"
                  }
                ],
                "placeholder": null,
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "select",
                "variable": "stream_function_calling"
              },
              {
                "default": "no_support",
                "label": {
                  "en_US": "Vision Support",
                  "zh_Hans": "Vision 支持"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Support",
                      "zh_Hans": "支持"
                    },
                    "show_on": [],
                    "value": "support"
                  },
                  {
                    "label": {
                      "en_US": "Not Support",
                      "zh_Hans": "不支持"
                    },
                    "show_on": [],
                    "value": "no_support"
                  }
                ],
                "placeholder": null,
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "select",
                "variable": "vision_support"
              },
              {
                "default": "Chinese Female",
                "label": {
                  "en_US": "Available Voices (comma-separated)",
                  "zh_Hans": "可用声音（用英文逗号分隔）"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Chinese Female,Chinese Male, Japanese Male, Cantonese Female, English Female, English Male, Korean Female",
                  "zh_Hans": "Chinese Female,Chinese Male, Japanese Male, Cantonese Female, English Female, English Male, Korean Female"
                },
                "required": false,
                "show_on": [
                  {
                    "value": "tts",
                    "variable": "__model_type"
                  }
                ],
                "type": "text-input",
                "variable": "voices"
              },
              {
                "default": "600",
                "label": {
                  "en_US": "Timeout(s)",
                  "zh_Hans": "超时时间(秒)"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "600",
                  "zh_Hans": "600"
                },
                "required": false,
                "show_on": [
                  {
                    "value": "rerank",
                    "variable": "__model_type"
                  }
                ],
                "type": "text-input",
                "variable": "timeout"
              }
            ],
            "model": {
              "label": {
                "en_US": "Model Name",
                "zh_Hans": "模型名称"
              },
              "placeholder": {
                "en_US": "Enter your model name",
                "zh_Hans": "输入模型名称"
              }
            }
          },
          "models": [],
          "provider": "gpustack",
          "provider_credential_schema": null,
          "supported_model_types": [
            "llm",
            "text-embedding",
            "rerank",
            "speech2text",
            "tts"
          ]
        },
        "name": "gpustack",
        "org": "langgenius",
        "plugin_id": "langgenius/gpustack",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/gpustack.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": true,
              "speech2text": true,
              "text_embedding": true,
              "tts": true
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-14T11:14:26Z",
        "version_updated_at": "2025-04-14T11:14:26Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "ArXiv, https://arxiv.org.",
          "zh_Hans": "ArXiv，https://arxiv.org."
        },
        "category": "tool",
        "created_at": "2024-12-04T04:37:00Z",
        "endpoint": {},
        "icon": "langgenius/packages/arxiv/_assets/icon.svg",
        "index_id": "langgenius___arxiv",
        "install_count": 3208,
        "introduction": "# ArXiv Tool\n\n## Overview\n\nArXiv is an open-access repository for scholarly articles in physics, mathematics, computer science, quantitative biology, statistics, and related fields. It enables researchers to share their preprints and working papers. It provides search and browsing capabilities, allowing users to find research papers based on keywords, authors, and subjects.\n\n## Configuration\n\n### 1. Get ArXiv tools from Plugin Marketplace\n\nThe ArXiv tools could be found at the Plugin Marketplace, please install it first.\n\n![](./_assets/arxiv_1.PNG)\n\n### 2. Use the tool\n\nYou can use the ArXiv tool in the following application types.\n\n![](./_assets/arxiv_2.PNG)\n\n#### Chatflow / Workflow applications\n\nBoth Chatflow and Workflow applications support adding ArXiv tool nodes.\n\n#### Agent applications\n\nAdd the ArXiv tool in the Agent application, then enter the search command to call this tool.",
        "label": {
          "en_US": "ArXiv",
          "zh_Hans": "ArXiv"
        },
        "latest_package_identifier": "langgenius/arxiv:0.0.2@c09081d7df380f8555e67fc7705e4dff0a7dc973b7b65e42c08546d6fdae6b38",
        "latest_version": "0.0.2",
        "model": {},
        "name": "arxiv",
        "org": "langgenius",
        "plugin_id": "langgenius/arxiv",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/arxiv.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "search"
          }
        ],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "yash_parmar",
            "description": {
              "en_US": "Access to a vast repository of scientific papers and articles in various fields of research.",
              "zh_Hans": "访问各个研究领域大量科学论文和文章的存储库。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "ArXiv",
              "zh_Hans": "ArXiv"
            },
            "name": "arxiv",
            "tags": [
              "search"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool for searching scientific papers and articles from the Arxiv repository. Input can be an Arxiv ID or an author's name.",
                  "zh_Hans": "一个用于从Arxiv存储库搜索科学论文和文章的工具。 输入可以是Arxiv ID或作者姓名。"
                },
                "llm": "A tool for searching scientific papers and articles from the Arxiv repository. Input can be an Arxiv ID or an author's name."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "yash_parmar",
                "label": {
                  "en_US": "Arxiv Search",
                  "zh_Hans": "Arxiv 搜索"
                },
                "name": "arxiv_search"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The Arxiv ID or author's name used for searching.",
                    "zh_Hans": "用于搜索的Arxiv ID或作者姓名。"
                  },
                  "label": {
                    "en_US": "Query string",
                    "zh_Hans": "查询字符串"
                  },
                  "llm_description": "The Arxiv ID or author's name used for searching.",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:14:07Z",
        "version_updated_at": "2025-02-17T07:14:07Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "link dify with wechat subscription account",
          "ja_JP": "difyとウェチャットサブスクリプションアカウントを接続します",
          "pt_BR": "link dify with wechat subscription account",
          "zh_Hans": "连接dify与微信公众号"
        },
        "category": "extension",
        "created_at": "2025-03-13T16:40:25Z",
        "endpoint": {
          "endpoints": [
            {
              "hidden": false,
              "method": "GET",
              "path": "/wechat/input"
            },
            {
              "hidden": false,
              "method": "POST",
              "path": "/wechat/input"
            }
          ],
          "settings": [
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "App",
                "zh_Hans": "App"
              },
              "name": "app",
              "options": null,
              "placeholder": null,
              "required": true,
              "scope": "chat",
              "type": "app-selector",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Wechat Token",
                "zh_Hans": "微信公众号 Token"
              },
              "name": "wechat_token",
              "options": null,
              "placeholder": null,
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Wechat EncodingAESKey",
                "zh_Hans": "微信公众号 EncodingAESKey,配了就填,不配就留空"
              },
              "name": "encoding_aes_key",
              "options": null,
              "placeholder": null,
              "required": false,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Wechat AppId",
                "zh_Hans": "微信公众号 AppId"
              },
              "name": "app_id",
              "options": null,
              "placeholder": null,
              "required": false,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Wechat AppSecret",
                "zh_Hans": "微信公众号 AppSecret,如果需要发客服消息,则需要配"
              },
              "name": "app_secret",
              "options": null,
              "placeholder": null,
              "required": false,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Timeout Message",
                "zh_Hans": "超时提示信息,默认值为\"内容生成耗时较长，请稍等...\""
              },
              "name": "timeout_message",
              "options": null,
              "placeholder": null,
              "required": false,
              "scope": null,
              "type": "text-input",
              "url": null
            }
          ]
        },
        "icon": "bikeread/packages/dify_wechat_plugin/_assets/icon.svg",
        "index_id": "bikeread___dify_wechat_plugin",
        "install_count": 3164,
        "introduction": "# Dify WeChat Official Account Plugin\r\n\r\n**Author:** bikeread  \r\n**Version:** 0.0.2  \r\n**Type:** extension  \r\n**GitHub:** [Repository](https://github.com/bikeread/dify_wechat_plugin) | [Issues](https://github.com/bikeread/dify_wechat_plugin/issues)\r\n\r\n## Overview\r\n\r\nThe Dify WeChat Official Account Plugin is designed for content creators and public account owners who want to integrate AI capabilities into their WeChat Official Accounts. It provides 24/7 intelligent customer service and content assistance.\r\n\r\n## Quick Setup Guide\r\n\r\n### Step 1: Configure the Plugin\r\n\r\n1. After installing the plugin, create a new endpoint\r\n2. Configure the following settings:\r\n   - **Endpoint Name**: Any name you prefer\r\n   - **APP**: Select the Dify application that will handle user messages\r\n   - **WeChat Token**: Copy from your WeChat Official Account platform\r\n   - **EncodingAESKey**: Copy from your WeChat Official Account platform\r\n   - **AppID**: Your Official Account's AppID\r\n   - **AppSecret**: Your Official Account's AppSecret\r\n   - **Timeout Message**: A message to show when response takes longer than 15 seconds\r\n\r\n> **Note**: The timeout message is important because WeChat requires a response within 15 seconds. If your AI application takes longer to generate a complete response:\r\n> - The timeout message will be sent as an immediate response\r\n> - If AppID and AppSecret are configured, the complete AI response will be sent via WeChat's customer service message API\r\n> - Please ensure your Official Account has permission to send customer service messages\r\n\r\n### Step 2: Configure WeChat Official Account\r\n\r\n1. Log in to WeChat Official Account Platform (https://mp.weixin.qq.com/)\r\n2. Go to \"Settings & Development\" -> \"Basic Settings\"\r\n3. Under \"Server Configuration\":\r\n   - Copy one of the two endpoint URLs from your plugin configuration\r\n   - Paste it into the \"Server URL\" field\r\n   - Set the same Token as configured in your plugin\r\n   - Choose message encryption method (Plain Text or Secure Mode)\r\n   - If using Secure Mode, set the same EncodingAESKey as in your plugin\r\n4. Click \"Submit\" to save the configuration\r\n\r\n![Configuration Example](img.png)\r\n\r\n### Step 3: Verify Configuration\r\n\r\n1. After saving both plugin and WeChat configurations\r\n2. Send a test message to your Official Account\r\n3. If you receive an AI response, the configuration is successful\r\n\r\n## Plugin Configuration\r\n\r\nRequired Settings:\r\n- `wechat_token`: Same token as configured in your WeChat Official Account\r\n\r\nEncryption Mode Settings:\r\n- `encoding_aes_key`: Same as EncodingAESKey in your WeChat Official Account\r\n- `app_id`: Your Official Account's AppID\r\n\r\nCustomer Service Message Support:\r\n- `app_secret`: Your Official Account's AppSecret\r\n\r\nOptional Settings:\r\n- `timeout_message`: Temporary response message for timeout situations\r\n\r\n## Advanced Usage\r\n\r\n### Supported Message Types\r\n\r\nThis plugin supports multiple types of messages that your users can send to your WeChat Official Account:\r\n\r\n#### 1. Text Messages\r\n- Users can send regular text messages\r\n- Relevant input parameters:\r\n  ```\r\n  msgId: Unique message ID\r\n  msgType: Message type (\"text\")\r\n  fromUser: Sender's OpenID\r\n  createTime: Message creation timestamp\r\n  content: The text message content\r\n  ```\r\n\r\n#### 2. Image Messages\r\n- Users can send image content\r\n- The system provides image URL to AI for processing\r\n- Relevant input parameters:\r\n  ```\r\n  msgId: Unique message ID\r\n  msgType: Message type (\"image\")\r\n  fromUser: Sender's OpenID\r\n  createTime: Message creation timestamp\r\n  picUrl: URL of the image sent by user\r\n  ```\r\n\r\n#### 3. Voice Messages\r\n- Users can send voice recordings\r\n- The system converts voice to base64 format for AI processing\r\n- Relevant input parameters:\r\n  ```\r\n  msgId: Unique message ID\r\n  msgType: Message type (\"voice\")\r\n  fromUser: Sender's OpenID\r\n  createTime: Message creation timestamp\r\n  media_id: WeChat media ID for the voice\r\n  voice_base64: Base64 encoded voice data\r\n  voice_media_type: Media type of the voice\r\n  voice_format: Format of the voice (default \"amr\")\r\n  ```\r\n\r\n#### 4. Link Messages\r\n- Users can share links to articles/websites\r\n- The system extracts link information for AI processing\r\n- Relevant input parameters:\r\n  ```\r\n  msgId: Unique message ID\r\n  msgType: Message type (\"link\")\r\n  fromUser: Sender's OpenID\r\n  createTime: Message creation timestamp\r\n  url: The shared URL\r\n  title: Title of the shared link\r\n  description: Description of the shared link\r\n  ```\r\n\r\nYour Dify application can access all these parameters in the conversation context and respond accordingly.\r\n\r\n## Technical Architecture\r\n\r\nThis plugin uses a modular design with the following main components:\r\n\r\n### Directory Structure\r\n```\r\nendpoints/\r\n├── wechat/                    # Core WeChat processing module\r\n│   ├── __init__.py            # Package initialization\r\n│   ├── models.py              # WechatMessage model definition\r\n│   ├── parsers.py             # XML parser definition\r\n│   ├── formatters.py          # Response formatter definition\r\n│   ├── factory.py             # Message handler factory\r\n│   ├── crypto.py              # WeChat message encryption tools\r\n│   ├── retry_tracker.py       # Message retry tracker\r\n│   ├── api/                   # API-related\r\n│   │   ├── __init__.py        # API package initialization\r\n│   │   └── custom_message.py  # Customer service message sender\r\n│   └── handlers/              # Message handlers\r\n│       ├── __init__.py        # Handlers package initialization\r\n│       ├── base.py            # Abstract handler base class\r\n│       ├── text.py            # Text message handler\r\n│       ├── image.py           # Image message handler\r\n│       ├── voice.py           # Voice message handler\r\n│       ├── link.py            # Link message handler\r\n│       └── unsupported.py     # Unsupported message type handler\r\n├── wechat_get.py              # Handle WeChat server verification\r\n└── wechat_post.py             # Handle user messages\r\n```",
        "label": {
          "en_US": "Wechat Subscription Account",
          "ja_JP": "ウェチャットサブスクリプションアカウント",
          "pt_BR": "Conta de Assinatura do Wechat",
          "zh_Hans": "微信公众号对接助手"
        },
        "latest_package_identifier": "bikeread/dify_wechat_plugin:0.0.2@7b0051bf0c884b7dabec11c4e0608ce019a971fd2fdc5e4e99959f4d87678297",
        "latest_version": "0.0.2",
        "model": {},
        "name": "dify_wechat_plugin",
        "org": "bikeread",
        "plugin_id": "bikeread/dify_wechat_plugin",
        "plugins": {
          "agent_strategies": null,
          "endpoints": [
            "group/wechat_sub.yaml"
          ],
          "models": null,
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": true,
              "rerank": true,
              "speech2text": true,
              "text_embedding": true,
              "tts": true
            },
            "storage": {
              "enabled": true,
              "size": 1048576000
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-03-31T07:16:23Z",
        "version_updated_at": "2025-03-31T07:16:23Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Spider API integration, returning LLM-ready data by scraping & crawling websites."
        },
        "category": "tool",
        "created_at": "2024-12-04T04:46:54Z",
        "endpoint": {},
        "icon": "langgenius/packages/spider/_assets/icon.svg",
        "index_id": "langgenius___spider",
        "install_count": 3153,
        "introduction": "# Overview\nSpider is a web crawler for AI agents and LLMs provided by spider.cloud.\n## Configure\n### Get API Key\n1. Create an account in spider.cloud.\n2. Add sufficient fund to Spider.\n3. Get an [API key](https://spider.cloud/api-keys).\n![](_assets/spider_api.PNG)\nConfigure Spider tool\n1. Install Spider from Marketplace. \n![](_assets/spider_install.PNG)\n2. Add Spider node to your workflow.\n3. Fill in the Spider API key.",
        "label": {
          "en_US": "Spider"
        },
        "latest_package_identifier": "langgenius/spider:0.0.2@1f800653747430d0791387dc84f27de0fadba2ceadce8251fcce2a8cde808611",
        "latest_version": "0.0.2",
        "model": {},
        "name": "spider",
        "org": "langgenius",
        "plugin_id": "langgenius/spider",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/spider.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "utilities"
          },
          {
            "name": "search"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "Spider API Key"
              },
              "name": "spider_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Spider API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://spider.cloud/"
            }
          ],
          "identity": {
            "author": "William Espegren",
            "description": {
              "en_US": "Spider API integration, returning LLM-ready data by scraping & crawling websites."
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Spider"
            },
            "name": "spider",
            "tags": [
              "search",
              "utilities"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool for scraping & crawling webpages. Input should be a url.",
                  "zh_Hans": "用于抓取和爬取网页的工具。输入应该是一个网址。"
                },
                "llm": "A tool for scraping & crawling webpages. Input should be a url."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "William Espegren",
                "label": {
                  "en_US": "Web Scraper & Crawler",
                  "zh_Hans": "网页抓取与爬虫"
                },
                "name": "scraper_crawler"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "url to be scraped or crawled",
                    "zh_Hans": "要抓取或爬取的网址"
                  },
                  "label": {
                    "en_US": "URL",
                    "zh_Hans": "网址"
                  },
                  "llm_description": "url to either be scraped or crawled",
                  "max": null,
                  "min": null,
                  "name": "url",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "crawl",
                  "form": "form",
                  "human_description": {
                    "en_US": "used for selecting to either scrape the website or crawl the entire website following subpages",
                    "zh_Hans": "用于选择抓取网站或爬取整个网站及其子页面"
                  },
                  "label": {
                    "en_US": "Mode",
                    "zh_Hans": "模式"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "mode",
                  "options": [
                    {
                      "label": {
                        "en_US": "scrape",
                        "zh_Hans": "抓取"
                      },
                      "value": "scrape"
                    },
                    {
                      "label": {
                        "en_US": "crawl",
                        "zh_Hans": "爬取"
                      },
                      "value": "crawl"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 0,
                  "form": "form",
                  "human_description": {
                    "en_US": "specify the maximum number of pages to crawl per website. the crawler will stop after reaching this limit.",
                    "zh_Hans": "指定每个网站要爬取的最大页面数。爬虫将在达到此限制后停止。"
                  },
                  "label": {
                    "en_US": "maximum number of pages to crawl",
                    "zh_Hans": "最大爬取页面数"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": 0,
                  "name": "limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 0,
                  "form": "form",
                  "human_description": {
                    "en_US": "the crawl limit for maximum depth.",
                    "zh_Hans": "最大爬取深度的限制。"
                  },
                  "label": {
                    "en_US": "maximum depth of pages to crawl",
                    "zh_Hans": "最大爬取深度"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": 0,
                  "name": "depth",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "blacklist a set of paths that you do not want to crawl. you can use regex patterns to help with the list.",
                    "zh_Hans": "指定一组不想爬取的路径。您可以使用正则表达式模式来帮助定义列表。"
                  },
                  "label": {
                    "en_US": "url patterns to exclude",
                    "zh_Hans": "要排除的URL模式"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "blacklist",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Whitelist a set of paths that you want to crawl, ignoring all other routes that do not match the patterns. You can use regex patterns to help with the list.",
                    "zh_Hans": "指定一组要爬取的路径，忽略所有不匹配模式的其他路由。您可以使用正则表达式模式来帮助定义列表。"
                  },
                  "label": {
                    "en_US": "URL patterns to include",
                    "zh_Hans": "要包含的URL模式"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "whitelist",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Use Mozilla's readability to pre-process the content for reading. This may drastically improve the content for LLM usage.",
                    "zh_Hans": "如果启用，爬虫将仅返回页面的主要内容，不包括标题、导航、页脚等。"
                  },
                  "label": {
                    "en_US": "Pre-process the content for LLM usage",
                    "zh_Hans": "仅返回页面的主要内容"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "readability",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:13:35Z",
        "version_updated_at": "2025-02-17T07:13:35Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Encoding and decoding Base64 for text or image files",
          "ja_JP": "Base64のエンコードとデコードのためのツール",
          "zh_Hans": "Base64编码及解码，支持文本和图片文件"
        },
        "category": "tool",
        "created_at": "2025-03-03T11:48:50Z",
        "endpoint": {},
        "icon": "bowenliang123/packages/base64_codec/_assets/icon.png",
        "index_id": "bowenliang123___base64_codec",
        "install_count": 3151,
        "introduction": "# Base64 Codec - Encode and Decode Base64\n\n**Author:** [bowenliang123](https://github.com/bowenliang123)\n\n**Github Repository:** https://github.com/bowenliang123/base64_codec\n\n**Dify Marketplace:** https://marketplace.dify.ai/plugins/bowenliang123/base64_codec\n\nThis Dify plugin provides tools for encoding and decoding Base64 specified in [RFC 4648](https://datatracker.ietf.org/doc/html/rfc4648.html).\nIt supports text, image files and binary files for the input or output.\nURL safe Base64 encoding is also supported for text encoding and decoding.\n\n## Description\n\n| Tool                 | Input                                                    | Output              |\n|----------------------|----------------------------------------------------------|---------------------|\n| base64_encoder       | Raw text                                                 | Base64 encoded text |\n| base64_decoder       | Base64 encoded text                                      | Raw text            |\n| base64_image_encoder | Image file                                               | Base64 encoded text |\n| base64_image_decoder | Base64 encoded text of PNG, JPG, WEBP, SVG format prefix | Image file          |\n| base64_file_encoder  | Binary file                                              | Base64 encoded text |\n\n## Tools and Usage\n\n- Raw text → Base64 Encoded text\n\n  ![](_assets/snapshot1.png)\n\n- Base64 Encoded text → Raw text\n\n  ![](_assets/snapshot2.png)\n\n- Image file → Base64 Encoded text\n\n  ![](_assets/snapshot4.png)\n\n- Base64 Encoded text → Image file\n\n  ![](_assets/snapshot3.png)\n\n- Binary file → Base64 Encoded text\n\n## Changelog\n\n- 0.2.0\n    - Add `base64_file_encoder` for encoding binary file to Base64 encoded text\n\n- 0.1.0\n    - Add `base64_image_encoder` for encoding image file to Base64 encoded text\n\n- 0.0.3\n    - Support URL safe Base64 encoding and decoding\n\n- 0.0.1\n    - Initial release for text encoding and decoding and image decoding from Base64 encoded text\n\n## License\n\n- Apache License 2.0\n\n## Privacy\n\nThis plugin collects no data.\n\nAll the file transformations are completed locally. NO data is transmitted to third-party services.\n",
        "label": {
          "en_US": "Base64 Codec",
          "ja_JP": "Base64 コーデック",
          "zh_Hans": "Base64 编解码器"
        },
        "latest_package_identifier": "bowenliang123/base64_codec:0.2.1@348bebd1f5df34a5b4340b38cd19be8d4665fb893a39355f7ba1aa16640ebd88",
        "latest_version": "0.2.1",
        "model": {},
        "name": "base64_codec",
        "org": "bowenliang123",
        "plugin_id": "bowenliang123/base64_codec",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/base64_codec.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "bowenliang123",
            "description": {
              "en_US": "Encoding and decoding Base64 with text or image file as output",
              "ja_JP": "Base64のエンコードとデコードのためのツール",
              "zh_Hans": "Base64编码及解码，支持生成文本和图片文件"
            },
            "icon": "icon.png",
            "label": {
              "en_US": "Base64 Codec",
              "ja_JP": "Base64 コーデック",
              "zh_Hans": "Base64 编解码器"
            },
            "name": "base64_codec",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool to encode text to Base64-encoded string",
                  "zh_Hans": "将文本编码为 Base64 编码的字符串的工具"
                },
                "llm": "A tool to encode text to Base64-encoded string"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "bowenliang123",
                "label": {
                  "en_US": "Base64 Encoder",
                  "zh_Hans": "Base64 编码"
                },
                "name": "base64_encoder"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Text to encode",
                    "zh_Hans": "原始文本"
                  },
                  "label": {
                    "en_US": "Raw Text",
                    "zh_Hans": "原始文本"
                  },
                  "llm_description": "Text to encode",
                  "max": null,
                  "min": null,
                  "name": "plain_text",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "false",
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to enable URL safe alphabet",
                    "zh_Hans": "是否启用URL安全字符"
                  },
                  "label": {
                    "en_US": "Whether to enable URL safe alphabet",
                    "zh_Hans": "是否启用URL安全字符"
                  },
                  "llm_description": "Whether to enable URL safe alphabet, default to \"false\"",
                  "max": null,
                  "min": null,
                  "name": "urlsafe_enabled",
                  "options": [
                    {
                      "label": {
                        "en_US": "Yes",
                        "zh_Hans": "是"
                      },
                      "value": "true"
                    },
                    {
                      "label": {
                        "en_US": "No",
                        "zh_Hans": "否"
                      },
                      "value": "false"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool to decode Base64-encoded text",
                  "zh_Hans": "解码 Base64 编码的文本的工具"
                },
                "llm": "A tool to decode Base64-encoded text"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "bowenliang123",
                "label": {
                  "en_US": "Base64 Decoder",
                  "zh_Hans": "Base64 解码"
                },
                "name": "base64_decoder"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Base64-encoded text",
                    "zh_Hans": "Base64 编码的文本"
                  },
                  "label": {
                    "en_US": "Base64 encoded Text",
                    "zh_Hans": "已 Base64 编码的文本"
                  },
                  "llm_description": "A tool for decoding Base64-encoded text to plain text",
                  "max": null,
                  "min": null,
                  "name": "encoded_text",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "false",
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to enable URL safe alphabet",
                    "zh_Hans": "是否启用URL安全字符"
                  },
                  "label": {
                    "en_US": "Whether to enable URL safe alphabet",
                    "zh_Hans": "是否启用URL安全字符"
                  },
                  "llm_description": "Whether to enable URL safe alphabet, default to \"false\"",
                  "max": null,
                  "min": null,
                  "name": "urlsafe_enabled",
                  "options": [
                    {
                      "label": {
                        "en_US": "Yes",
                        "zh_Hans": "是"
                      },
                      "value": "true"
                    },
                    {
                      "label": {
                        "en_US": "No",
                        "zh_Hans": "否"
                      },
                      "value": "false"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for encoding image file to Base64-encoded text",
                  "zh_Hans": "将图片文件转为 Base64 编码文本"
                },
                "llm": "A tool for encoding image file to Base64-encoded text"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "bowenliang123",
                "label": {
                  "en_US": "Base64 Image Encoder",
                  "zh_Hans": "图片转Base64"
                },
                "name": "base64_image_encoder"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Input Image File",
                    "zh_Hans": "输入的图片文件"
                  },
                  "label": {
                    "en_US": "Input Image File",
                    "zh_Hans": "输入的图片文件"
                  },
                  "llm_description": "A tool for encoding image file to Base64-encoded text",
                  "max": null,
                  "min": null,
                  "name": "input_image",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "file"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for decoding Base64-encoded text to image file",
                  "zh_Hans": "解码 Base64 编码文本为图片的工具"
                },
                "llm": "A tool for decoding Base64-encoded text to image file"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "bowenliang123",
                "label": {
                  "en_US": "Base64 Image Decoder",
                  "zh_Hans": "Base64 转图片"
                },
                "name": "base64_image_decoder"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Base64 encoded image string, default convert to PNG, support PNG (\"data:image/png;base64\" prefix) and JPG (\"data:image/jpeg;base64\" prefix)",
                    "zh_Hans": "Base64 编码的图片字符串，默认转为PNG格式，支持PNG格式（data:image/png;base64开头）及JPG格式（data:image/jpeg;base64开头）"
                  },
                  "label": {
                    "en_US": "Base64 encoded Text",
                    "zh_Hans": "已 Base64 编码的图片字符串"
                  },
                  "llm_description": "A tool for decoding Base64-encoded text to image file",
                  "max": null,
                  "min": null,
                  "name": "encoded_text",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for encoding file to Base64-encoded text",
                  "zh_Hans": "将文件转为 Base64 编码文本"
                },
                "llm": "A tool for encoding file to Base64-encoded text"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "bowenliang123",
                "label": {
                  "en_US": "Base64 File Encoder",
                  "zh_Hans": "文件转Base64"
                },
                "name": "base64_file_encoder"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Input File",
                    "zh_Hans": "输入的文件"
                  },
                  "label": {
                    "en_US": "Input File",
                    "zh_Hans": "输入的文件"
                  },
                  "llm_description": "A tool for encoding file to Base64-encoded text",
                  "max": null,
                  "min": null,
                  "name": "input_file",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "file"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-11T02:47:22Z",
        "version_updated_at": "2025-04-11T02:47:22Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "GroqCloud provides access to the Groq Cloud API, which hosts models like LLama2 and Mixtral.",
          "zh_Hans": "GroqCloud 提供对 Groq Cloud API 的访问，其中托管了 LLama2 和 Mixtral 等模型。"
        },
        "category": "model",
        "created_at": "2024-11-29T11:39:10Z",
        "endpoint": {},
        "icon": "langgenius/packages/groq/_assets/icon_s_en.svg",
        "index_id": "langgenius___groq",
        "install_count": 3127,
        "introduction": "## Overview\n\nGroqCloud is a cloud-based inference platform from Groq, delivering exceptionally fast AI inference for LLMs and speech-to-text (STT) models. With this plugin, developers can easily integrate GroqCloud's powerful models, including Llama and the Whisper family, into applications requiring low latency via its API.\n\n## Configure\n\nTo use GroqCloud, you'll need your API key. After installing the plugin, find the Model Provider settings and enter the key you obtained from GroqCloud. Save to activate.\n\n![](./_assets/groq-01.png)\n",
        "label": {
          "en_US": "GroqCloud",
          "zh_Hans": "GroqCloud"
        },
        "latest_package_identifier": "langgenius/groq:0.0.6@a83039d06df8e854a045835daa525e882aaa673a07eb76e153f592d5c130040b",
        "latest_version": "0.0.6",
        "model": {
          "background": "#F5F5F4",
          "configurate_methods": [
            "predefined-model"
          ],
          "description": {
            "en_US": "GroqCloud provides access to the Groq Cloud API, which hosts models like LLama2 and Mixtral.",
            "zh_Hans": "GroqCloud 提供对 Groq Cloud API 的访问，其中托管了 LLama2 和 Mixtral 等模型。"
          },
          "help": {
            "title": {
              "en_US": "Get your API Key from GroqCloud",
              "zh_Hans": "从 GroqCloud 获取 API Key"
            },
            "url": {
              "en_US": "https://console.groq.com/keys"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.svg"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "GroqCloud",
            "zh_Hans": "GroqCloud"
          },
          "model_credential_schema": null,
          "models": [
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "DeepSeek R1 Distill Llama 70B SpecDec",
                "zh_Hans": "DeepSeek R1 Distill Llama 70B SpecDec"
              },
              "model": "deepseek-r1-distill-llama-70b-specdec",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 16000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "DeepSeek R1 Distill Llama 70B"
              },
              "model": "deepseek-r1-distill-llama-70b",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 16000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.75",
                "output": "0.99",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "DeepSeek R1 Distill Qwen 32B 128k",
                "zh_Hans": "DeepSeek R1 Distill Qwen 32B 128k"
              },
              "model": "deepseek-r1-distill-qwen-32b",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 16000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.69",
                "output": "0.69",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemma 7B Instruction Tuned",
                "zh_Hans": "Gemma 7B Instruction Tuned"
              },
              "model": "gemma-7b-it",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.05",
                "output": "0.1",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemma 2 9B Instruction Tuned",
                "zh_Hans": "Gemma 2 9B Instruction Tuned"
              },
              "model": "gemma2-9b-it",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.05",
                "output": "0.1",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama-3.1-405b-reasoning",
                "zh_Hans": "Llama-3.1-405b-reasoning"
              },
              "model": "llama-3.1-405b-reasoning",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.05",
                "output": "0.1",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama-3.1-70b-versatile",
                "zh_Hans": "Llama-3.1-70b-versatile"
              },
              "model": "llama-3.1-70b-versatile",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.05",
                "output": "0.1",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama-3.1-8b-instant",
                "zh_Hans": "Llama-3.1-8b-instant"
              },
              "model": "llama-3.1-8b-instant",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.05",
                "output": "0.1",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama 3.2 11B Text (Preview)",
                "zh_Hans": "Llama 3.2 11B Text (Preview)"
              },
              "model": "llama-3.2-11b-text-preview",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.05",
                "output": "0.1",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama 3.2 11B Vision (Preview)",
                "zh_Hans": "Llama 3.2 11B Vision (Preview)"
              },
              "model": "llama-3.2-11b-vision-preview",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.05",
                "output": "0.1",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama 3.2 1B Text (Preview)",
                "zh_Hans": "Llama 3.2 1B Text (Preview)"
              },
              "model": "llama-3.2-1b-preview",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.05",
                "output": "0.1",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama 3.2 3B Text (Preview)",
                "zh_Hans": "Llama 3.2 3B Text (Preview)"
              },
              "model": "llama-3.2-3b-preview",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.05",
                "output": "0.1",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama 3.2 90B Text (Preview)",
                "zh_Hans": "Llama 3.2 90B Text (Preview)"
              },
              "model": "llama-3.2-90b-text-preview",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.05",
                "output": "0.1",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama 3.2 90B Vision (Preview)",
                "zh_Hans": "Llama 3.2 90B Vision (Preview)"
              },
              "model": "llama-3.2-90b-vision-preview",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.05",
                "output": "0.1",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama 3.3 70b Speculative Decoding (PREVIEW)",
                "zh_Hans": "Llama 3.3 70b Speculative Decoding  (PREVIEW)"
              },
              "model": "llama-3.3-70b-specdec",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.05",
                "output": "0.1",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama-Guard-3-8B",
                "zh_Hans": "Llama-Guard-3-8B"
              },
              "model": "llama-guard-3-8b",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.2",
                "output": "0.2",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama-2-70B-4096",
                "zh_Hans": "Llama-2-70B-4096"
              },
              "model": "llama2-70b-4096",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.7",
                "output": "0.8",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama-3-70B-8192",
                "zh_Hans": "Llama-3-70B-8192"
              },
              "model": "llama3-70b-8192",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.59",
                "output": "0.79",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama-3-8B-8192",
                "zh_Hans": "Llama-3-8B-8192"
              },
              "model": "llama3-8b-8192",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.05",
                "output": "0.08",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama3-groq-70b-8192-tool-use (PREVIEW)",
                "zh_Hans": "Llama3-groq-70b-8192-tool-use (PREVIEW)"
              },
              "model": "llama3-groq-70b-8192-tool-use-preview",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.05",
                "output": "0.08",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Mixtral-8x7b-Instruct-v0.1",
                "zh_Hans": "Mixtral-8x7b-Instruct-v0.1"
              },
              "model": "mixtral-8x7b-32768",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 20480,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.27",
                "output": "0.27",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen 2.5 32B Instruct 128k",
                "zh_Hans": "Qwen 2.5 32B Instruct 128k"
              },
              "model": "qwen-2.5-32b",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.79",
                "output": "0.79",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen 2.5 Coder 32B Instruct 128k",
                "zh_Hans": "Qwen 2.5 Coder 32B Instruct 128k"
              },
              "model": "qwen-2.5-coder-32b",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.79",
                "output": "0.79",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen QwQ 32B (Preview) 128k",
                "zh_Hans": "Qwen QwQ 32B (Preview) 128k"
              },
              "model": "qwen-qwq-32b",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.29",
                "output": "0.39",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "distil-whisper-large-v3-en"
              },
              "model": "distil-whisper-large-v3-en",
              "model_properties": {
                "file_upload_limit": 1,
                "supported_file_extensions": "flac,mp3,mp4,mpeg,mpga,m4a,ogg,wav,webm"
              },
              "model_type": "speech2text",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "whisper-large-v3-turbo"
              },
              "model": "whisper-large-v3-turbo",
              "model_properties": {
                "file_upload_limit": 1,
                "supported_file_extensions": "flac,mp3,mp4,mpeg,mpga,m4a,ogg,wav,webm"
              },
              "model_type": "speech2text",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "whisper-large-v3"
              },
              "model": "whisper-large-v3",
              "model_properties": {
                "file_upload_limit": 1,
                "supported_file_extensions": "flac,mp3,mp4,mpeg,mpga,m4a,ogg,wav,webm"
              },
              "model_type": "speech2text",
              "parameter_rules": [],
              "pricing": null
            }
          ],
          "position": {
            "llm": [
              "deepseek-r1-distill-llama-70b",
              "deepseek-r1-distill-qwen-32b",
              "qwen-2.5-32b",
              "qwen-2.5-coder-32b",
              "qwen-qwq-32b",
              "llama-3.1-405b-reasoning",
              "llama-3.1-70b-versatile",
              "llama-3.1-8b-instant",
              "llama3-70b-8192",
              "llama3-8b-8192",
              "mixtral-8x7b-32768",
              "llama2-70b-4096",
              "llama-guard-3-8b"
            ],
            "speech2text": null
          },
          "provider": "groq",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              }
            ]
          },
          "supported_model_types": [
            "llm",
            "speech2text"
          ]
        },
        "name": "groq",
        "org": "langgenius",
        "plugin_id": "langgenius/groq",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/groq.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-03-20T10:34:09Z",
        "version_updated_at": "2025-03-18T12:42:29Z"
      },
      {
        "agent_strategy": {},
        "badges": [
          "partner"
        ],
        "brief": {
          "en_US": "Brave Search offers programmatic web search capabilities, providing private, high-quality search results in various formats with comprehensive sources and an intuitive structure.",
          "pt_BR": "Brave Search offers programmatic web search capabilities, providing private, high-quality search results in various formats with comprehensive sources and an intuitive structure.",
          "zh_Hans": "Brave Search 提供程序化的网络搜索功能，以各种格式提供私密、高质量的搜索结果，具有全面的来源和直观的结构。"
        },
        "category": "tool",
        "created_at": "2024-12-04T04:55:32Z",
        "endpoint": {},
        "icon": "langgenius/packages/brave/_assets/icon.svg",
        "index_id": "langgenius___brave",
        "install_count": 3116,
        "introduction": "Brave Search offers programmatic web search capabilities, providing private, high-quality search results in various formats with comprehensive sources and an **intuitive structure**.\n\nThe Brave Search API plugin is now integrated into Dify and accessible within the Tools category. You can use this plugin after installation in three ways:\n\n1. **Quick Chatbot Creation:** Create basic agents quickly by combining an LLM with the Brave Search tool.\n\n![](./_assets/brave_1.png)\n\n2. **Standalone Tool in Workflows:** Enhance LLM workflows with accuracy search outcomes by deploying the Brave Search tool.\n\n![](./_assets/brave_2.png)\n\n3. **Integration into Agent Nodes (Advanced Applications):** For more complex AI applications, integrate the Brave Search tool into Agent Nodes. Agent Nodes consist of three core components: **LLM + Tools + Strategies**:\n\n![](./_assets/brave_3.png)\n\n   - **LLM:** The core of the Agent Node, responsible for reasoning, tool invocation, and strategy execution.  \n   - **Tools:** Modules that extend LLM capabilities, such as **Brave Search**, image generation, web crawling, etc. You can customize and add tools.  \n   - **Strategies:** Guidelines that direct how the LLM uses tools to solve problems. These include officially supported methods (Function Call and ReAct) as well as custom strategies you can create using Llamaindex, LangGraph, or other frameworks.\n\n# Get Started\n\nEquip your AI applications with powerful search capabilities using the Brave Search tool. Refer to the [documentation](https://brave.com/api/guides) for a detailed user guide.",
        "label": {
          "en_US": "Brave",
          "pt_BR": "Brave",
          "zh_Hans": "Brave"
        },
        "latest_package_identifier": "langgenius/brave:0.0.2@aef68a4187ed04d101dee906521b26d9c9add32d826068b55892c41deddce63a",
        "latest_version": "0.0.2",
        "model": {},
        "name": "brave",
        "org": "langgenius",
        "plugin_id": "langgenius/brave",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/brave.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "search"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": "https://api.search.brave.com/res/v1/web/search",
              "helper": null,
              "label": {
                "en_US": "Brave server's Base URL",
                "zh_Hans": "Brave服务器的API URL"
              },
              "name": "base_url",
              "options": null,
              "placeholder": {
                "en_US": "https://api.search.brave.com/res/v1/web/search"
              },
              "required": false,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "Brave Search API key",
                "pt_BR": "Brave Search API key",
                "zh_Hans": "Brave Search API key"
              },
              "name": "brave_search_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Brave Search API key",
                "pt_BR": "Please input your Brave Search API key",
                "zh_Hans": "请输入你的 Brave Search API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://brave.com/search/api/"
            }
          ],
          "identity": {
            "author": "Yash Parmar",
            "description": {
              "en_US": "Brave",
              "pt_BR": "Brave",
              "zh_Hans": "Brave"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Brave",
              "pt_BR": "Brave",
              "zh_Hans": "Brave"
            },
            "name": "brave",
            "tags": [
              "search"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "BraveSearch is a privacy-focused search engine that leverages its own index to deliver unbiased, independent, and fast search results. It's designed to respect user privacy by not tracking searches or personal information, making it a secure choice for those concerned about online privacy.",
                  "pt_BR": "BraveSearch é um mecanismo de busca focado na privacidade que utiliza seu próprio índice para entregar resultados de busca imparciais, independentes e rápidos. Ele é projetado para respeitar a privacidade do usuário, não rastreando buscas ou informações pessoais, tornando-se uma escolha segura para aqueles preocupados com a privacidade online.",
                  "zh_Hans": "BraveSearch 是一个注重隐私的搜索引擎，它利用自己的索引来提供公正、独立和快速的搜索结果。它旨在通过不跟踪搜索或个人信息来尊重用户隐私，为那些关注在线隐私的用户提供了一个安全的选择。"
                },
                "llm": "BraveSearch is a privacy-centric search engine utilizing its unique index to offer unbiased, independent, and swift search results. It aims to protect user privacy by avoiding the tracking of search activities or personal data, presenting a secure option for users mindful of their online privacy."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Yash Parmar",
                "label": {
                  "en_US": "BraveSearch",
                  "pt_BR": "BraveSearch",
                  "zh_Hans": "BraveSearch"
                },
                "name": "brave_search"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The text input used for initiating searches on the web, focusing on delivering relevant and accurate results without compromising user privacy.",
                    "pt_BR": "A entrada de texto usada para iniciar pesquisas na web, focada em entregar resultados relevantes e precisos sem comprometer a privacidade do usuário.",
                    "zh_Hans": "用于在网上启动搜索的文本输入，专注于提供相关且准确的结果，同时不妨碍用户隐私。"
                  },
                  "label": {
                    "en_US": "Query string",
                    "pt_BR": "Query string",
                    "zh_Hans": "查询语句"
                  },
                  "llm_description": "Keywords or phrases entered to perform searches, aimed at providing relevant and precise results while ensuring the privacy of the user is maintained.",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 3,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The number of search results to return, allowing users to control the breadth of their search output.",
                    "pt_BR": "O número de resultados de pesquisa a serem retornados, permitindo que os usuários controlem a amplitude de sua saída de pesquisa.",
                    "zh_Hans": "要返回的搜索结果数量，允许用户控制他们搜索输出的广度。"
                  },
                  "label": {
                    "en_US": "Result count",
                    "pt_BR": "Contagem de resultados",
                    "zh_Hans": "结果数量"
                  },
                  "llm_description": "Specifies the amount of search results to be displayed, offering users the ability to adjust the scope of their search findings.",
                  "max": null,
                  "min": null,
                  "name": "count",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "Ensure the JSON output is ASCII encoded",
                    "pt_BR": "Ensure the JSON output is ASCII encoded",
                    "zh_Hans": "确保输出的 JSON 是 ASCII 编码"
                  },
                  "label": {
                    "en_US": "Ensure ASCII",
                    "pt_BR": "Ensure ASCII",
                    "zh_Hans": "确保 ASCII"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "ensure_ascii",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-26T03:55:35Z",
        "version_updated_at": "2025-02-26T03:55:35Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Python tool for converting files and office documents to Markdown.",
          "ja_JP": "Python tool for converting files and office documents to Markdown.",
          "pt_BR": "Python tool for converting files and office documents to Markdown.",
          "zh_Hans": "Python tool for converting files and office documents to Markdown."
        },
        "category": "tool",
        "created_at": "2025-02-18T10:52:06Z",
        "endpoint": {},
        "icon": "yevanchen/packages/markitdown/_assets/micro.png",
        "index_id": "yevanchen___markitdown",
        "install_count": 3017,
        "introduction": "# MarkItDown Dify Plugin\n\nA powerful document conversion plugin for Dify based on MarkItDown 0.0.2a1, designed to convert various file formats into Markdown with high accuracy and reliability.\n\n## Overview\n\nThis plugin serves as an excellent alternative to traditional document extraction nodes, offering robust file conversion capabilities within the Dify ecosystem. It leverages MarkItDown's plugin-based architecture to provide seamless conversion of multiple file formats to Markdown.\n\n## Supported File Formats\n\n- **Documents**\n  - PDF files (`.pdf`)\n  - Microsoft Word documents (`.doc`, `.docx`)\n  - Microsoft PowerPoint presentations (`.ppt`, `.pptx`)\n  - Microsoft Excel spreadsheets (`.xls`, `.xlsx`)\n  - HTML files (`.html`, `.htm`)\n\n- **Media Files**\n  - Images with EXIF metadata and OCR support\n  - Audio files with metadata and speech transcription\n\n- **Data Formats**\n  - CSV files\n  - JSON documents\n  - XML files\n  - Text files\n\n- **Archives**\n  - ZIP files (with automatic content iteration)\n\n## Usage in Dify\n\n### Parameters\n\nThe plugin accepts the following parameters in the Dify interface:\n\n```yaml\nfiles:\n  type: files\n  required: false\n  description: \"Array of files to be converted to Markdown\"\n```\n\n### Response Format\n\nThe plugin provides three types of response formats for maximum flexibility:\n\n1. **JSON Response** (New)\n   ```json\n   {\n     \"status\": \"success|error\",\n     \"total_files\": 2,\n     \"successful_conversions\": 2,\n     \"results\": [\n       {\n         \"filename\": \"example1.pdf\",\n         \"original_format\": \"pdf\",\n         \"markdown_content\": \"# Content...\",\n         \"status\": \"success\"\n       },\n       {\n         \"filename\": \"example2.docx\",\n         \"original_format\": \"docx\",\n         \"markdown_content\": \"# Content...\",\n         \"status\": \"success\"\n       }\n     ]\n   }\n   ```\n\n   Error response example:\n   ```json\n   {\n     \"filename\": \"failed.pdf\",\n     \"original_format\": \"pdf\",\n     \"error\": \"Error message\",\n     \"status\": \"error\"\n   }\n   ```\n\n2. **Blob Response**\n   - Returns raw markdown content as a blob\n   - Includes mime_type metadata: \"text/markdown\"\n   - Useful for direct content processing\n\n3. **Text Response** (Legacy)\n   - Single File:\n   ```\n   [Markdown content of the file]\n   ```\n\n   - Multiple Files:\n   ```\n   ==================================================\n   File 1: example1.pdf\n   ==================================================\n\n   [Markdown content of file 1]\n\n   ==================================================\n   File 2: example2.docx\n   ==================================================\n\n   [Markdown content of file 2]\n   ```\n\n### Example Usage in Prompts\n\n```\nPlease convert the attached files to Markdown format.\n{@markitdown files=[\"document.pdf\", \"presentation.pptx\"]}\n```\n\n## Features\n\n- **Batch Processing**: Process multiple files in a single request\n- **Clear File Separation**: When processing multiple files, content is clearly separated with headers and dividers\n- **Format Preservation**: Maintains important formatting elements in the Markdown output\n- **Error Handling**: Provides clear error messages for failed conversions\n- **Automatic Cleanup**: Temporary files are automatically managed and cleaned up\n\n## Best Practices\n\n1. **File Size**: While there's no strict limit, it's recommended to keep individual files under 50MB for optimal performance\n2. **Batch Processing**: You can process multiple files simultaneously, but consider limiting batches to 5-10 files\n3. **Format Support**: When possible, use standard file formats from the supported list for best results\n4. **Error Handling**: Always check for error messages in the response when processing critical documents\n\n## Integration Example\n\nHere's how to integrate the plugin into your Dify workflow:\n\n1. **Document Analysis Flow**\n   ```\n   Input: {files} -> MarkItDown Plugin -> LLM Analysis\n   ```\n\n2. **Content Extraction Flow**\n   ```\n   Input: {files} -> MarkItDown Plugin -> Text Extraction -> Database Storage\n   ```\n\n## Advantages Over Traditional Document Extraction\n\n1. **Format Support**: Broader range of supported file formats\n2. **Metadata Preservation**: Retains important metadata from source files\n3. **Structured Output**: Consistently formatted Markdown output\n4. **Batch Processing**: Efficient handling of multiple files\n5. **Clear Separation**: Better organization of multiple file contents\n6. **Error Handling**: Comprehensive error reporting and handling\n\n## Technical Notes\n\n- Based on MarkItDown 0.0.2a1\n- Maintains backward compatibility with 0.0.1a3\n- Implements plugin-based architecture for extensibility\n- Automatic temporary file management\n- Thread-safe processing for concurrent requests\n\n## Limitations\n\n- Network connectivity required for some conversion operations\n- Processing time may vary based on file size and complexity\n- Some advanced formatting may be simplified in the Markdown output\n\n## Support\n\nFor issues and feature requests, please create an issue in the repository or contact the plugin maintainer.\n\n---\n\n*Note: This plugin is based on MarkItDown 0.0.2a1 and may receive updates as the base library evolves to its first non-alpha release.*\n\n## Response Types Use Cases\n\n1. **JSON Response**\n   - Workflow automation and data processing\n   - Status tracking and error handling\n   - Structured data extraction\n   - API integrations\n\n2. **Blob Response**\n   - Direct content processing\n   - Raw markdown handling\n   - Stream processing\n   - File system operations\n\n3. **Text Response**\n   - Human readable output\n   - Legacy system compatibility\n   - Simple content viewing\n   - Direct LLM input\n\n\n\ncontact：evanchen@dify.ai",
        "label": {
          "en_US": "markitdown",
          "ja_JP": "markitdown",
          "pt_BR": "markitdown",
          "zh_Hans": "markitdown"
        },
        "latest_package_identifier": "yevanchen/markitdown:0.0.3@02e42fa0d944c2e717183bbf3e9c8ac0c708c9745d84f7407824631e7735d6af",
        "latest_version": "0.0.3",
        "model": {},
        "name": "markitdown",
        "org": "yevanchen",
        "plugin_id": "yevanchen/markitdown",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/markitdown.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": false,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "yevanchen",
            "description": {
              "en_US": "Python tool for converting files and office documents to Markdown.",
              "pt_BR": "Python tool for converting files and office documents to Markdown.",
              "zh_Hans": "Python tool for converting files and office documents to Markdown."
            },
            "icon": "micro.png",
            "label": {
              "en_US": "markitdown",
              "pt_BR": "markitdown",
              "zh_Hans": "markitdown"
            },
            "name": "markitdown",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Python tool for converting files and office documents to Markdown.",
                  "pt_BR": "Python tool for converting files and office documents to Markdown.",
                  "zh_Hans": "Python tool for converting files and office documents to Markdown."
                },
                "llm": "Python tool for converting files and office documents to Markdown."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "yevanchen",
                "label": {
                  "en_US": "markitdown",
                  "pt_BR": "markitdown",
                  "zh_Hans": "markitdown"
                },
                "name": "markitdown"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Upload files for processing",
                    "pt_BR": "Carregar arquivos para processamento",
                    "zh_Hans": "上传文件进行处理"
                  },
                  "label": {
                    "en_US": "Files",
                    "pt_BR": "Arquivos",
                    "zh_Hans": "文件"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "files",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "files"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-08T06:48:28Z",
        "version_updated_at": "2025-04-08T06:48:28Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Convert your PNG and JPG images to SVG vectors quickly and easily. Fully automatically. Using AI.",
          "zh_Hans": "一个将 PNG 和 JPG 图像快速轻松地转换为 SVG 矢量图的工具。"
        },
        "category": "tool",
        "created_at": "2024-12-18T08:14:21Z",
        "endpoint": {},
        "icon": "langgenius/packages/vectorizer/_assets/icon.png",
        "index_id": "langgenius___vectorizer",
        "install_count": 3006,
        "introduction": "## Overview\n\n\n**Vectorizer.AI** is a powerful tool that converts PNG and JPG images into scalable SVG vector graphics quickly and easily. Powered by AI, the conversion process is fully automated, allowing you to transform raster images into high-quality vector formats with minimal effort.\n\nThis tool is ideal for graphic designers, developers, and anyone who needs vectorized images for their projects.\n\n---\n\n## Configuration\n\nTo start using **Vectorizer.AI**, follow these steps:\n\n1. **Install Vectorizer.AI Tool**  \n   Access the Plugin Marketplace and install the Vectorizer.AI tool.\n\n2. **Apply for a Firecrawl API Key**  \n   Go to the [Vectorizer.AI API Keys](https://vectorizer.ai/api) page, create a new API Key, and ensure your account has sufficient balance.\n\n3. **Authorize Vectorizer.AI**  \n   Navigate to **Tools > Vectorizer.AI > To Authorize** in your application and provide API Key ID and Secret to activate the plugin.\n\n![](./_assets/vectorizer-01.png)\n\n## Tool Feature\n\nWhen using **Vectorizer.AI**, you need to configure the following input parameters to convert your images into SVG vector files:\n\n1. **Image** (*Files, Required*):\n   - Description: The image file that you want to convert.\n   - Supported Formats: PNG and JPG.\n   - This field is mandatory, and the uploaded file will serve as the source for vectorization.\n\n2. **Mode** (*String, Required*):\n   - Description: Specifies the operating mode for the tool.\n   - Default Value: `test`.\n   - Purpose: Ensures the conversion process operates under optimal settings for high-quality output.\n\n<img src=\"./_assets/vectorizer-02.png\" width=\"400\"/>\n\n## Usage\n\n### Chatflow / Workflow Apps\n\n1. Add the **Vectorizer.AI** node to your Chatflow or Workflow pipeline.\n2. Upload the image file by using file variables.\n3. Execute the pipeline to generate the SVG file, which can be further processed or shared within the workflow.\n\n![](./_assets/vectorizer-03.png)\n\n### Agent Apps\n\n1. Integrate **Vectorizer.AI** into your Agent application.\n2. Provide the PNG or JPG file via the chat interface.\n3. The tool processes the file and returns the converted SVG, ready for use.\n\n![](./_assets/vectorizer-04.png)\n",
        "label": {
          "en_US": "Vectorizer.AI",
          "zh_Hans": "Vectorizer.AI"
        },
        "latest_package_identifier": "langgenius/vectorizer:0.0.2@5213191fd5d455b36f4ca7bdf4729e4baad1d5003074d5eaa9baa1df8e1729bd",
        "latest_version": "0.0.2",
        "model": {},
        "name": "vectorizer",
        "org": "langgenius",
        "plugin_id": "langgenius/vectorizer",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/vectorizer.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "image"
          },
          {
            "name": "productivity"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Get your Vectorizer.AI API Key from Vectorizer.AI.",
                "zh_Hans": "从 Vectorizer.AI 获取您的 Vectorizer.AI API Key。"
              },
              "label": {
                "en_US": "Vectorizer.AI API Key ID",
                "zh_Hans": "Vectorizer.AI API Key ID"
              },
              "name": "api_key_name",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Vectorizer.AI ApiKey name",
                "zh_Hans": "请输入你的 Vectorizer.AI ApiKey name"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://vectorizer.ai/api"
            },
            {
              "default": null,
              "help": {
                "en_US": "Get your Vectorizer.AI API Key from Vectorizer.AI.",
                "zh_Hans": "从 Vectorizer.AI 获取您的 Vectorizer.AI API Key。"
              },
              "label": {
                "en_US": "Vectorizer.AI API Key Secret",
                "zh_Hans": "Vectorizer.AI API Key Secret"
              },
              "name": "api_key_value",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Vectorizer.AI ApiKey",
                "zh_Hans": "请输入你的 Vectorizer.AI ApiKey"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            }
          ],
          "identity": {
            "author": "langgenius",
            "description": {
              "en_US": "Convert your PNG and JPG images to SVG vectors quickly and easily. Fully automatically. Using AI.",
              "zh_Hans": "一个将 PNG 和 JPG 图像快速轻松地转换为 SVG 矢量图的工具。"
            },
            "icon": "icon.png",
            "label": {
              "en_US": "Vectorizer.AI",
              "zh_Hans": "Vectorizer.AI"
            },
            "name": "vectorizer",
            "tags": [
              "productivity",
              "image"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Convert your PNG and JPG images to SVG vectors quickly and easily. Fully automatically. Using AI.",
                  "zh_Hans": "一个将 PNG 和 JPG 图像快速轻松地转换为 SVG 矢量图的工具。"
                },
                "llm": "A tool for converting images to SVG vectors. you should input the image id as the input of this tool. the image id can be got from parameters."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Vectorizer.AI",
                  "zh_Hans": "Vectorizer.AI"
                },
                "name": "vectorizer"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The image to be converted.",
                    "zh_Hans": "要转换的图片。"
                  },
                  "label": {
                    "en_US": "image"
                  },
                  "llm_description": "you should not input this parameter. just input the image_id.",
                  "max": null,
                  "min": null,
                  "name": "image",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "file"
                },
                {
                  "auto_generate": null,
                  "default": "test",
                  "form": "form",
                  "human_description": {
                    "en_US": "It is free to integrate with and test out the API in test mode, no subscription required.",
                    "zh_Hans": "在测试模式下，可以免费测试API。"
                  },
                  "label": {
                    "en_US": "Mode",
                    "zh_Hans": "模式"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "mode",
                  "options": [
                    {
                      "label": {
                        "en_US": "production",
                        "zh_Hans": "生产模式"
                      },
                      "value": "production"
                    },
                    {
                      "label": {
                        "en_US": "test",
                        "zh_Hans": "测试模式"
                      },
                      "value": "test"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-20T02:26:28Z",
        "version_updated_at": "2025-03-20T02:26:28Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "OpenLLM"
        },
        "category": "model",
        "created_at": "2024-12-06T10:51:10Z",
        "endpoint": {},
        "icon": "langgenius/packages/openllm/_assets/icon_s_en.svg",
        "index_id": "langgenius___openllm",
        "install_count": 2956,
        "introduction": "",
        "label": {
          "en_US": "OpenLLM"
        },
        "latest_package_identifier": "langgenius/openllm:0.0.2@4e5440508ce792e3d973e7e05a8172fe7ab5fbbfdfcfd7c26ab7299344853318",
        "latest_version": "0.0.2",
        "model": {
          "background": "#F9FAFB",
          "configurate_methods": [
            "customizable-model"
          ],
          "description": {
            "en_US": "OpenLLM"
          },
          "help": {
            "title": {
              "en_US": "How to deploy OpenLLM",
              "zh_Hans": "如何部署 OpenLLM"
            },
            "url": {
              "en_US": "https://github.com/bentoml/OpenLLM"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.svg"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "OpenLLM"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "Server url",
                  "zh_Hans": "服务器URL"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter the url of your OpenLLM, e.g. http://192.168.1.100:3000",
                  "zh_Hans": "在此输入OpenLLM的服务器地址，如 http://192.168.1.100:3000"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "server_url"
              }
            ],
            "model": {
              "label": {
                "en_US": "Model Name",
                "zh_Hans": "模型名称"
              },
              "placeholder": {
                "en_US": "Enter your model name",
                "zh_Hans": "输入模型名称"
              }
            }
          },
          "models": [],
          "position": {
            "llm": null,
            "text_embedding": null
          },
          "provider": "openllm",
          "provider_credential_schema": null,
          "supported_model_types": [
            "llm",
            "text-embedding"
          ]
        },
        "name": "openllm",
        "org": "langgenius",
        "plugin_id": "langgenius/openllm",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/openllm.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-02-17T07:01:03Z",
        "version_updated_at": "2025-02-17T07:01:03Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Generate podcast audio using Text-to-Speech services",
          "zh_Hans": "使用文字转语音服务生成播客音频"
        },
        "category": "tool",
        "created_at": "2024-12-05T05:52:46Z",
        "endpoint": {},
        "icon": "langgenius/packages/podcast_generator/_assets/icon.svg",
        "index_id": "langgenius___podcast_generator",
        "install_count": 2950,
        "introduction": "## Overview\n\n**Podcast Generator** is a powerful tool for creating podcast audio files using Text-to-Speech (TTS) services. This tool can generate a podcast with alternating voices by providing a script, making it ideal for dialogue-based content, interviews, or storytelling.\n\nPowered by OpenAI's TTS service, Podcast Generator simplifies the production of high-quality audio content.\n\n## Configuration\n\nTo start using Podcast Generator, follow these steps:\n\n1. **Install the Podcast Generator Tool** Open the Plugin Marketplace, search for the Podcast Generator tool, and install it to integrate it with your application.\n\n2. **Get a Podcast Generator API Key** Go to the [OpenAI Platform](https://platform.openai.com/), create a new API Key, and ensure your account is properly set up with sufficient access.\n\n3. **Authorize Podcast Generator** In Dify, go to **Plugins > Podcast Generator > Authorize**. Enter your API Key to activate the tool.\n\n![](./_assets/podcast_generator-01.png)\n\n## Tool Feature\n\nThe **Podcast Audio Generator** action converts your text script into a podcast audio file using two alternating voices.\n\n1. **Input the Podcast Script** Provide a script containing alternating lines for two hosts, separated by newline characters. Each line corresponds to what one of the hosts will say.\n\n2. **Select Host Voices** Choose a voice for **Host 1** and **Host 2** from the available options. These voices will be used to narrate the respective lines in the script.\n\n3. **Generate the Podcast Audio** Once the script and voices are set, run the action to create your podcast audio file. The result will combine the two voices, alternating as per the script.\n\n<img src=\"./_assets/podcast_generator-02.png\" width=\"400\" />\n\n## Usage\n\nPodcast Generator can seamlessly integrate **Chatflow / Workflow Apps** and **Agent Apps**.\n\n### Chatflow / Workflow Apps\n\n1. Add the Podcast Generator node to your Chatflow or Workflow pipeline.\n2. Input the podcast script in the node configuration.\n3. Run the pipeline to generate and deliver the podcast audio as part of the workflow.\n\n![](./_assets/podcast_generator-03.png)\n\n### Agent Apps\n\n1. Add the Podcast Generator tool to your Agent application.\n2. Send a podcast script via the chat interface.\n3. The tool processes the script and returns the generated audio file to the user.\n\n![](./_assets/podcast_generator-04.png)\n\n## Use Cases\n\n* **Podcast Creation**: Quickly produce podcasts for storytelling, interviews, or educational content.\n* **Dialogue Simulations**: Generate podcasts with alternating voices to mimic conversations or debates.\n* **Marketing Content**: Create engaging audio advertisements or announcements.\n* **Content Accessibility**: Provide audio versions of written content for visually impaired audiences.\n\nThe Podcast Generator makes podcast production efficient and accessible, enabling creators to focus on crafting compelling scripts while automating the audio generation process.\n",
        "label": {
          "en_US": "Podcast Generator",
          "zh_Hans": "播客生成器"
        },
        "latest_package_identifier": "langgenius/podcast_generator:0.0.3@d05fc9f85221a19e72176c8f42dcd17dfcc1326411feb1edced0169c2782e5da",
        "latest_version": "0.0.3",
        "model": {},
        "name": "podcast_generator",
        "org": "langgenius",
        "plugin_id": "langgenius/podcast_generator",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/podcast_generator.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "API Key",
                "zh_Hans": "API 密钥"
              },
              "name": "api_key",
              "options": null,
              "placeholder": {
                "en_US": "Enter your TTS service API key",
                "zh_Hans": "输入您的 TTS 服务 API 密钥"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "OpenAI base URL",
                "zh_Hans": "OpenAI base URL"
              },
              "name": "openai_base_url",
              "options": null,
              "placeholder": {
                "en_US": "Please input your OpenAI base URL",
                "zh_Hans": "请输入你的 OpenAI base URL"
              },
              "required": false,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "TTS Service",
                "zh_Hans": "TTS 服务"
              },
              "name": "tts_service",
              "options": [
                {
                  "label": {
                    "en_US": "OpenAI TTS",
                    "zh_Hans": "OpenAI TTS"
                  },
                  "value": "openai"
                }
              ],
              "placeholder": {
                "en_US": "Select a TTS service",
                "zh_Hans": "选择一个 TTS 服务"
              },
              "required": true,
              "scope": null,
              "type": "select",
              "url": null
            }
          ],
          "identity": {
            "author": "langgenius",
            "description": {
              "en_US": "Generate podcast audio using Text-to-Speech services",
              "zh_Hans": "使用文字转语音服务生成播客音频"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Podcast Generator",
              "zh_Hans": "播客生成器"
            },
            "name": "podcast_generator",
            "tags": []
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Generate a podcast audio file from a script with two alternating voices using OpenAI's TTS service.",
                  "zh_Hans": "使用 OpenAI 的 TTS 服务，从包含两个交替声音的脚本生成播客音频文件。"
                },
                "llm": "This tool converts a prepared podcast script into an audio file using OpenAI's Text-to-Speech service, with two specified voices for alternating hosts."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Podcast Audio Generator",
                  "zh_Hans": "播客音频生成器"
                },
                "name": "podcast_audio_generator"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "A string containing alternating lines for two hosts, separated by newline characters.",
                    "zh_Hans": "包含两位主持人交替台词的字符串，每行用换行符分隔。"
                  },
                  "label": {
                    "en_US": "Podcast Script",
                    "zh_Hans": "播客脚本"
                  },
                  "llm_description": "A string representing the script, with alternating lines for two hosts separated by newline characters.",
                  "max": null,
                  "min": null,
                  "name": "script",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The voice for the first host.",
                    "zh_Hans": "第一位主持人的音色。"
                  },
                  "label": {
                    "en_US": "Host 1 Voice",
                    "zh_Hans": "主持人1 音色"
                  },
                  "llm_description": "The voice identifier for the first host's voice.",
                  "max": null,
                  "min": null,
                  "name": "host1_voice",
                  "options": [
                    {
                      "label": {
                        "en_US": "Alloy",
                        "zh_Hans": "Alloy"
                      },
                      "value": "alloy"
                    },
                    {
                      "label": {
                        "en_US": "Echo",
                        "zh_Hans": "Echo"
                      },
                      "value": "echo"
                    },
                    {
                      "label": {
                        "en_US": "Fable",
                        "zh_Hans": "Fable"
                      },
                      "value": "fable"
                    },
                    {
                      "label": {
                        "en_US": "Onyx",
                        "zh_Hans": "Onyx"
                      },
                      "value": "onyx"
                    },
                    {
                      "label": {
                        "en_US": "Nova",
                        "zh_Hans": "Nova"
                      },
                      "value": "nova"
                    },
                    {
                      "label": {
                        "en_US": "Shimmer",
                        "zh_Hans": "Shimmer"
                      },
                      "value": "shimmer"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The voice for the second host.",
                    "zh_Hans": "第二位主持人的音色。"
                  },
                  "label": {
                    "en_US": "Host 2 Voice",
                    "zh_Hans": "主持人2 音色"
                  },
                  "llm_description": "The voice identifier for the second host's voice.",
                  "max": null,
                  "min": null,
                  "name": "host2_voice",
                  "options": [
                    {
                      "label": {
                        "en_US": "Alloy",
                        "zh_Hans": "Alloy"
                      },
                      "value": "alloy"
                    },
                    {
                      "label": {
                        "en_US": "Echo",
                        "zh_Hans": "Echo"
                      },
                      "value": "echo"
                    },
                    {
                      "label": {
                        "en_US": "Fable",
                        "zh_Hans": "Fable"
                      },
                      "value": "fable"
                    },
                    {
                      "label": {
                        "en_US": "Onyx",
                        "zh_Hans": "Onyx"
                      },
                      "value": "onyx"
                    },
                    {
                      "label": {
                        "en_US": "Nova",
                        "zh_Hans": "Nova"
                      },
                      "value": "nova"
                    },
                    {
                      "label": {
                        "en_US": "Shimmer",
                        "zh_Hans": "Shimmer"
                      },
                      "value": "shimmer"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:08:15Z",
        "version_updated_at": "2025-02-17T07:08:15Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "send email through smtp protocol",
          "zh_Hans": "通过smtp协议发送电子邮件"
        },
        "category": "tool",
        "created_at": "2024-12-04T04:49:25Z",
        "endpoint": {},
        "icon": "langgenius/packages/email/_assets/icon.svg",
        "index_id": "langgenius___email",
        "install_count": 2949,
        "introduction": "# Email\n\n## Overview\n\nThe email is a method of electronic communication for sending and receiving information through the Internet. This tool helps users to send emails to one person or to multiple recipients with support for CC, BCC, file attachments, and markdown-to-HTML conversion.\n\n## Configuration\n\n### 1. Get email tools from Plugin Marketplace\n\nThe email tools could be found at the Plugin Marketplace, please install it first.\n\n### 2. Fill in the configuration in Dify\n\nOn the Dify navigation page, click `Tools > email > To authorize`.\n\n![](./_assets/email_1.PNG)\n\n**Note**: If your email account is gmail, please use \"START TLS\" as encrypt method, the smtp server is smtp.gmail.com, and the port is 587. For other common email service settings, please check this [manual](https://docs.mattermost.com/configure/smtp-email.html#sample-smtp-settings).\n\n### 3. Use the tool\n\nYou can use the email tool in the following application types.\n\n![](./_assets/email_2.PNG)\n\n#### Chatflow / Workflow applications\nBoth Chatflow and Workflow applications support adding a `email` tool node.\n\n### 4. Advanced Features\n\n#### CC and BCC Recipients\nYou can include carbon copy (CC) and blind carbon copy (BCC) recipients to your emails. These should be formatted as JSON arrays of email addresses.\n\n#### File Attachments\nThe tool supports attaching files to your emails. You can include multiple file attachments that will be sent along with your email message.\n\n#### Markdown to HTML Conversion\nEnable the \"Convert to HTML\" option to automatically convert your markdown-formatted email content to properly formatted HTML, making your emails more visually appealing. The conversion supports:\n\n- Rich text formatting (bold, italic, headers)\n- Links and inline code blocks\n- Tables with proper formatting\n- Inline images that can be embedded directly in the email body\n\n![](./_assets/email_3.PNG)\n",
        "label": {
          "en_US": "email",
          "zh_Hans": "电子邮件"
        },
        "latest_package_identifier": "langgenius/email:0.0.6@b81c6c1277c5da6b0a645e177967baed02e68b8ae85169fd25c90c4f2af8f9fb",
        "latest_version": "0.0.6",
        "model": {},
        "name": "email",
        "org": "langgenius",
        "plugin_id": "langgenius/email",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/email.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "utilities"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "email account",
                "zh_Hans": "邮件账号"
              },
              "label": {
                "en_US": "email account",
                "zh_Hans": "邮件账号"
              },
              "name": "email_account",
              "options": null,
              "placeholder": {
                "en_US": "input you email account",
                "zh_Hans": "输入你的邮箱账号"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "help": {
                "en_US": "email password",
                "zh_Hans": "邮件密码"
              },
              "label": {
                "en_US": "email password",
                "zh_Hans": "邮件密码"
              },
              "name": "email_password",
              "options": null,
              "placeholder": {
                "en_US": "email password",
                "zh_Hans": "邮件密码"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "help": {
                "en_US": "smtp server encrypt method",
                "zh_Hans": "发信smtp服务器加密方式"
              },
              "label": {
                "en_US": "encrypt method",
                "zh_Hans": "加密方式"
              },
              "name": "encrypt_method",
              "options": [
                {
                  "label": {
                    "en_US": "NONE",
                    "zh_Hans": "无加密"
                  },
                  "value": "NONE"
                },
                {
                  "label": {
                    "en_US": "SSL",
                    "zh_Hans": "SSL加密"
                  },
                  "value": "SSL"
                },
                {
                  "label": {
                    "en_US": "START TLS",
                    "zh_Hans": "START TLS加密"
                  },
                  "value": "TLS"
                }
              ],
              "placeholder": null,
              "required": true,
              "scope": null,
              "type": "select",
              "url": null
            },
            {
              "default": null,
              "help": {
                "en_US": "smtp server port",
                "zh_Hans": "发信smtp服务器端口"
              },
              "label": {
                "en_US": "smtp server port",
                "zh_Hans": "发信smtp服务器端口"
              },
              "name": "smtp_port",
              "options": null,
              "placeholder": {
                "en_US": "smtp server port",
                "zh_Hans": "发信smtp服务器端口"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "help": {
                "en_US": "smtp server",
                "zh_Hans": "发信smtp服务器地址"
              },
              "label": {
                "en_US": "smtp server",
                "zh_Hans": "发信smtp服务器地址"
              },
              "name": "smtp_server",
              "options": null,
              "placeholder": {
                "en_US": "smtp server",
                "zh_Hans": "发信smtp服务器地址"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            }
          ],
          "identity": {
            "author": "wakaka6",
            "description": {
              "en_US": "send email through smtp protocol",
              "zh_Hans": "通过smtp协议发送电子邮件"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "email",
              "zh_Hans": "电子邮件"
            },
            "name": "email",
            "tags": [
              "utilities"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool for sending email to multiple recipients",
                  "zh_Hans": "用于发送邮件给多个收件人的工具"
                },
                "llm": "A tool for sending email to multiple recipients"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "wakaka6",
                "label": {
                  "en_US": "send email to multiple recipients",
                  "zh_Hans": "发送邮件给多个收件人"
                },
                "name": "send_mail_batch"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Recipient email account",
                    "zh_Hans": "收件人邮箱账号"
                  },
                  "label": {
                    "en_US": "Recipient email account(json list)",
                    "zh_Hans": "收件人邮箱账号(json list)"
                  },
                  "llm_description": "A list of recipient email account(json format)",
                  "max": null,
                  "min": null,
                  "name": "send_to",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Carbon copy email account",
                    "zh_Hans": "抄送邮箱账号"
                  },
                  "label": {
                    "en_US": "Carbon copy email account(json list)",
                    "zh_Hans": "抄送邮箱账号(json list)"
                  },
                  "llm_description": "Carbon copy email account(json list)",
                  "max": null,
                  "min": null,
                  "name": "cc",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Blind carbon copy email account",
                    "zh_Hans": "密送邮箱账号"
                  },
                  "label": {
                    "en_US": "Blind carbon copy email account(json list)",
                    "zh_Hans": "密送邮箱账号(json list)"
                  },
                  "llm_description": "Blind carbon copy email account(json list)",
                  "max": null,
                  "min": null,
                  "name": "bcc",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "email subject",
                    "zh_Hans": "邮件主题"
                  },
                  "label": {
                    "en_US": "email subject",
                    "zh_Hans": "邮件主题"
                  },
                  "llm_description": "email subject",
                  "max": null,
                  "min": null,
                  "name": "subject",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "email content",
                    "zh_Hans": "邮件内容"
                  },
                  "label": {
                    "en_US": "email content",
                    "zh_Hans": "邮件内容"
                  },
                  "llm_description": "email content",
                  "max": null,
                  "min": null,
                  "name": "email_content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Convert content from markdown to HTML",
                    "zh_Hans": "将内容从Markdown转换为HTML"
                  },
                  "label": {
                    "en_US": "Convert to HTML",
                    "zh_Hans": "转换为HTML"
                  },
                  "llm_description": "Whether to convert the email content from markdown to HTML format",
                  "max": null,
                  "min": null,
                  "name": "convert_to_html",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Files to attach to the email",
                    "zh_Hans": "要附加到电子邮件的文件"
                  },
                  "label": {
                    "en_US": "File Attachments",
                    "zh_Hans": "文件附件"
                  },
                  "llm_description": "Files to attach to the email",
                  "max": null,
                  "min": null,
                  "name": "attachments",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "files"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for sending email",
                  "zh_Hans": "用于发送邮件"
                },
                "llm": "A tool for sending email"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "wakaka6",
                "label": {
                  "en_US": "send email",
                  "zh_Hans": "发送邮件"
                },
                "name": "send_mail"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Recipient email account",
                    "zh_Hans": "收件人邮箱账号"
                  },
                  "label": {
                    "en_US": "Recipient email account",
                    "zh_Hans": "收件人邮箱账号"
                  },
                  "llm_description": "Recipient email account",
                  "max": null,
                  "min": null,
                  "name": "send_to",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Carbon copy email account",
                    "zh_Hans": "抄送邮箱账号"
                  },
                  "label": {
                    "en_US": "Carbon copy email account(json list)",
                    "zh_Hans": "抄送邮箱账号(json list)"
                  },
                  "llm_description": "Carbon copy email account(json list)",
                  "max": null,
                  "min": null,
                  "name": "cc",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Blind carbon copy email account",
                    "zh_Hans": "密送邮箱账号"
                  },
                  "label": {
                    "en_US": "Blind carbon copy email account(json list)",
                    "zh_Hans": "密送邮箱账号(json list)"
                  },
                  "llm_description": "Blind carbon copy email account(json list)",
                  "max": null,
                  "min": null,
                  "name": "bcc",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "email subject",
                    "zh_Hans": "邮件主题"
                  },
                  "label": {
                    "en_US": "email subject",
                    "zh_Hans": "邮件主题"
                  },
                  "llm_description": "email subject",
                  "max": null,
                  "min": null,
                  "name": "subject",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "email content",
                    "zh_Hans": "邮件内容"
                  },
                  "label": {
                    "en_US": "email content",
                    "zh_Hans": "邮件内容"
                  },
                  "llm_description": "email content",
                  "max": null,
                  "min": null,
                  "name": "email_content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Convert content from markdown to HTML",
                    "zh_Hans": "将内容从Markdown转换为HTML"
                  },
                  "label": {
                    "en_US": "Convert to HTML",
                    "zh_Hans": "转换为HTML"
                  },
                  "llm_description": "Whether to convert the email content from markdown to HTML format",
                  "max": null,
                  "min": null,
                  "name": "convert_to_html",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Files to attach to the email",
                    "zh_Hans": "要附加到电子邮件的文件"
                  },
                  "label": {
                    "en_US": "File Attachments",
                    "zh_Hans": "文件附件"
                  },
                  "llm_description": "Files to attach to the email",
                  "max": null,
                  "min": null,
                  "name": "attachments",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "files"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-09T13:36:04Z",
        "version_updated_at": "2025-04-09T13:36:04Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Mistral OCR is ideal for RAG systems with multimodal documents like slides or complex PDFs.",
          "zh_Hans": "Mistral OCR 非常适合处理包含多模态文档（如幻灯片或复杂 PDF）的 RAG 系统。"
        },
        "category": "tool",
        "created_at": "2025-03-24T07:54:36Z",
        "endpoint": {},
        "icon": "inlei/packages/mistral_ocr/_assets/icon.svg",
        "index_id": "inlei___mistral_ocr",
        "install_count": 2928,
        "introduction": "# Mistral OCR Plugin\n\nThis plugin integrates Mistral OCR capabilities into Dify, allowing you to extract text and structured content from PDF documents and images with high accuracy and formatting preservation.\n\n## Features\n\n- Extract text while preserving structure and formatting (headers, paragraphs, lists, tables)\n- Return results in markdown format\n- Handle complex layouts (multi-column text, mixed content)\n- Process various formats (PDF, images) with high accuracy\n\n## Setup\n\n1. Get your Mistral API key from [Mistral AI Console](https://console.mistral.ai/api-keys/)\n2. Configure the plugin with your API key in the credentials section\n3. Use it in your Dify Agent, Chatflow, and Workflow.\n\n## Usage\n\nThe Mistral OCR tool can process documents in two ways:\n\n1. **File Upload**: Upload PDF documents or images directly through the Dify interface\n2. **URL Processing**: Process documents from publicly accessible URLs\n\n### Parameters\n\n- `file`: Upload a file for OCR processing. Supports PDF documents and common image formats\n- `pages`: Specific pages to process (e.g., \"0,2,4-7\"). For PDF documents only (default: \"0\")\n- `image_limit`: Maximum number of images to extract from the document (optional)\n- `image_min_size`: Minimum size threshold for extracting images in pixels (default: 100)\n\n## Examples\n\n### Processing a PDF document\n\nUpload a PDF or enter the PDF URL through the Dify interface and configure the following parameters:\n\n![](./_assets/mistral_ocr_1.png)\n\n![](./_assets/mistral_ocr_2.png)\n\n### Processing an image\n\nSimply upload an image or provide a URL through the Dify interface without needing to configure any additional parameters.\n\n![](./_assets/mistral_ocr_3.png)\n\n## Response\n\nThe tool returns OCR results in JSON format that includes:\n\n- **Pages**: Array of page objects with extracted text in markdown format\n- **Images**: Any images extracted from the document (if applicable)\n- **Document structure**: Information about the document structure and layout\n- **Formatting**: Preserved formatting elements like headings, paragraphs, and tables\n\n## Privacy\n\nThis plugin processes your documents according to our [Privacy Policy](./PRIVACY.md). Your files are processed temporarily and are not stored permanently by the plugin.\n\n## Contact\n\nFor questions, feedback, or support regarding the Mistral OCR plugin, please contact the author:\n\n**Leillei**  \n📧 jeroen20211101@gmail.com\n",
        "label": {
          "en_US": "Mistral OCR",
          "zh_Hans": "Mistral OCR"
        },
        "latest_package_identifier": "inlei/mistral_ocr:0.0.1@c46107c6e7f6136d742642a146514a4b75920c0cb1f20af64203d7d87fdcf836",
        "latest_version": "0.0.1",
        "model": {},
        "name": "mistral_ocr",
        "org": "inlei",
        "plugin_id": "inlei/mistral_ocr",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/mistral_ocr.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "utilities"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Get your Mistral API key from Mistral AI",
                "zh_Hans": "从 Mistral AI 获取您的 Mistral API key"
              },
              "label": {
                "en_US": "Mistral API key",
                "zh_Hans": "Mistral API key"
              },
              "name": "mistral_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Mistral API key",
                "zh_Hans": "请输入您的 Mistral API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://console.mistral.ai/api-keys/"
            }
          ],
          "identity": {
            "author": "inlei",
            "description": {
              "en_US": "Mistral OCR",
              "zh_Hans": "Mistral OCR"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Mistral OCR",
              "zh_Hans": "Mistral OCR"
            },
            "name": "mistral_ocr",
            "tags": [
              "image",
              "productivity",
              "other"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Mistral OCR is a powerful document OCR processor that extracts text and structured content from PDF documents and images while maintaining document structure and hierarchy. It preserves formatting like headers, paragraphs, lists and tables, and returns results in markdown format for easy parsing and rendering.",
                  "zh_Hans": "Mistral OCR 是一个强大的文档 OCR 处理器，可以从 PDF 文档和图像中提取文本和结构化内容，同时保持文档结构和层次结构。它保留了标题、段落、列表和表格等格式，并以 markdown 格式返回结果，便于解析和渲染。"
                },
                "llm": "Mistral OCR processes documents and images to extract text while preserving structure and formatting. It handles complex layouts including multi-column text and mixed content, returning results in markdown format."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "inlei",
                "label": {
                  "en_US": "Mistral OCR",
                  "zh_Hans": "Mistral OCR"
                },
                "name": "mistral_ocr_tool"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Upload a single file for OCR processing. Only one document can be processed at a time. Supports PDF documents and common image formats.",
                    "zh_Hans": "上传单个文件进行 OCR 处理。每次只能处理一个文档。支持 PDF 文档和常见图像格式。"
                  },
                  "label": {
                    "en_US": "Upload File",
                    "zh_Hans": "上传文件"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "file_path",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "file"
                },
                {
                  "auto_generate": null,
                  "default": "0",
                  "form": "llm",
                  "human_description": {
                    "en_US": "Specific pages to process (e.g., \"0,2,4-7\"). For PDF documents only.",
                    "zh_Hans": "要处理的特定页面（例如：\"0,2,4-7\"）。仅适用于 PDF 文档。"
                  },
                  "label": {
                    "en_US": "Pages",
                    "zh_Hans": "页面"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "pages",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Maximum number of images to extract from the document.",
                    "zh_Hans": "从文档中提取的最大图像数量。"
                  },
                  "label": {
                    "en_US": "Image Limit",
                    "zh_Hans": "图像限制"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "image_limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 100,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Minimum size threshold for extracting images (default 100px). Smaller images are ignored.",
                    "zh_Hans": "提取图像的最小尺寸阈值（默认 100px），小于该尺寸的将被忽略。"
                  },
                  "label": {
                    "en_US": "Image Minimum Size",
                    "zh_Hans": "图像最小尺寸"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "image_min_size",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-24T07:54:48Z",
        "version_updated_at": "2025-03-24T07:54:48Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Trigger a dify app from webhook.",
          "pt_BR": "Acione um aplicativo dify a partir de um webhook.",
          "zh_Hans": "通过网络钩子触发dify应用程序。"
        },
        "category": "extension",
        "created_at": "2025-03-08T17:02:18Z",
        "endpoint": {
          "endpoints": [
            {
              "hidden": false,
              "method": "POST",
              "path": "/workflow/<app_id>"
            },
            {
              "hidden": false,
              "method": "POST",
              "path": "/chatflow/<app_id>"
            },
            {
              "hidden": false,
              "method": "POST",
              "path": "/single-chatflow"
            },
            {
              "hidden": false,
              "method": "POST",
              "path": "/single-workflow"
            }
          ],
          "settings": [
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "App (Disables the <app_id> routes)",
                "pt_BR": "Aplicativo (Desativa as rotas de <app_id>)",
                "zh_Hans": "应用程序 (禁用<app_id>路由)"
              },
              "name": "static_app_id",
              "options": null,
              "placeholder": {
                "en_US": "Select a specific app to expose, instead of exposing all workspace apps",
                "pt_BR": "Selecione um aplicativo específico para expor, em vez de expor todos os aplicativos do espaço de trabalho",
                "zh_Hans": "选择要公开的特定应用，而不是公开所有工作区应用"
              },
              "required": false,
              "scope": null,
              "type": "app-selector",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "API key",
                "pt_BR": "Chave de API",
                "zh_Hans": "API 密钥"
              },
              "name": "api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your API key",
                "pt_BR": "Por favor, insira sua chave de API",
                "zh_Hans": "请输入你的 API 密钥"
              },
              "required": false,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": "api_key_header",
              "help": null,
              "label": {
                "en_US": "API key location",
                "pt_BR": "Localização da chave de API",
                "zh_Hans": "API 密钥位置"
              },
              "name": "api_key_location",
              "options": [
                {
                  "label": {
                    "en_US": "X-API-Key Header",
                    "pt_BR": "Cabeçalho X-API-Key",
                    "zh_Hans": "X-API-Key 头"
                  },
                  "value": "api_key_header"
                },
                {
                  "label": {
                    "en_US": "URL Query Param 'difyToken'",
                    "pt_BR": "Parâmetro de consulta URL 'difyToken'",
                    "zh_Hans": "URL 查询参数 'difyToken'"
                  },
                  "value": "token_query_param"
                },
                {
                  "label": {
                    "en_US": "None",
                    "pt_BR": "Nenhum",
                    "zh_Hans": "无"
                  },
                  "value": "none"
                }
              ],
              "placeholder": {
                "en_US": "Please select the API key location",
                "pt_BR": "Por favor, selecione a localização da chave de API",
                "zh_Hans": "请选择 API 密钥位置"
              },
              "required": true,
              "scope": null,
              "type": "select",
              "url": null
            },
            {
              "default": "none",
              "help": null,
              "label": {
                "en_US": "Custom Middleware",
                "pt_BR": "Middleware Personalizado",
                "zh_Hans": "自定义中间件"
              },
              "name": "middleware",
              "options": [
                {
                  "label": {
                    "en_US": "Discord",
                    "pt_BR": "Discord",
                    "zh_Hans": "Discord"
                  },
                  "value": "discord"
                },
                {
                  "label": {
                    "en_US": "None",
                    "pt_BR": "Nenhum",
                    "zh_Hans": "无"
                  },
                  "value": "none"
                }
              ],
              "placeholder": {
                "en_US": "Custom middlewares can add logic like signature validation",
                "pt_BR": "Middlewares personalizados podem adicionar lógica como validação de assinatura",
                "zh_Hans": "自定义中间件可以添加诸如签名验证的逻辑"
              },
              "required": true,
              "scope": null,
              "type": "select",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Signature Verification Public Key",
                "pt_BR": "Chave Pública de Verificação de Assinatura",
                "zh_Hans": "签名验证公钥"
              },
              "name": "signature_verification_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your public key for signature verification",
                "pt_BR": "Por favor, insira sua chave pública para verificação de assinatura",
                "zh_Hans": "请输入您的签名验证公钥"
              },
              "required": false,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": true,
              "help": null,
              "label": {
                "en_US": "Use req.body.inputs instead of req.body as the inputs object",
                "pt_BR": "Usar req.body.inputs em vez de req.body como objeto de entradas",
                "zh_Hans": "使用 req.body.inputs 代替 req.body 作为输入对象"
              },
              "name": "explicit_inputs",
              "options": null,
              "placeholder": null,
              "required": false,
              "scope": null,
              "type": "boolean",
              "url": null
            },
            {
              "default": false,
              "help": null,
              "label": {
                "en_US": "Transform req.body to req.body.json_string as JSON string.",
                "pt_BR": "Transforme req.body em req.body.json_string como string JSON.",
                "zh_Hans": "将req.body转换为req.body.json_string作为JSON字符串。"
              },
              "name": "json_string_input",
              "options": null,
              "placeholder": null,
              "required": false,
              "scope": null,
              "type": "boolean",
              "url": null
            },
            {
              "default": false,
              "help": null,
              "label": {
                "en_US": "Send res.body.data instead of res.body as workflow response.",
                "pt_BR": "Envie res.body.data como resposta do fluxo de trabalho em vez de res.body.",
                "zh_Hans": "发送 res.body.data 作为工作流响应，而不是 res.body。"
              },
              "name": "raw_data_output",
              "options": null,
              "placeholder": null,
              "required": false,
              "scope": null,
              "type": "boolean",
              "url": null
            }
          ]
        },
        "icon": "perzeuss/packages/webhook/_assets/icon.svg",
        "index_id": "perzeuss___webhook",
        "install_count": 2851,
        "introduction": "## Dify Plugin: Webhook \n\n<div align=\"center\">\n  <img src=\"https://img.shields.io/badge/Plugin%20Type-Extensionl-blue\" alt=\"Plugin Type: Extension\">\n  <img src=\"https://img.shields.io/github/v/release/perzeuss/dify-plugin-webhook?label=Version&color=DD7200\" alt=\"Latest Release Version\">\n  <br>\n  <img src=\"https://img.shields.io/badge/Compatible%20With-Dify%201.0-purple\" alt=\"Compatible With: Dify 1.0.*\">\n  <a href=\"https://codecov.io/gh/perzeuss/dify-plugin-webhook\">\n    <img src=\"https://codecov.io/gh/perzeuss/dify-plugin-webhook/main/graph/badge.svg\" alt=\"Coverage Status\">\n  </a>\n  <img src=\"https://img.shields.io/github/license/perzeuss/dify-plugin-webhook?label=License&color=darkgreen\" alt=\"License\">\n</div>\n\n### 🔍 Description\n\nThis project is a Dify Plugin that enables seamless triggering of Dify applications using webhooks. With this plugin, you can effortlessly initiate both chatflows and workflows through HTTP requests from any third-party system. 🚀\n\n### ⭐ GitHub Repository\nStar and watch our GitHub repository at https://github.com/perzeuss/dify-plugin-webhook to be notified about new releases! The project is open source, feel free to fork and modify it!\n\n### ✨ Key Features & Benefits\n\n| Feature | Webhook Plugin | Standard Dify API | Benefit |\n|---------|----------------|-------------------|---------|\n| **Flexible API Key Location** | Supports header, URL param, or none | Only Authorization header | Compatible with more third-party systems |\n| **Custom Endpoints** | Create multiple endpoints with different configs | Limited to standard endpoints | Support different third-party integrations simultaneously |\n| **Request Body Handling** | Full body or inputs object only | Fixed schema required | Works with systems that can't match Dify's schema |\n| **Raw Data Output** | Optional removal of Dify metadata | Always includes metadata | Clean responses for third-party integrations |\n| **Middleware Support** | Extensible with custom middleware | Not available | Add custom validation, or transformations |\n| **Discord Integration** | Built-in Discord webhook support | Requires custom implementation | Effortless Discord bot creation |\n| **Authentication Options** | Three authentication methods | Fixed authorization | Flexible security model |\n\n## 🚀 Getting Started\n\n### 📦 Installation\nVisit the Dify Plugin marketplace, search for the \"Webhook\" plugin and click the install button. After installation, click on the \"Webhook\" plugin on the plugins page.\n\n1. **Create Endpoint**:  \n   In the Endpoints section, click the \"+\" icon to create a unique webhook domain. You can choose any name you want. Each endpoint can have its own configuration, such as individualized credentials and request handling.\n\n2. **Configure API Key**:  \n   After installing the plugin, ensure you have set up an API key in your settings, unless using the `none` option for the API key location. For other configurations, this key is necessary for authenticating requests.\n\n3. **Configure API Key Location**:  \n   The API key can be utilized in various ways for compatibility with 3rd party systems:\n   - `X-API-Key` header\n   - URL query parameter `difyToken`\n   - `none` (no API key required)\n\n4. **Middleware Support**:  \n   The plugin supports the use of custom middlewares for request validation, transformations, and more. Built-in support for Discord webhooks is included, and you can add more middleware for other integrations. Please open a GitHub issue before working on custom middlewares - at the moment there is no dedicated middleware api and you might need to modify the main plugin code to support additional middleware features.\n\n5. **Specify Input Handling**:  \n   You have the option to specify whether to use `req.body.inputs` or the entire `req.body` for input variables. This flexibility enhances integration with third-party systems that don't support defining the request payload structure required by Dify.\n\n6. **JSON String Input**:  \n   Enable this option to automatically convert the entire request body to a JSON string. This is particularly useful when you want to pass a complex payload through a single input variable in Dify and parse it within your application logic.\n\n7. **Specify Output Handling**:  \n   Configure the output data from **workflows**. The webhook can send res.body.data (Output of the End node) as the response body without Dify metadata. By default the response contains metada which could conflict with the requirements of your integration.\n\n8. **Available Endpoints**:  \n   You have access to the following endpoint URLs:\n   - Dynamic endpoints, exposes all apps in the workspace\n     - **Chatflow Endpoint**: `/chatflow/<app_id>`\n     - **Workflow Endpoint**: `/workflow/<app_id>`\n   - Single app endpoints, exposes only the selected app\n     - **Chatflow Endpoint**: `/single-chatflow`\n     - **Workflow Endpoint**: `/single-workflow`\n\n### 📘 Usage Guide\n\n#### 🔊 Chatflow Endpoint\n\nTrigger a chatflow by sending a POST request to the chatflow endpoint:\n\n- **URL Without App**: `/chatflow/<app_id>`\n- **URL With App**: `/single-chatflow`\n- **Method**: `POST`\n- **Headers**:\n  - `Content-Type: application/json`\n  - If using an API key: `X-API-Key: <your_api_key>`\n- **Body** (JSON):\n  ```json\n  {\n    \"query\": \"Hi\",\n    \"inputs\": { \"name\": \"John\" },\n    \"conversation_id\": \"\"\n  }\n  ```\n\nFor endpoints configured with a specific Dify app, use the `/single-chatflow` route. A successful response will include the chatflow output.\n\n#### 🔄 Workflow Endpoint\n\nTo initiate a workflow, send a POST request to the workflow endpoint:\n\n- **URL Without App**: `/workflow/<app_id>`\n- **URL With App**: `/single-workflow`\n- **Method**: `POST`\n- **Headers**:\n  - `Content-Type: application/json`\n  - If using an API key: `X-API-Key: <your_api_key>`\n- **Body** (JSON):\n  ```json\n  {\n    \"inputs\": { \"name\": \"John\" }\n  }\n  ```\n\nFor endpoints configured with a specific Dify app, use the `/single-workflow` route. The response will contain results from the workflow execution.\n\n### 🧩 Customization with Middlewares\n\nThe plugin supports middleware for extended functionality:\n\n1. **Discord Webhook Integration**:  \n   Built-in support for Discord interaction verification and response handling.\n\n2. **Default Middleware**:  \n   Provides JSON string conversion functionality.\n\n3. **Custom Middlewares**:  \n   You can develop additional middlewares to:\n   - Verify signatures from other platforms\n   - Transform request and response data\n   - Implement custom authentication methods\n   - Handle special payload formats\n\n### ⚙️ Advanced Configuration Examples\n\n#### Multiple Endpoints Configuration\n\nYou can create multiple endpoints with different configurations. For example:\n\n- **Discord Bot Endpoint**: With Discord middleware and public key for signature verification\n- **Zapier Integration**: With request payload in json_string variable and res.body.data as output\n- **Internal Systems**: With full response data including metadata for token usage tracking\n\n#### Custom Response Formatting\n\nFor workflows that need to integrate with systems expecting specific response formats:\n1. Enable the toggle for: `Send res.body.data instead of res.body as workflow response.`\n2. In your Dify workflow, ensure the End node provides exactly the format expected\n\n### 🔍 Troubleshooting\n\n- Use valid JSON for request bodies to avoid parsing errors.\n- Successful requests return a 200 status code. Unauthorized access returns a 403 status code unless API key location is set to `none`.\n- Proper error messages are given for input validation failures, returning a 400 status code.\n\nLeverage the power of Dify by automating your chatflow and workflow triggers efficiently using this webhook plugin! 🎉\n\n### 🙏 Acknowledgments\n\nSpecial thanks to the Dify team for delivering a fantastic developer experience and tools that facilitated the creation of this plugin. The first version of this plugin was developed during a beta program, and we appreciate the support and resources made available throughout the period. ❤️",
        "label": {
          "en_US": "Webhook",
          "pt_BR": "Webhook",
          "zh_Hans": "网络钩子"
        },
        "latest_package_identifier": "perzeuss/webhook:0.5.1@d8731aeaa601fe826507cd2d348e80d3d036a647b1b714ca4fa825a58a7efea5",
        "latest_version": "0.5.1",
        "model": {},
        "name": "webhook",
        "org": "perzeuss",
        "plugin_id": "perzeuss/webhook",
        "plugins": {
          "agent_strategies": null,
          "endpoints": [
            "group/webhook.yaml"
          ],
          "models": null,
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-03-28T07:01:27Z",
        "version_updated_at": "2025-03-28T07:01:27Z"
      },
      {
        "agent_strategy": {},
        "badges": [
          "partner"
        ],
        "brief": {
          "en_US": "AgentQL API integration for web data extraction.",
          "zh_Hans": "AgentQL API 集成，用于网页数据提取。"
        },
        "category": "tool",
        "created_at": "2025-03-07T12:57:01Z",
        "endpoint": {},
        "icon": "jayfish0/packages/agentql/_assets/icon.svg",
        "index_id": "jayfish0___agentql",
        "install_count": 2711,
        "introduction": "# AgentQL\n\n## Overview\n\n**[AgentQL](https://agentql.com)** provides structured data extraction from any web page using an [AgentQL query](https://docs.agentql.com/concepts/query-language) or a Natural Language prompt. AgentQL works across multiple languages and web pages without breaking over time.\n\n## Configuration\n\n1. **Install AgentQL Tool**\n\n   - Access the Plugin Marketplace\n   - Locate and install the AgentQL tool\n\n2. **Create an AgentQL API Key**\n\n   - Visit [AgentQL Dev Portal](https://dev.agentql.com/)\n   - Generate your API key\n\n3. **Authorize AgentQL**\n   - Go to **Plugins > AgentQL > To Authorize** in Dify\n   - Input your API key\n\n![](./_assets/authorization.png)\n\n## Workflow Usage\n\nIntegrate AgentQL into your pipeline by following these steps:\n\n1. Add AgentQL's **Extract Web Data** tool to your pipeline\n2. Configure input variables in the tool's UI\n3. Run the pipeline to extract web page data\n\n![](./_assets/workflow.png)\n\n### Query Methods\n\nUsing AgentQL query language:\n![](./_assets/workflow_ql.png)\n\nUsing Natural Language:\n![](./_assets/workflow_nl.png)\n\n> **Note:** You must provide either `query` or `prompt`. If both are provided, `query` takes precedence:\n>\n> - Use `query` if you want to extract data in a structure _you_ define.\n> - Use `prompt` if you want to extract data in a structure _AgentQL_ infers from your Natural Language description.\n\n## Agent Usage\n\n1. Add AgentQL's **Extract Web Data** tool to your Agent app\n2. Prompt the Agent to extract data from a web page with either an AgentQL query or a Natural Language prompt:\n   - Using AgentQL query: \"Extract the data from https://www.agentql.com/blog using the following agentql query: { posts[] { title author }}\"\n   - Using Natural Language: \"Extract the blog posts title and author from https://www.agentql.com/blog\"\n\n![](./_assets/agent_apps.png)\n\n**Example:**\n![](./_assets/agent_apps_nl.png)\n",
        "label": {
          "en_US": "AgentQL",
          "zh_Hans": "AgentQL"
        },
        "latest_package_identifier": "jayfish0/agentql:1.0.0@0d612ddf87b1159b73766957b0c9ce06ccf4fded7c45d0a67ea284499baffbcb",
        "latest_version": "1.0.0",
        "model": {},
        "name": "agentql",
        "org": "jayfish0",
        "plugin_id": "jayfish0/agentql",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/agentql.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 1048576
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Get your AgentQL API key from the AgentQL Dev Portal",
                "zh_Hans": "从 DevPortal 获取您的 AgentQL API key"
              },
              "label": {
                "en_US": "AgentQL API key",
                "zh_Hans": "AgentQL API key"
              },
              "name": "api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please enter your AgentQL API key",
                "zh_Hans": "请输入你的 AgentQL API 密钥"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://dev.agentql.com/"
            }
          ],
          "identity": {
            "author": "TinyFish",
            "description": {
              "en_US": "AgentQL",
              "zh_Hans": "AgentQL"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "AgentQL",
              "zh_Hans": "AgentQL"
            },
            "name": "agentql",
            "tags": [
              "productivity",
              "utilities"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Extracts structured data from a web page using an AgentQL query or a Natural Language description.",
                  "zh_Hans": "从给定的 URL 中提取结构化数据。"
                },
                "llm": "Extracts structured data as JSON from a web page given a URL using either an AgentQL query or a Natural Language description of the data."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "TinyFish",
                "label": {
                  "en_US": "Extract Web Data",
                  "zh_Hans": "网页数据提取"
                },
                "name": "extract_web_data"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The URL of the public web page you want to extract data from.",
                    "zh_Hans": "要从中提取数据的网页的公共 URL。"
                  },
                  "label": {
                    "en_US": "URL",
                    "zh_Hans": "URL"
                  },
                  "llm_description": "Accepts the URL of the public webpage to extract data from.",
                  "max": null,
                  "min": null,
                  "name": "url",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The AgentQL query to execute. Learn more at https://docs.agentql.com/agentql-query or use a prompt.",
                    "zh_Hans": "要执行的 AgentQL 查询。更多信息请参阅 https://docs.agentql.com/agentql-query。如果您想要精确提取结构化数据, 使用 AgentQL 查询。请指定 query 或 prompt 字段。"
                  },
                  "label": {
                    "en_US": "AgentQL Query",
                    "zh_Hans": "AgentQL 查询语言"
                  },
                  "llm_description": "Accepts AgentQL query used to extract the data. The query must be enclosed with curly braces `{}`. Either this field or `prompt` field must be provided.",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "A Natural Language description of the data to extract from the page. Alternative to AgentQL query.",
                    "zh_Hans": "对要提取的数据的自然语言描述。如果您想要提取非结构化数据, 使用 prompt。请指定 prompt 或 query 字段。"
                  },
                  "label": {
                    "en_US": "Prompt",
                    "zh_Hans": "提示"
                  },
                  "llm_description": "Accepts Natural Language description of the data to extract from the page. If AgentQL query is not specified, always use the `prompt` field. Either this field or `query` field must be provided.",
                  "max": null,
                  "min": null,
                  "name": "prompt",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Enable experimental anti-bot evasion strategies. May not work for all websites at all times.",
                    "zh_Hans": "启用隐身模式以绕过一些网站的反机器人检测。此功能是实验性的，可能不适用于所有网站。数据提取可能比非隐身模式花费更多时间。"
                  },
                  "label": {
                    "en_US": "Enable Stealth Mode (Beta)",
                    "zh_Hans": "隐身模式"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "stealth_mode",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": 900,
                  "form": "form",
                  "human_description": {
                    "en_US": "Seconds to wait for a request.",
                    "zh_Hans": "请求的超时时间（秒）。如果数据提取时间过长，请增加此值。"
                  },
                  "label": {
                    "en_US": "Timeout",
                    "zh_Hans": "超时"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": 0,
                  "name": "timeout",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "fast",
                  "form": "form",
                  "human_description": {
                    "en_US": "'standard' uses deep data analysis, while 'fast' trades some depth of analysis for speed.",
                    "zh_Hans": "'standard' 使用深度数据分析，而 'fast' 则牺牲了一些深度分析以换取速度。"
                  },
                  "label": {
                    "en_US": "Request Mode",
                    "zh_Hans": "请求模式"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "mode",
                  "options": [
                    {
                      "label": {
                        "en_US": "Fast",
                        "zh_Hans": "快速"
                      },
                      "value": "fast"
                    },
                    {
                      "label": {
                        "en_US": "Standard",
                        "zh_Hans": "标准"
                      },
                      "value": "standard"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 0,
                  "form": "form",
                  "human_description": {
                    "en_US": "Seconds to wait for the page to load before extracting data.",
                    "zh_Hans": "在数据提取之前等待页面加载的时间（秒）。"
                  },
                  "label": {
                    "en_US": "Wait For",
                    "zh_Hans": "等待"
                  },
                  "llm_description": "",
                  "max": 10,
                  "min": 0,
                  "name": "wait_for",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Scroll to bottom of the page before extracting data.",
                    "zh_Hans": "在数据提取之前滚动到页面底部。"
                  },
                  "label": {
                    "en_US": "Enable scroll to bottom",
                    "zh_Hans": "是否滚动到底部"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "scroll_to_bottom",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Take a screenshot before extracting data. Returned in 'metadata' as a Base64 string.",
                    "zh_Hans": "启用截图捕获。"
                  },
                  "label": {
                    "en_US": "Enable screenshot",
                    "zh_Hans": "是否启用截图"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "enable_screenshot",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-17T15:20:58Z",
        "version_updated_at": "2025-03-07T12:57:23Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Tools for processing PDF content",
          "zh_Hans": "利用 PyPDF2 处理 PDF 内容的工具"
        },
        "category": "tool",
        "created_at": "2025-03-21T07:47:45Z",
        "endpoint": {},
        "icon": "kalochin/packages/pdf_process/_assets/icon.svg",
        "index_id": "kalochin___pdf_process",
        "install_count": 2666,
        "introduction": "# PDF Process Plugin for Dify\n\nA comprehensive suite of PDF processing tools for Dify, enabling various PDF operations like page extraction, counting, and splitting.\n\n## Overview\n\nPDF Process is a collection of powerful tools designed to perform various PDF operations within the Dify environment. Each tool is specialized for specific PDF manipulation tasks, making it easy to integrate PDF processing capabilities into your workflows.\n\n## Features\n\n- Single page extraction\n- Multiple pages extraction with fixed page support\n- PDF page counting with customizable output formats\n- PDF splitting into individual pages\n- PDF to PNG conversion with adjustable quality\n\n## Important Note\nAll page numbers in this plugin are 1-indexed, meaning the first page of any PDF is page 1, the second is page 2, and so on.\n\n## Available Tools\n\n### 1. PDF Single Page Extractor\nExtracts a specific page from a PDF file and saves it as a new PDF.\n\nParameters:\n- **PDF Content**: The input PDF file (required)\n- **Page Number**: The specific page to extract (1-indexed, where page 1 is the first page, required)\n\n![PDF Single Page Extractor Interface](./_assets/pdf_single_page_extractor.png)\n\n### 2. PDF Multi Pages Extractor\nExtracts specified pages from a PDF file. Supports flexible page specifications like ranges (\"1-3\"), individual pages (\"1,2,3\"), or combinations (\"1-3,5\"). Optionally includes a set of fixed pages before the dynamic pages. The order of pages and any duplicates specified in the input strings are preserved in the output PDF.\n\nParameters:\n- **PDF Content**: The input PDF file (required).\n- **Fixed Pages**: Optional string specifying fixed pages to include at the beginning (1-indexed). Examples: `\"1-3\"`, `\"5\"`, `\"1,3,5-7\"`, `\"1,3,1-2\"`. Order and duplicates are preserved. Leave empty if none (default: `\"\"`).\n- **Dynamic Pages**: Required string specifying the dynamic pages to extract (1-indexed). Examples: `\"1-3\"`, `\"5\"`, `\"1,3,5-7\"`, `\"1,3,1-2\"`. Order and duplicates are preserved (default: `\"1\"`).\n\n![PDF Multi Pages Extractor Interface](./_assets/pdf_multi_pages_extractor.png)\n\n### 3. PDF Page Counter\nCounts the total number of pages in a PDF file with customizable output format.\n\nParameters:\n- **PDF Content**: The input PDF file (required)\n- **Output Format**: Choose between 'number' or 'json' format (optional, defaults to 'number')\n\n![PDF Page Counter Interface](./_assets/pdf_page_counter.png)\n\n### 4. PDF Splitter\nSplits a PDF file into multiple individual PDF files, creating a separate file for each page.\n\nParameters:\n- **PDF Content**: The input PDF file (required)\n\n![PDF Splitter Interface](./_assets/pdf_splitter.png)\n\n### 5. PDF to PNG Converter\nConverts each page of a PDF file into high-quality PNG images with configurable zoom settings.\n\nParameters:\n- **PDF Content**: The input PDF file (required)\n- **Zoom Factor**: Quality control zoom factor (optional, defaults to 2)\n\n![PDF to PNG Converter Interface](./_assets/pdf_to_png.png)\n\n## Author\nCreated by [Kalo Chin](https://github.com/fdb02983rhy)\n\n## Repository\nhttps://github.com/fdb02983rhy/dify-pdf-process-plugin",
        "label": {
          "en_US": "PDF Process",
          "zh_Hans": "PDF 处理"
        },
        "latest_package_identifier": "kalochin/pdf_process:0.0.4@29c7b0927a11333044049de20657119779a06e0eb003b6c5cffaec07e5204332",
        "latest_version": "0.0.4",
        "model": {},
        "name": "pdf_process",
        "org": "kalochin",
        "plugin_id": "kalochin/pdf_process",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/pdf_process.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "utilities"
          }
        ],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "kalochin",
            "description": {
              "en_US": "Tools for processing PDF content",
              "pt_BR": "Tools for processing PDF content",
              "zh_Hans": "利用 PyPDF2 处理 PDF 内容的工具"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "PDF Process",
              "pt_BR": "PDF Process",
              "zh_Hans": "PDF 处理"
            },
            "name": "pdf_process",
            "tags": [
              "utilities"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool for extracting PDF content",
                  "zh_Hans": "一个提取 PDF 内容的工具"
                },
                "llm": "A tool for extracting text from a specific page of a PDF document"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "kalochin",
                "label": {
                  "en_US": "PDF Single Page Extractor",
                  "zh_Hans": "PDF 单页提取器"
                },
                "name": "pdf_single_page_extractor"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "PDF file content",
                    "zh_Hans": "PDF 文件内容"
                  },
                  "label": {
                    "en_US": "PDF Content",
                    "zh_Hans": "PDF 内容"
                  },
                  "llm_description": "PDF file content in base64 encoded format",
                  "max": null,
                  "min": null,
                  "name": "pdf_content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "file"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Page number to extract (starting from 1)",
                    "zh_Hans": "要提取的页码（从1开始）"
                  },
                  "label": {
                    "en_US": "Page Number",
                    "zh_Hans": "页码"
                  },
                  "llm_description": "Specific page number to extract from the PDF. If not provided, all pages will be extracted.",
                  "max": null,
                  "min": null,
                  "name": "page_number",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for extracting multiple pages from a PDF with optional fixed pages using flexible page specifications",
                  "zh_Hans": "一个提取 PDF 多页的工具，可选择固定页，支持灵活的页码指定方式"
                },
                "llm": "A tool for extracting specified pages from a PDF document. Supports ranges (\"1-3\"), individual pages (\"1,3,5\"), or combinations (\"1-3,5\"). Can optionally include a set of fixed pages before the dynamic pages."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "kalochin",
                "label": {
                  "en_US": "PDF Multi Pages Extractor",
                  "zh_Hans": "PDF 多页提取器"
                },
                "name": "pdf_multi_pages_extractor"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "PDF file content",
                    "zh_Hans": "PDF 文件内容"
                  },
                  "label": {
                    "en_US": "PDF Content",
                    "zh_Hans": "PDF 内容"
                  },
                  "llm_description": "PDF file content in base64 encoded format or as a File object",
                  "max": null,
                  "min": null,
                  "name": "pdf_content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "file"
                },
                {
                  "auto_generate": null,
                  "default": "",
                  "form": "llm",
                  "human_description": {
                    "en_US": "Fixed Pages to include (e.g., \"1-3\", \"1,2,3\", \"1,3-5\"). Leave empty if not using fixed pages.",
                    "zh_Hans": "要包含的固定页码（例如：\"1-3\", \"1,2,3\", \"1,3-5\"）。如果不使用固定页可留空。"
                  },
                  "label": {
                    "en_US": "Fixed Pages",
                    "zh_Hans": "固定页码"
                  },
                  "llm_description": "A string specifying the fixed page numbers or ranges (1-indexed). Examples: \"1-3\", \"5\", \"1,3,5-7\". Optional.",
                  "max": null,
                  "min": null,
                  "name": "fixed_pages",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "1",
                  "form": "llm",
                  "human_description": {
                    "en_US": "Dynamic Pages to extract (e.g., \"1-3\", \"1,2,3\", \"1,3-5\").",
                    "zh_Hans": "要提取的动态页码（例如：\"1-3\", \"1,2,3\", \"1,3-5\"）。"
                  },
                  "label": {
                    "en_US": "Dynamic Pages",
                    "zh_Hans": "动态页码"
                  },
                  "llm_description": "A string specifying the dynamic page numbers or ranges to extract (1-indexed). Examples: \"1-3\", \"5\", \"1,3,5-7\". Required.",
                  "max": null,
                  "min": null,
                  "name": "dynamic_pages",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for counting pages in a PDF with customizable output format",
                  "zh_Hans": "一个计算 PDF 页数并可自定义输出格式的工具"
                },
                "llm": "A tool for counting the total number of pages in a PDF document with option to output as number or JSON format"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "kalochin",
                "label": {
                  "en_US": "PDF Page Counter",
                  "zh_Hans": "PDF 页数计算器"
                },
                "name": "pdf_page_counter"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "PDF file content (base64 encoded)",
                    "zh_Hans": "PDF 文件内容（base64 编码）"
                  },
                  "label": {
                    "en_US": "PDF Content",
                    "zh_Hans": "PDF 内容"
                  },
                  "llm_description": "PDF file content in base64 encoded format",
                  "max": null,
                  "min": null,
                  "name": "pdf_content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "file"
                },
                {
                  "auto_generate": null,
                  "default": "number",
                  "form": "llm",
                  "human_description": {
                    "en_US": "Format of the output (number or json)",
                    "zh_Hans": "输出格式（数字或JSON）"
                  },
                  "label": {
                    "en_US": "Output Format",
                    "zh_Hans": "输出格式"
                  },
                  "llm_description": "Choose between simple number output or JSON format with page numbers",
                  "max": null,
                  "min": null,
                  "name": "output_format",
                  "options": [
                    {
                      "label": {
                        "en_US": "Number",
                        "zh_Hans": "数字"
                      },
                      "value": "number"
                    },
                    {
                      "label": {
                        "en_US": "JSON",
                        "zh_Hans": "JSON"
                      },
                      "value": "json"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for splitting PDF files into individual pages",
                  "zh_Hans": "一个将PDF文件分割成单独页面的工具"
                },
                "llm": "A tool for splitting a PDF document into individual pages, returning each page as a separate PDF file"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "kalochin",
                "label": {
                  "en_US": "PDF Splitter",
                  "zh_Hans": "PDF 分割器"
                },
                "name": "pdf_splitter"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "PDF file content to split into individual pages",
                    "zh_Hans": "要分割成单独页面的PDF文件内容"
                  },
                  "label": {
                    "en_US": "PDF Content",
                    "zh_Hans": "PDF 内容"
                  },
                  "llm_description": "PDF file content in base64 encoded format or as a file object",
                  "max": null,
                  "min": null,
                  "name": "pdf_content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "file"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for converting PDF files to PNG images",
                  "zh_Hans": "一个将PDF文件转换为PNG图片的工具"
                },
                "llm": "A tool that converts each page of a PDF document into a separate PNG image with configurable quality"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "kalochin",
                "label": {
                  "en_US": "PDF to PNG Converter",
                  "zh_Hans": "PDF转PNG转换器"
                },
                "name": "pdf_to_png"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "PDF file to convert to PNG images",
                    "zh_Hans": "要转换为PNG图片的PDF文件"
                  },
                  "label": {
                    "en_US": "PDF Content",
                    "zh_Hans": "PDF 内容"
                  },
                  "llm_description": "PDF file content to be converted to PNG images",
                  "max": null,
                  "min": null,
                  "name": "pdf_content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "file"
                },
                {
                  "auto_generate": null,
                  "default": 2,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Zoom factor for image quality (default is 2)",
                    "zh_Hans": "图像质量的缩放因子（默认为2）"
                  },
                  "label": {
                    "en_US": "Zoom Factor",
                    "zh_Hans": "缩放因子"
                  },
                  "llm_description": "Zoom factor to control the quality of output PNG images",
                  "max": null,
                  "min": null,
                  "name": "zoom",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-17T15:31:48Z",
        "version_updated_at": "2025-04-17T15:31:48Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "ChatGLM"
        },
        "category": "model",
        "created_at": "2024-12-06T10:50:20Z",
        "endpoint": {},
        "icon": "langgenius/packages/chatglm/_assets/icon_s_en.svg",
        "index_id": "langgenius___chatglm",
        "install_count": 2554,
        "introduction": "## Overview\n\n[ChatGLM](https://open.bigmodel.cn/) is an open language model based on GLM (General Language Model) framework that supports English and Chinese. It's designed for tasks like text generation, conversation, and information extraction, and can be fine-tuned for specific applications.\n\n## Configure\n\nAfter installing the plugin, configure the API URL and API base within the Model Provider settings. Obtain your API URL from [here](https://open.bigmodel.cn/). Once saved, you can begin using ChatGLM to build your AI agents and agentic workflows.\n![](./_assets/chatglm_config.PNG)",
        "label": {
          "en_US": "ChatGLM"
        },
        "latest_package_identifier": "langgenius/chatglm:0.0.2@06cb2a89646ca97b2425913fc2e457552f352aa6be6bf80edbfaf49c2d7605dd",
        "latest_version": "0.0.2",
        "model": {
          "background": "#F4F7FF",
          "configurate_methods": [
            "predefined-model"
          ],
          "description": {
            "en_US": "ChatGLM"
          },
          "help": {
            "title": {
              "en_US": "Deploy ChatGLM to your local",
              "zh_Hans": "部署您的本地 ChatGLM"
            },
            "url": {
              "en_US": "https://github.com/THUDM/ChatGLM3"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.svg"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "ChatGLM"
          },
          "model_credential_schema": null,
          "models": [
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "ChatGLM2-6B-32K"
              },
              "model": "chatglm2-6b-32k",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 2000,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 32000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "ChatGLM2-6B"
              },
              "model": "chatglm2-6b",
              "model_properties": {
                "context_size": 2000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 256,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "tool-call",
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "ChatGLM3-6B-32K"
              },
              "model": "chatglm3-6b-32k",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 8000,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 32000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "tool-call",
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "ChatGLM3-6B"
              },
              "model": "chatglm3-6b",
              "model_properties": {
                "context_size": 8000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 256,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 8000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": null
            }
          ],
          "position": {
            "llm": [
              "chatglm2-6b-32k",
              "chatglm2-6b",
              "chatglm3-6b",
              "chatglm3-6b-32k"
            ]
          },
          "provider": "chatglm",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API URL"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API URL",
                  "zh_Hans": "在此输入您的 API URL"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "api_base"
              }
            ]
          },
          "supported_model_types": [
            "llm"
          ]
        },
        "name": "chatglm",
        "org": "langgenius",
        "plugin_id": "langgenius/chatglm",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/chatglm.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-02-17T06:54:13Z",
        "version_updated_at": "2025-02-17T06:54:13Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Database Query Utils (Pre-authorization).",
          "zh_Hans": "数据库查询工具（预授权）。"
        },
        "category": "tool",
        "created_at": "2025-03-24T07:37:43Z",
        "endpoint": {},
        "icon": "junjiem/packages/db_query_pre_auth/_assets/icon.svg",
        "index_id": "junjiem___db_query_pre_auth",
        "install_count": 2516,
        "introduction": "## Dify 1.0 Plugin Database Query Tools (Pre-authorization)\r\n\r\n\r\n**Author:** [Junjie.M](https://github.com/junjiem)   \r\n**Type:** tool  \r\n**Github Repo:** [https://github.com/junjiem/dify-plugin-tools-dbquery](https://github.com/junjiem/dify-plugin-tools-dbquery)  \r\n**Github Issues:** [issues](https://github.com/junjiem/dify-plugin-tools-dbquery/issues)\r\n\r\n\r\n---\r\n\r\n\r\n### Demonstration\r\n\r\nDatabase Query Tools (Pre-authorization)\r\n\r\n数据库查询工具（预授权）\r\n\r\nCurrently supported database types: mysql, oracle, postgresql, or mssql.\r\n\r\n目前支持的数据库类型：mysql、oracle、postgresql、mssql。\r\n\r\n![db_query_pre_auth](_assets/db_query_pre_auth.png)\r\n\r\n![db_query_pre_auth_setup_auth](_assets/db_query_pre_auth_setup_auth.png)\r\n",
        "label": {
          "en_US": "Database Query (Pre-authorization)",
          "zh_Hans": "数据库查询（预授权）"
        },
        "latest_package_identifier": "junjiem/db_query_pre_auth:0.0.5@28b16e781f12de0829b4d72a3a8b65aa6bfc6d897bc34ead1540797478c04c64",
        "latest_version": "0.0.5",
        "model": {},
        "name": "db_query_pre_auth",
        "org": "junjiem",
        "plugin_id": "junjiem/db_query_pre_auth",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/db_query.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "utilities"
          },
          {
            "name": "search"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": "mysql",
              "help": {
                "en_US": "Used for selecting the database type, mysql, oracle, postgresql or mssql.",
                "zh_Hans": "用于选择数据库类型，mysql、oracle、postgresql或mssql。"
              },
              "label": {
                "en_US": "Database type",
                "zh_Hans": "数据库类型"
              },
              "name": "db_type",
              "options": [
                {
                  "label": {
                    "en_US": "MySQL",
                    "zh_Hans": "MySQL"
                  },
                  "value": "mysql"
                },
                {
                  "label": {
                    "en_US": "Oracle",
                    "zh_Hans": "Oracle"
                  },
                  "value": "oracle"
                },
                {
                  "label": {
                    "en_US": "PostgreSQL",
                    "zh_Hans": "PostgreSQL"
                  },
                  "value": "postgresql"
                }
              ],
              "placeholder": null,
              "required": true,
              "scope": null,
              "type": "select",
              "url": null
            },
            {
              "default": "localhost",
              "help": null,
              "label": {
                "en_US": "Database Host",
                "zh_Hans": "数据库地址"
              },
              "name": "db_host",
              "options": null,
              "placeholder": null,
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Port",
                "zh_Hans": "端口"
              },
              "name": "db_port",
              "options": null,
              "placeholder": null,
              "required": false,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Username",
                "zh_Hans": "用户名"
              },
              "name": "db_username",
              "options": null,
              "placeholder": null,
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Password",
                "zh_Hans": "密码"
              },
              "name": "db_password",
              "options": null,
              "placeholder": null,
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Database name",
                "zh_Hans": "库名"
              },
              "name": "db_name",
              "options": null,
              "placeholder": null,
              "required": false,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "help": {
                "en_US": "Database properties, for example: alt_host=host1&alt_host=host2&ssl_cipher=%2Fpath%2Fto%2Fcrt",
                "zh_Hans": "数据库属性，例如：alt_host=host1&alt_host=host2&ssl_cipher=%2Fpath%2Fto%2Fcrt"
              },
              "label": {
                "en_US": "Database properties",
                "zh_Hans": "数据库属性"
              },
              "name": "db_properties",
              "options": null,
              "placeholder": null,
              "required": false,
              "scope": null,
              "type": "text-input",
              "url": null
            }
          ],
          "identity": {
            "author": "junjiem",
            "description": {
              "en_US": "Database Query Utils (Pre-authorization).",
              "zh_Hans": "数据库查询工具（预授权）。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Database Query (Pre-authorization)",
              "zh_Hans": "数据库查询（预授权）"
            },
            "name": "db_query_pre_auth",
            "tags": [
              "search",
              "utilities"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool for Database SQL query (Pre-authorization).",
                  "zh_Hans": "数据库SQL查询工具（预授权）。"
                },
                "llm": "A tool for executing SQL query. Input should be a search query."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "junjiem",
                "label": {
                  "en_US": "SQL Query (Pre-authorization)",
                  "zh_Hans": "SQL查询（预授权）"
                },
                "name": "sql_query_pre_auth"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "SQL query statement, for example: select * from tbl_name",
                    "zh_Hans": "SQL查询语句，例如：select * from tbl_name"
                  },
                  "label": {
                    "en_US": "Query SQL",
                    "zh_Hans": "SQL查询语句"
                  },
                  "llm_description": "SQL query statement, for example: select * from tbl_name",
                  "max": null,
                  "min": null,
                  "name": "query_sql",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-09T09:04:46Z",
        "version_updated_at": "2025-04-09T09:04:46Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Vertex AI in Google Cloud Platform."
        },
        "category": "model",
        "created_at": "2025-01-02T07:23:14Z",
        "endpoint": {},
        "icon": "langgenius/packages/vertex_ai/_assets/icon_s_en.svg",
        "index_id": "langgenius___vertex_ai",
        "install_count": 2512,
        "introduction": "",
        "label": {
          "en_US": "Vertex AI | Google Cloud Platform"
        },
        "latest_package_identifier": "langgenius/vertex_ai:0.0.9@bd63a7d365d61e335607cd84cffbd92ec66ceae0956a044407eea6c3147ba17e",
        "latest_version": "0.0.9",
        "model": {
          "background": "#FCFDFF",
          "configurate_methods": [
            "predefined-model"
          ],
          "description": {
            "en_US": "Vertex AI in Google Cloud Platform."
          },
          "help": {
            "title": {
              "en_US": "Get your Access Details from Google"
            },
            "url": {
              "en_US": "https://cloud.google.com/vertex-ai/"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.png"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "Vertex AI | Google Cloud Platform"
          },
          "model_credential_schema": null,
          "models": [
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Claude 3 Haiku"
              },
              "model": "claude-3-haiku@20240307",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 4096,
                  "help": {
                    "en_US": "The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.",
                    "zh_Hans": "停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "The amount of randomness injected into the response.",
                    "zh_Hans": "生成内容的随机性。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.999,
                  "help": {
                    "en_US": "In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.",
                    "zh_Hans": "在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.",
                    "zh_Hans": "对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。"
                  },
                  "label": {
                    "en_US": "top_k"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "top_k"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.00025",
                "output": "0.00125",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Claude 3 Opus"
              },
              "model": "claude-3-opus@20240229",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 4096,
                  "help": {
                    "en_US": "The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.",
                    "zh_Hans": "停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "The amount of randomness injected into the response.",
                    "zh_Hans": "生成内容的随机性。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.999,
                  "help": {
                    "en_US": "In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.",
                    "zh_Hans": "在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.",
                    "zh_Hans": "对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。"
                  },
                  "label": {
                    "en_US": "top_k"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "top_k"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.015",
                "output": "0.075",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Claude 3 Sonnet"
              },
              "model": "claude-3-sonnet@20240229",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 4096,
                  "help": {
                    "en_US": "The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.",
                    "zh_Hans": "停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "The amount of randomness injected into the response.",
                    "zh_Hans": "生成内容的随机性。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.999,
                  "help": {
                    "en_US": "In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.",
                    "zh_Hans": "在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.",
                    "zh_Hans": "对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。"
                  },
                  "label": {
                    "en_US": "top_k"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "top_k"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.003",
                "output": "0.015",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Claude 3.5 Sonnet v2"
              },
              "model": "claude-3-5-sonnet-v2@20241022",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 8192,
                  "help": {
                    "en_US": "The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.",
                    "zh_Hans": "停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "The amount of randomness injected into the response.",
                    "zh_Hans": "生成内容的随机性。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.999,
                  "help": {
                    "en_US": "In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.",
                    "zh_Hans": "在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.",
                    "zh_Hans": "对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。"
                  },
                  "label": {
                    "en_US": "top_k"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "top_k"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.003",
                "output": "0.015",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Claude 3.5 Sonnet"
              },
              "model": "claude-3-5-sonnet@20240620",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 4096,
                  "help": {
                    "en_US": "The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.",
                    "zh_Hans": "停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "The amount of randomness injected into the response.",
                    "zh_Hans": "生成内容的随机性。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.999,
                  "help": {
                    "en_US": "In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.",
                    "zh_Hans": "在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.",
                    "zh_Hans": "对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。"
                  },
                  "label": {
                    "en_US": "top_k"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "top_k"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.003",
                "output": "0.015",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 1.0 Pro Vision"
              },
              "model": "gemini-1.0-pro-vision-001",
              "model_properties": {
                "context_size": 16384,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token."
                  },
                  "label": {
                    "en_US": "Top k"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 1.0 Pro"
              },
              "model": "gemini-1.0-pro-002",
              "model_properties": {
                "context_size": 32760,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token."
                  },
                  "label": {
                    "en_US": "Top k"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 1.5 Flash 001"
              },
              "model": "gemini-1.5-flash-001",
              "model_properties": {
                "context_size": 1048576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token."
                  },
                  "label": {
                    "en_US": "Top k"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 1.5 Flash 002"
              },
              "model": "gemini-1.5-flash-002",
              "model_properties": {
                "context_size": 1048576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token."
                  },
                  "label": {
                    "en_US": "Top k"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 1.5 Pro 001"
              },
              "model": "gemini-1.5-pro-001",
              "model_properties": {
                "context_size": 1048576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token."
                  },
                  "label": {
                    "en_US": "Top k"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 1.5 Pro 002"
              },
              "model": "gemini-1.5-pro-002",
              "model_properties": {
                "context_size": 1048576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token."
                  },
                  "label": {
                    "en_US": "Top k"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document",
                "video",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 2.0 Flash 001"
              },
              "model": "gemini-2.0-flash-001",
              "model_properties": {
                "context_size": 1048576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document",
                "video",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 2.0 Flash Exp"
              },
              "model": "gemini-2.0-flash-exp",
              "model_properties": {
                "context_size": 1048576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document",
                "video",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 2.0 Flash Lite Preview 0205"
              },
              "model": "gemini-2.0-flash-lite-preview-02-05",
              "model_properties": {
                "context_size": 1048576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "document",
                "video",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 2.0 Flash Thinking Exp 01-21"
              },
              "model": "gemini-2.0-flash-thinking-exp-01-21",
              "model_properties": {
                "context_size": 32767,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document",
                "video",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 2.0 pro exp 02-05"
              },
              "model": "gemini-2.0-pro-exp-02-05",
              "model_properties": {
                "context_size": 1048576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision",
                "tool-call",
                "stream-tool-call",
                "document",
                "video",
                "audio"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini 2.5 pro exp 03-25"
              },
              "model": "gemini-2.5-pro-exp-03-25",
              "model_properties": {
                "context_size": 2097152,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 65535,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 65535,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response json schema will ensure LLM to adhere it.",
                    "zh_Hans": "设置返回的json schema，llm将按照它返回"
                  },
                  "label": {
                    "en_US": "json_schema"
                  },
                  "max": null,
                  "min": null,
                  "name": "json_schema",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "json_schema"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini Flash Experimental"
              },
              "model": "gemini-flash-experimental",
              "model_properties": {
                "context_size": 1048576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token."
                  },
                  "label": {
                    "en_US": "Top k"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemini Pro Experimental"
              },
              "model": "gemini-pro-experimental",
              "model_properties": {
                "context_size": 1048576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token."
                  },
                  "label": {
                    "en_US": "Top k"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 8192,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_output_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_output_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0",
                "output": "0",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "text-embedding-004"
              },
              "model": "text-embedding-004",
              "model_properties": {
                "context_size": 2048
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.00013",
                "output": null,
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "text-multilingual-embedding-002"
              },
              "model": "text-multilingual-embedding-002",
              "model_properties": {
                "context_size": 2048
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.00013",
                "output": null,
                "unit": "0.001"
              }
            }
          ],
          "position": {},
          "provider": "vertex_ai",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "Project ID"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Google Cloud Project ID"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "vertex_project_id"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Location"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Google Cloud Location"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "vertex_location"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Service Account Key (Leave blank if you use Application Default Credentials)"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Google Cloud Service Account Key in base64 format"
                },
                "required": false,
                "show_on": [],
                "type": "secret-input",
                "variable": "vertex_service_account_key"
              }
            ]
          },
          "supported_model_types": [
            "llm",
            "text-embedding"
          ]
        },
        "name": "vertex_ai",
        "org": "langgenius",
        "plugin_id": "langgenius/vertex_ai",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/vertex_ai.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-03T08:19:47Z",
        "version_updated_at": "2025-04-03T08:19:47Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "weather",
          "zh_Hans": "天气查询是一个用于获取实时天气数据和预报信息的服务接口。该API提供国内范围内的天气状况、预报和相关气象数据。"
        },
        "category": "tool",
        "created_at": "2025-03-13T18:07:32Z",
        "endpoint": {},
        "icon": "baobaobao/packages/weather/_assets/icon.svg",
        "index_id": "baobaobao___weather",
        "install_count": 2391,
        "introduction": "<!--\n * @Author: baobaobao\n * @Date: 2025-03-11 17:56:04\n * @LastEditTime: 2025-03-12 17:52:55\n * @LastEditors: baobaobao\n-->\n## weather\n\n**Author:** baobaobao\n**Version:** 0.0.3\n**Type:** tool\n\n### Description\n一款基于和风天气的天气查询工具\n\n### Usage\n\n```python\nfrom weather import WeatherTool\n\nweather_tool = WeatherTool()\nweather_tool.invoke({\"city\": \"beijing\"})\n```\n\n![](./_assets/ocr.png)\n\n\n\n\n\n",
        "label": {
          "en_US": "weather",
          "zh_Hans": "天气查询"
        },
        "latest_package_identifier": "baobaobao/weather:0.0.3@d200d18dc5e8f1d5c99bf60575fd939ffaebd8cca7f14edc745ffcc53a358d52",
        "latest_version": "0.0.3",
        "model": {},
        "name": "weather",
        "org": "baobaobao",
        "plugin_id": "baobaobao/weather",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/weather.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Get your QWeather API key from QWeather",
                "zh_Hans": "从 QWeather 获取您的 QWeather API key"
              },
              "label": {
                "en_US": "QWeather API key",
                "zh_Hans": "QWeather API key"
              },
              "name": "qweather_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your QWeather API key",
                "zh_Hans": "请输入你的 QWeather API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://dev.qweather.com/docs/start/"
            }
          ],
          "identity": {
            "author": "baobaobao",
            "description": {
              "en_US": "weather",
              "zh_Hans": "天气查询是一个用于获取实时天气数据和预报信息的服务接口。该API提供国内范围内的天气状况、预报和相关气象数据。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "weather",
              "zh_Hans": "天气查询"
            },
            "name": "weather",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "weather",
                  "zh_Hans": "天气查询是一个用于获取实时天气数据和预报信息的服务接口。该API提供国内范围内的天气状况、预报和相关气象数据。"
                },
                "llm": "weather"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "baobaobao",
                "label": {
                  "en_US": "weather",
                  "zh_Hans": "天气查询"
                },
                "name": "weather"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": "beijing",
                  "form": "form",
                  "human_description": {
                    "en_US": "used for searching city weather",
                    "zh_Hans": "输入要查询的城市拼音, 如beijing"
                  },
                  "label": {
                    "en_US": "Query string",
                    "zh_Hans": "城市拼音"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "city",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-13T18:07:41Z",
        "version_updated_at": "2025-03-13T18:07:41Z"
      },
      {
        "agent_strategy": {},
        "badges": [
          "partner"
        ],
        "brief": {
          "en_US": "The Agora Conversational AI extension enables developers to build voice assistants powered by Dify Agent.",
          "ja_JP": "Agora会話型AI拡張機能は、開発者がDify Agentを活用して高機能な音声アシスタントを構築できるようにします。",
          "pt_BR": "A extensão de IA Conversacional da Agora permite que desenvolvedores criem assistentes de voz poderosos com o suporte do Dify Agent.",
          "zh_Hans": "Agora 会话式 AI 插件让开发者能够借助 Dify Agent 构建功能强大的语音助手。"
        },
        "category": "extension",
        "created_at": "2025-02-19T04:26:03Z",
        "endpoint": {
          "endpoints": [
            {
              "hidden": false,
              "method": "POST",
              "path": "/convoai/<action>"
            },
            {
              "hidden": false,
              "method": "GET",
              "path": "/convoai-token/<channel>/<uid>"
            },
            {
              "hidden": false,
              "method": "GET",
              "path": "/convoai-web/<file>"
            }
          ],
          "settings": [
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "App",
                "pt_BR": "App",
                "zh_Hans": "App"
              },
              "name": "app",
              "options": null,
              "placeholder": null,
              "required": true,
              "scope": "chat",
              "type": "app-selector",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Agora App ID",
                "pt_BR": "Agora App ID",
                "zh_Hans": "Agora App ID"
              },
              "name": "agora_app_id",
              "options": null,
              "placeholder": {
                "en_US": "App ID for your Agora project",
                "pt_BR": "App ID for your Agora project",
                "zh_Hans": "你的 Agora 项目的 App ID"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Agora RESTful Customer ID",
                "pt_BR": "Agora RESTful Customer ID",
                "zh_Hans": "Agora RESTful 鉴权 ID"
              },
              "name": "agora_restful_customer_id",
              "options": null,
              "placeholder": {
                "en_US": "This value is used to authenticate your Agora RESTful API",
                "pt_BR": "This value is used to authenticate your Agora RESTful API",
                "zh_Hans": "这个值用于鉴权你的 Agora RESTful API"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Agora RESTful Customer Secret",
                "pt_BR": "Agora RESTful Customer Secret",
                "zh_Hans": "Agora RESTful 鉴权 Secret"
              },
              "name": "agora_restful_customer_secret",
              "options": null,
              "placeholder": {
                "en_US": "This value is used to authenticate your Agora RESTful API",
                "pt_BR": "This value is used to authenticate your Agora RESTful API",
                "zh_Hans": "这个值用于鉴权你的 Agora RESTful API"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "TTS Vendor",
                "pt_BR": "TTS tts_vendor",
                "zh_Hans": "TTS 供应商"
              },
              "name": "tts_vendor",
              "options": [
                {
                  "label": {
                    "en_US": "ElevenLabs",
                    "pt_BR": "ElevenLabs",
                    "zh_Hans": "ElevenLabs"
                  },
                  "value": "elevenlabs"
                },
                {
                  "label": {
                    "en_US": "Azure",
                    "pt_BR": "Azure",
                    "zh_Hans": "Azure"
                  },
                  "value": "microsoft"
                }
              ],
              "placeholder": null,
              "required": true,
              "scope": null,
              "type": "select",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "TTS Params",
                "pt_BR": "TTS Params",
                "zh_Hans": "TTS 参数"
              },
              "name": "tts_params",
              "options": null,
              "placeholder": {
                "en_US": "TTS Params in JSON format",
                "pt_BR": "TTS Params in JSON format",
                "zh_Hans": "TTS 参数以 JSON 格式填写"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Greeting Message",
                "pt_BR": "Greeting Message",
                "zh_Hans": "欢迎语"
              },
              "name": "greeting_message",
              "options": null,
              "placeholder": {
                "en_US": "This message will be sent to the user when they first start the conversation",
                "pt_BR": "This message will be sent to the user when they first start the conversation",
                "zh_Hans": "这个消息会在用户第一次开始对话时发送给用户"
              },
              "required": false,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Failure Message",
                "pt_BR": "Failure Message",
                "zh_Hans": "错误信息"
              },
              "name": "failure_message",
              "options": null,
              "placeholder": {
                "en_US": "This message will be sent to the user when the conversation has error",
                "pt_BR": "This message will be sent to the user when the conversation has error",
                "zh_Hans": "这个消息会在对话出现错误时发送给用户"
              },
              "required": false,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Agora App Certificate",
                "pt_BR": "Agora App Certificate",
                "zh_Hans": "Agora App Certificate"
              },
              "name": "agora_app_cert",
              "options": null,
              "placeholder": {
                "en_US": "This value is only needed when you have turned on security token for your Agora project",
                "pt_BR": "This value is only needed when you have turned on security token for your Agora project",
                "zh_Hans": "只有在你开启了 Agora 安全Token时才需要填写"
              },
              "required": false,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "API key",
                "pt_BR": "API key",
                "zh_Hans": "API key"
              },
              "name": "api_key",
              "options": null,
              "placeholder": {
                "en_US": "This is used to protect your API endpoint",
                "pt_BR": "This is used to protect your API endpoint",
                "zh_Hans": "这个值用于保护你的 API Endpoint"
              },
              "required": false,
              "scope": null,
              "type": "secret-input",
              "url": null
            }
          ]
        },
        "icon": "plutoless/packages/convoai/_assets/icon.svg",
        "index_id": "plutoless___convoai",
        "install_count": 2365,
        "introduction": "## Agora Conversational AI\r\n\r\n**Author:** plutoless\r\n**Version:** 0.0.6\r\n**Type:** extension\r\n\r\n### Description\r\n\r\n#### Overview\r\n\r\nThis extension provides an endpoint to make Dify agents work with Agora’s Conversational AI Engine to easily turn your Dify agents into voice assistants.\r\n\r\n#### Prerequisites\r\n\r\n- **Agora Account**\r\n    You need an Agora account to use the Agora Conversational AI service. You can sign up for a free account at [Agora](https://sso.agora.io/en/signup/).\r\n- **Agora App ID / App Certificate / RESTful Customer ID / RESTful Customer Secret**\r\n    You need to create an Agora project and get the App ID, App Certificate, RESTful Customer ID and RESTful Customer Secret from [Agora Console](https://console.agora.io/v2). Note to enable the Agora Conversational AI service in the Agora Console.\r\n- **TTS Vendor Account**\r\n    You need an account for the TTS vendor you choose. The TTS vendor provides the voice synthesis service for the voice assistant. \r\n\r\n#### Configuration\r\n\r\n- **APP**\r\n    To turn a Dify agent into a voice assistant, choose one from your agent library.\r\n- **Agora App ID**\r\n    In the [Agora Console](https://console.agora.io/v2), get your Agora App ID and enable the Conversational AI Engine service.\r\n- **Agora RESTful Customer ID**\r\n   In the [Agora Console](https://console.agora.io/v2), get the Agora RESTful Customer ID.\r\n- **Agora RESTful Customer Secret**\r\n   In the [Agora Console](https://console.agora.io/v2), get the Agora RESTful Customer Secret.\r\n- **TTS Vendor**\r\n    The TTS vendor to use for voice synthesis. Choose one from the list below.\r\n  - **Azure**\r\n  - **ElevenLabs**\r\n- **TTS Vendor Params**\r\n    The parameters for the TTS vendor. The parameters are different for each vendor, please refer to the vendor's documentation for more information.\r\n  - **Azure**\r\n\r\n    ```json\r\n    {\r\n        \"key\": \"<your api key>\",\r\n        \"region\": \"eastasia\",\r\n        \"voice_name\": \"en-US-AndrewMultilingualNeural\"\r\n    }\r\n    ```\r\n\r\n  - **ElevenLabs**\r\n\r\n    ```json\r\n    {\r\n        \"key\": \"<your api key>\",\r\n        \"model_id\": \"eleven_flash_v2_5\",\r\n        \"voice_id\": \"pNInz6obpgDQGcFmaJgB\"\r\n    }\r\n    ```\r\n\r\n- **Greeting Message**\r\n    The message to greet the user when the conversation starts.\r\n- **Failure Message**\r\n    The message to tell the user when the conversation fails.\r\n- **Agora App Certificate**\r\n    The Agora App Certificate to use for RTC service. Get it from [Agora Console](https://console.agora.io/v2). Only needed when security token is enabled for your Agora project.\r\n- **API Key**\r\n    The API Key to protect your Dify endpoint.\r\n\r\n#### Usage\r\n\r\nOnce you finish the configuration, you'll fnd the APl in the endpoint as follows:\r\n\r\n`https://qv90***.ai-plugin.io/convoai-web/<file>`\r\n\r\nReplace `<file>` with `index.html`,\r\n\r\nThen you may navigate to the following URL to access the integrated Conversational Al web page.\r\n\r\n`https://qv90***.ai-plugin.io/convoai-web/index.html`\r\n\r\n#### Using API without Web Page\r\n\r\nYou can also use the API directly without the web page. The API endpoint is:\r\n\r\n##### Start Conversation\r\n\r\nAPI Endpoint: `https://qv90***.ai-plugin.io/convoai-start`\r\n\r\n| key | value |\r\n| --- | --- |\r\n| base_url | The base url of the extension |\r\n| channel | The channel id of the extension |\r\n\r\nExample cURL:\r\n\r\n```bash\r\ncurl 'https://qv90***.ai-plugin.io/convoai/convoai-start' \\\r\n  -H 'accept: application/json, text/plain, */*' \\\r\n  -H 'accept-language: zh,en;q=0.9,zh-CN;q=0.8' \\\r\n  -H 'cache-control: no-cache' \\\r\n  -H 'content-type: application/json' \\\r\n  --data-raw '{\"base_url\":\"https://qv90***.ai-plugin.io\",\"channel\":\"jh0y8fgk7\"}'\r\n```\r\n\r\n##### Stop Conversation\r\n\r\nAPI Endpoint: `https://qv90***.ai-plugin.io/convoai-stop`\r\n\r\n| key | value |\r\n| --- | --- |\r\n| agent_id | The agent id of the extension |\r\n\r\nExample cURL:\r\n\r\n```bash\r\ncurl 'https://qv90***.ai-plugin.io/convoai/convoai-stop' \\\r\n  -H 'accept: application/json, text/plain, */*' \\\r\n  -H 'accept-language: zh,en;q=0.9,zh-CN;q=0.8' \\\r\n  -H 'cache-control: no-cache' \\\r\n  -H 'content-type: application/json' \\\r\n  --data-raw '{\"agent_id\":\"1NT29X0ZX0JYPJ96CCL8F4Y4VUEGR566\"}'\r\n```\r\n",
        "label": {
          "en_US": "Agora Conversational AI",
          "ja_JP": "Agora Conversational AI",
          "pt_BR": "Agora Conversational AI",
          "zh_Hans": "Agora Conversational AI"
        },
        "latest_package_identifier": "plutoless/convoai:0.0.6@cf1835095b3ac8f969e1e485bb1bdd9c328bb1598f71105def3a75b39a78ccb3",
        "latest_version": "0.0.6",
        "model": {},
        "name": "convoai",
        "org": "plutoless",
        "plugin_id": "plutoless/convoai",
        "plugins": {
          "agent_strategies": null,
          "endpoints": [
            "group/convoai.yaml"
          ],
          "models": null,
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-03-24T01:48:10Z",
        "version_updated_at": "2025-03-24T01:48:10Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Tencent"
        },
        "category": "model",
        "created_at": "2025-02-17T06:59:46Z",
        "endpoint": {},
        "icon": "langgenius/packages/tencent/_assets/icon_s_en.svg",
        "index_id": "langgenius___tencent",
        "install_count": 2305,
        "introduction": "",
        "label": {
          "en_US": "tencent"
        },
        "latest_package_identifier": "langgenius/tencent:0.0.2@79f21c55ce83f173557e018999738e8180c9232f7b08387874a30ac02c2acff4",
        "latest_version": "0.0.2",
        "model": {
          "background": "#E5E7EB",
          "configurate_methods": [
            "predefined-model"
          ],
          "description": {
            "en_US": "Tencent"
          },
          "help": {
            "title": {
              "en_US": "Get your API key from Tencent AI",
              "zh_Hans": "从腾讯云获取 API Key"
            },
            "url": {
              "en_US": "https://cloud.tencent.com/product/asr"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.svg",
            "zh_Hans": "icon_l_zh.svg"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "Tencent",
            "zh_Hans": "腾讯云"
          },
          "model_credential_schema": null,
          "models": [
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "tencent"
              },
              "model": "tencent",
              "model_properties": {
                "file_upload_limit": 25,
                "supported_file_extensions": "flac,mp3,mp4,mpeg,mpga,m4a,ogg,wav,webm"
              },
              "model_type": "speech2text",
              "parameter_rules": [],
              "pricing": null
            }
          ],
          "position": {},
          "provider": "tencent",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "APPID",
                  "zh_Hans": "APPID"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter the APPID of your Tencent Cloud ASR service",
                  "zh_Hans": "在此输入您的腾讯语音识别服务的 APPID"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "app_id"
              },
              {
                "default": null,
                "label": {
                  "en_US": "SecretId",
                  "zh_Hans": "SecretId"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter the SecretId of your Tencent Cloud ASR service",
                  "zh_Hans": "在此输入您的腾讯语音识别服务的 SecretId"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "secret_id"
              },
              {
                "default": null,
                "label": {
                  "en_US": "SecretKey",
                  "zh_Hans": "SecretKey"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter the SecretKey of your Tencent Cloud ASR service",
                  "zh_Hans": "在此输入您的腾讯语音识别服务的 SecretKey"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "secret_key"
              }
            ]
          },
          "supported_model_types": [
            "speech2text"
          ]
        },
        "name": "tencent",
        "org": "langgenius",
        "plugin_id": "langgenius/tencent",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/tencent.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": false,
              "moderation": false,
              "rerank": false,
              "speech2text": true,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-02-17T06:59:55Z",
        "version_updated_at": "2025-02-17T06:59:55Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "A simple plugin that extracts specific values from JSON data based on user-defined keys or paths.",
          "ja_JP": "ユーザーが定義したキーまたはパスに基づいてJSONデータから特定の値を抽出するシンプルなプラグイン。",
          "pt_BR": "Um plugin simples que extrai valores específicos de dados JSON com base em chaves ou caminhos definidos pelo usuário.",
          "zh_Hans": "一个简单的插件，可以根据用户定义的键或路径从JSON数据中提取特定值。"
        },
        "category": "tool",
        "created_at": "2025-04-02T08:56:32Z",
        "endpoint": {},
        "icon": "shanjijian/packages/json_extractor/_assets/icon.svg",
        "index_id": "shanjijian___json_extractor",
        "install_count": 2235,
        "introduction": "## **Description**\n\n**json_extractor** is a simple and efficient tool designed to extract specific values from JSON data. It allows users to define custom query paths or keys to retrieve the exact information they need from complex JSON structures. The tool processes user-defined JSON objects or strings and returns the desired values based on the paths provided.\n\n### **Key Features:**\n\n- **User-defined query paths**: Extract data by specifying keys or paths using dot notation.\n- **Supports nested JSON**: Handles complex nested JSON objects and arrays.\n- **Efficient data extraction**: Quickly retrieves the required values without unnecessary processing.\n- **No data storage**: The tool processes data locally and does not store or share any user data.\n\nWhether you're working with small or large JSON files, **json_extractor** is a simple solution for extracting specific data with ease.",
        "label": {
          "en_US": "JSON Extractor",
          "ja_JP": "JSON エクストラクタ",
          "pt_BR": "Extrator de JSON",
          "zh_Hans": "JSON 提取器"
        },
        "latest_package_identifier": "shanjijian/json_extractor:0.0.1@956b785fbd77f193d7fa6a64c79c1e78336607f9fbe793a088139f7941d1a463",
        "latest_version": "0.0.1",
        "model": {},
        "name": "json_extractor",
        "org": "shanjijian",
        "plugin_id": "shanjijian/json_extractor",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/json_extractor.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {}
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "shanjijian",
            "description": {
              "en_US": "Extracts specific values from JSON data based on user-defined keys or paths.",
              "pt_BR": "Extrai valores específicos dos dados JSON com base em chaves ou caminhos definidos pelo usuário。",
              "zh_Hans": "根据用户定义的键或路径从 JSON 数据中提取特定值。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "JSON Extractor",
              "pt_BR": "Extrator JSON",
              "zh_Hans": "JSON 提取器"
            },
            "name": "json_extractor",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Extracts specific values from JSON data based on user-defined keys or paths.",
                  "pt_BR": "Extrai valores específicos dos dados JSON com base em chaves ou caminhos definidos pelo usuário.",
                  "zh_Hans": "根据用户定义的键或路径从 JSON 数据中提取特定值。"
                },
                "llm": "Extracts specific values from JSON data based on user-defined keys or paths."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "shanjijian",
                "label": {
                  "en_US": "JSON Extractor",
                  "pt_BR": "Extrator de JSON",
                  "zh_Hans": "JSON 提取器"
                },
                "name": "json_extractor"
              },
              "output_schema": {
                "properties": {
                  "name": {
                    "type": "string"
                  }
                },
                "type": "object"
              },
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The JSON data from which values will be extracted.",
                    "pt_BR": "Os dados JSON dos quais os valores serão extraídos。",
                    "zh_Hans": "从中提取值的 JSON 数据。"
                  },
                  "label": {
                    "en_US": "JSON Data",
                    "pt_BR": "Dados JSON",
                    "zh_Hans": "JSON 数据"
                  },
                  "llm_description": "The JSON data from which values will be extracted.",
                  "max": null,
                  "min": null,
                  "name": "json_data",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "One or more JSON paths to extract specific values using dot notation, separated by commas (e.g., user.address.city, user.name).",
                    "pt_BR": "Um ou mais caminhos JSON para extrair valores específicos usando a notação de ponto, separados por vírgulas (por exemplo, user.address.city, user.name).",
                    "zh_Hans": "使用点表示法提取特定值的一个或多个 JSON 路径，路径之间用逗号分隔（例如：user.address.city, user.name）。"
                  },
                  "label": {
                    "en_US": "Query Paths",
                    "pt_BR": "Caminhos de consulta",
                    "zh_Hans": "查询路径"
                  },
                  "llm_description": "One or more JSON paths to extract specific values using dot notation, separated by commas.",
                  "max": null,
                  "min": null,
                  "name": "query_path",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-02T08:56:37Z",
        "version_updated_at": "2025-04-02T08:56:37Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Autonavi Open Platform service toolkit.",
          "pt_BR": "Kit de ferramentas de serviço Autonavi Open Platform.",
          "zh_Hans": "高德开放平台服务工具包。"
        },
        "category": "tool",
        "created_at": "2024-11-28T10:37:34Z",
        "endpoint": {},
        "icon": "langgenius/packages/gaode/_assets/icon.svg",
        "index_id": "langgenius___gaode",
        "install_count": 2189,
        "introduction": "# Overview\nAutoNavi, also known as Gaode Map, is a provider of digital mapping, navigation, and location-based services.\n\nThe AutoNavi Weather Forecast tool integrated within Dify is designed to provide users with accurate and real-time weather information. \n\n# Configure\n1. Register an account in [Autonavi developer platform](https://console.amap.com/dev/key/app).\n2. Create a new application and copy the API key.\n3. Install the Autonavi tool from Dify Marketplace.\n\n![](./_assets/gaode_install.png)\n\n4. Add Autonavi tool to your workflow. Click \"To authorize\" and fill in the API key.\n5. Fill in the city name in Chinese. \n\n![](./_assets/gaode_parameters.png)\n\nThe response will be like the following:\n\n![](./_assets/gaode_test.png)",
        "label": {
          "en_US": "Autonavi",
          "pt_BR": "Autonavi",
          "zh_Hans": "高德"
        },
        "latest_package_identifier": "langgenius/gaode:0.0.2@960a445e3b92f6fe774486411305bc0e78bd515d583f6dac7f2f77af9d162446",
        "latest_version": "0.0.2",
        "model": {},
        "name": "gaode",
        "org": "langgenius",
        "plugin_id": "langgenius/gaode",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/gaode.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "utilities"
          },
          {
            "name": "travel"
          },
          {
            "name": "weather"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "API Key",
                "pt_BR": "Fogo a chave",
                "zh_Hans": "API Key"
              },
              "name": "api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please enter your Autonavi API Key",
                "pt_BR": "Insira sua chave de API Autonavi",
                "zh_Hans": "请输入你的高德开放平台 API Key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://console.amap.com/dev/key/app"
            }
          ],
          "identity": {
            "author": "CharlieWei",
            "description": {
              "en_US": "Autonavi Open Platform service toolkit.",
              "pt_BR": "Kit de ferramentas de serviço Autonavi Open Platform.",
              "zh_Hans": "高德开放平台服务工具包。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Autonavi",
              "pt_BR": "Autonavi",
              "zh_Hans": "高德"
            },
            "name": "gaode",
            "tags": [
              "utilities",
              "productivity",
              "travel",
              "weather"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Weather forecast inquiry",
                  "pt_BR": "Inquérito sobre previsão meteorológica.",
                  "zh_Hans": "天气预报查询。"
                },
                "llm": "A tool when you want to ask about the weather or weather-related question."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "CharlieWei",
                "label": {
                  "en_US": "Weather Forecast",
                  "pt_BR": "Previsão do tempo",
                  "zh_Hans": "天气预报"
                },
                "name": "gaode_weather"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Target city for weather forecast query.",
                    "pt_BR": "Cidade de destino para consulta de previsão do tempo.",
                    "zh_Hans": "天气预报查询的目标城市。"
                  },
                  "label": {
                    "en_US": "city",
                    "pt_BR": "cidade",
                    "zh_Hans": "城市"
                  },
                  "llm_description": "If you don't know you can extract the city name from the question or you can reply：Please tell me your city. You have to extract the Chinese city name from the question.",
                  "max": null,
                  "min": null,
                  "name": "city",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:04:05Z",
        "version_updated_at": "2025-02-17T07:04:05Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "YouTube",
          "pt_BR": "YouTube é o maior site de compartilhamento de vídeos do mundo, onde os usuários podem fazer upload, assistir e compartilhar vídeos.",
          "zh_Hans": "YouTube（油管）是全球最大的视频分享网站，用户可以在上面上传、观看和分享视频。"
        },
        "category": "tool",
        "created_at": "2024-12-02T14:51:14Z",
        "endpoint": {},
        "icon": "langgenius/packages/youtube/_assets/icon.svg",
        "index_id": "langgenius___youtube",
        "install_count": 2177,
        "introduction": "# YouTube\n\n## Overview\n\n[YouTube](https://www.youtube.com/) is the biggest online video sharing platform. Currently, Dify.ai has two relevant tools: `Video Statistics` to analyse the videos' information by entering the URL or keyword.\n\n## Configuration\n\n### 1. Apply for YouTube API Key\n\nEnsure that you are allowed to use Google Cloud Service\n\n> If you don't have an account, go to the [Google credential site](https://console.cloud.google.com/apis/credentials) and follow their instructions to create an account.\n\nIf you have the account, go to the APIs & Services page and click `Create credentials -> API key` to create an API key.\n\n![](./_assets/youtube_1.PNG)\n\nFollow the step and click `Enabled APIs and services -> YouTube Data API v3` to enable the YouTube Data API.\n\n### 2. Setup the YouTube API in the Dify Tool page\n\nOn the Dify navigation page, click `Tools > Youtube > To Authorize` to fill in the API Key.\n\n![](./_assets/youtube_2.PNG)\n\n### 3. Using the tool\n\nYou can use the YouTube tool in the following application types:\n\n![](./_assets/youtube_3.PNG)\n\n#### Chatflow / Workflow applications\n\nBoth Chatflow and Workflow applications support adding **Video statistics** nodes. \n\n#### Agent applications\n\nAdd the **Video statistics** tool in the Agent application, then enter relevant commands to invoke this tool.",
        "label": {
          "en_US": "YouTube",
          "pt_BR": "YouTube",
          "zh_Hans": "YouTube"
        },
        "latest_package_identifier": "langgenius/youtube:0.0.2@d8a2a859b2868a436069330b728afeb03c78393c142343397f97226b8da8e503",
        "latest_version": "0.0.2",
        "model": {},
        "name": "youtube",
        "org": "langgenius",
        "plugin_id": "langgenius/youtube",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/youtube.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "videos"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "Google API key",
                "pt_BR": "Chave da API do Google",
                "zh_Hans": "Google API key"
              },
              "name": "google_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Google API key",
                "pt_BR": "Insira sua chave da API do Google",
                "zh_Hans": "请输入你的 Google API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://console.developers.google.com/apis/credentials"
            }
          ],
          "identity": {
            "author": "langgenius",
            "description": {
              "en_US": "YouTube",
              "pt_BR": "YouTube é o maior site de compartilhamento de vídeos do mundo, onde os usuários podem fazer upload, assistir e compartilhar vídeos.",
              "zh_Hans": "YouTube（油管）是全球最大的视频分享网站，用户可以在上面上传、观看和分享视频。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "YouTube",
              "pt_BR": "YouTube",
              "zh_Hans": "YouTube"
            },
            "name": "youtube",
            "tags": [
              "videos"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool for get statistics about a channel's videos.",
                  "pt_BR": "Uma ferramenta para obter estatísticas sobre os vídeos de um canal.",
                  "zh_Hans": "一个用于获取油管频道视频统计数据的工具。"
                },
                "llm": "A tool for get statistics about a channel's videos. Input should be the name of the channel like PewDiePie."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Video statistics",
                  "pt_BR": "Estatísticas de vídeo",
                  "zh_Hans": "视频统计"
                },
                "name": "youtube_video_statistics"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The name of the channel you want to search.",
                    "pt_BR": "O nome do canal que você deseja pesquisar.",
                    "zh_Hans": "你想要搜索的油管频道名。"
                  },
                  "label": {
                    "en_US": "Channel name",
                    "pt_BR": "Nome do canal",
                    "zh_Hans": "频道名"
                  },
                  "llm_description": "The name of the channel you want to search.",
                  "max": null,
                  "min": null,
                  "name": "channel",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The start date of the analytics.",
                    "pt_BR": "A data de início da análise.",
                    "zh_Hans": "分析的开始日期。"
                  },
                  "label": {
                    "en_US": "Start date",
                    "pt_BR": "Data de início",
                    "zh_Hans": "开始日期"
                  },
                  "llm_description": "The start date of the analytics, the format of the date must be YYYY-MM-DD like 2020-01-01.",
                  "max": null,
                  "min": null,
                  "name": "start_date",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The end date of the analytics.",
                    "pt_BR": "A data de término da análise.",
                    "zh_Hans": "分析的结束日期。"
                  },
                  "label": {
                    "en_US": "End date",
                    "pt_BR": "Data de término",
                    "zh_Hans": "结束日期"
                  },
                  "llm_description": "The end date of the analytics, the format of the date must be YYYY-MM-DD like 2024-01-01.",
                  "max": null,
                  "min": null,
                  "name": "end_date",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:10:50Z",
        "version_updated_at": "2025-02-17T07:10:50Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "GetImg API integration for image generation and scraping."
        },
        "category": "tool",
        "created_at": "2024-12-04T04:52:23Z",
        "endpoint": {},
        "icon": "langgenius/packages/getimgai/_assets/icon.svg",
        "index_id": "langgenius___getimgai",
        "install_count": 2134,
        "introduction": "# GetImg.ai Tool\n\n## Overview\n\nGetImg.ai is an AI-powered platform specializing in image generation. It provides an accessible and versatile image generation solution: as a tool in Dify, it receives text inputs and generates corresponding images based on user prompts. The service offers various image styles and customization options. \n\n## Configuration\n\n### 1. Apply for getimg.ai Account\nPlease apply for an API Key from [getimg.ai dashboard](https://dashboard.getimg.ai/api-keys).\n\n![](./_assets/getimgai_1.png)\n\n### 2. Get getimg.ai tools from Plugin Marketplace\n\nThe getimg.ai tools could be found at the Plugin Marketplace, please install it first.\n\n### 3. Fill in the configuration in Dify\n\nOn the Dify navigation page, click `Tools > getimg.ai > Authorize` and fill in the API Key.\n\n![](./_assets/getimgai_2.png)\n\n### 4. Use the tool\nYou can use the getimg.ai tool in the following application types.\n\n![](./_assets/getimgai_3.png)\n\n#### Chatflow / Workflow applications\nBoth Chatflow and Workflow applications support adding a getimg.ai tool node.\n\n#### Agent applications\nAdd the getimg.ai tool in the Agent application, then enter online search instructions to call this tool.",
        "label": {
          "en_US": "getimg.ai"
        },
        "latest_package_identifier": "langgenius/getimgai:0.0.2@9fd607caafdd50fe2a7b426807ffbb8444e952b389a172856e96ce83f6a29e8c",
        "latest_version": "0.0.2",
        "model": {},
        "name": "getimgai",
        "org": "langgenius",
        "plugin_id": "langgenius/getimgai",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/getimgai.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "image"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "getimg.ai server's Base URL"
              },
              "name": "base_url",
              "options": null,
              "placeholder": {
                "en_US": "https://api.getimg.ai/v1"
              },
              "required": false,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "getimg.ai API Key"
              },
              "name": "getimg_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your getimg.ai API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://dashboard.getimg.ai/api-keys"
            }
          ],
          "identity": {
            "author": "Matri Qi",
            "description": {
              "en_US": "GetImg API integration for image generation and scraping."
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "getimg.ai"
            },
            "name": "getimgai",
            "tags": [
              "image"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Generate image via getimg.ai."
                },
                "llm": "This tool is used to generate image from prompt or image via https://getimg.ai."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Matri Qi",
                "label": {
                  "en_US": "text2image"
                },
                "name": "text2image"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The text prompt used to generate the image. The getimg.aier will generate an image based on this prompt."
                  },
                  "label": {
                    "en_US": "prompt"
                  },
                  "llm_description": "this prompt text will be used to generate image.",
                  "max": null,
                  "min": null,
                  "name": "prompt",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The getimg.ai mode to use. The mode determines the endpoint used to generate the image."
                  },
                  "label": {
                    "en_US": "mode"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "mode",
                  "options": [
                    {
                      "label": {
                        "en_US": "essential-v2"
                      },
                      "value": "essential-v2"
                    },
                    {
                      "label": {
                        "en_US": "stable-diffusion-xl"
                      },
                      "value": "stable-diffusion-xl"
                    },
                    {
                      "label": {
                        "en_US": "stable-diffusion"
                      },
                      "value": "stable-diffusion"
                    },
                    {
                      "label": {
                        "en_US": "latent-consistency"
                      },
                      "value": "latent-consistency"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The style preset to use. The style preset guides the generation towards a particular style. It's just efficient for `Essential V2` mode."
                  },
                  "label": {
                    "en_US": "style"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "style",
                  "options": [
                    {
                      "label": {
                        "en_US": "photorealism"
                      },
                      "value": "photorealism"
                    },
                    {
                      "label": {
                        "en_US": "anime"
                      },
                      "value": "anime"
                    },
                    {
                      "label": {
                        "en_US": "art"
                      },
                      "value": "art"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The aspect ratio of the generated image. It's just efficient for `Essential V2` mode."
                  },
                  "label": {
                    "en_US": "aspect ratio"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "aspect_ratio",
                  "options": [
                    {
                      "label": {
                        "en_US": "1:1"
                      },
                      "value": "1:1"
                    },
                    {
                      "label": {
                        "en_US": "4:5"
                      },
                      "value": "4:5"
                    },
                    {
                      "label": {
                        "en_US": "5:4"
                      },
                      "value": "5:4"
                    },
                    {
                      "label": {
                        "en_US": "2:3"
                      },
                      "value": "2:3"
                    },
                    {
                      "label": {
                        "en_US": "3:2"
                      },
                      "value": "3:2"
                    },
                    {
                      "label": {
                        "en_US": "4:7"
                      },
                      "value": "4:7"
                    },
                    {
                      "label": {
                        "en_US": "7:4"
                      },
                      "value": "7:4"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The file format of the generated image."
                  },
                  "label": {
                    "en_US": "output format"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "output_format",
                  "options": [
                    {
                      "label": {
                        "en_US": "jpeg"
                      },
                      "value": "jpeg"
                    },
                    {
                      "label": {
                        "en_US": "png"
                      },
                      "value": "png"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The format in which the generated images are returned. Must be one of url or b64. URLs are only valid for 1 hour after the image has been generated."
                  },
                  "label": {
                    "en_US": "response format"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    {
                      "label": {
                        "en_US": "url"
                      },
                      "value": "url"
                    },
                    {
                      "label": {
                        "en_US": "b64"
                      },
                      "value": "b64"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Model ID supported by this pipeline and family. It's just efficient for `Stable Diffusion XL`, `Stable Diffusion`, `Latent Consistency` mode."
                  },
                  "label": {
                    "en_US": "model"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Text input that will not guide the image generation. It's just efficient for `Stable Diffusion XL`, `Stable Diffusion`, `Latent Consistency` mode."
                  },
                  "label": {
                    "en_US": "negative prompt"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "negative_prompt",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Prompt sent to second tokenizer and text encoder. If not defined, prompt is used in both text-encoders. It's just efficient for `Stable Diffusion XL` mode."
                  },
                  "label": {
                    "en_US": "prompt2"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "prompt_2",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "he width of the generated image in pixels. Width needs to be multiple of 64."
                  },
                  "label": {
                    "en_US": "width"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "width",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "he height of the generated image in pixels. Height needs to be multiple of 64."
                  },
                  "label": {
                    "en_US": "height"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "height",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The number of denoising steps. More steps usually can produce higher quality images, but take more time to generate.  It's just efficient for `Stable Diffusion XL`, `Stable Diffusion`, `Latent Consistency` mode."
                  },
                  "label": {
                    "en_US": "steps"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "steps",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:03:22Z",
        "version_updated_at": "2025-02-17T07:03:22Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Provide workflow nodes with the ability to read and write databases.",
          "zh_Hans": "在工作流中提供读写数据库能力的节点。"
        },
        "category": "tool",
        "created_at": "2025-03-31T12:57:55Z",
        "endpoint": {},
        "icon": "spance/packages/db_client_node/_assets/icon.svg",
        "index_id": "spance___db_client_node",
        "install_count": 2112,
        "introduction": "# DB-Client-Node\n\n<p>\n<a href=\"https://github.com/spance/db-client-node\"><img alt=\"GitHub Release\" src=\"https://img.shields.io/github/v/release/spance/db-client-node?style=social\"/></a>\n<a href=\"https://marketplace.dify.ai/plugins/spance/db_client_node\"><img alt=\"Dify Marketplace\" src=\"https://img.shields.io/badge/Dify%20Marketplace-DB_Client_Node-blue\"/></a>\n</p>\n\n[简体中文](./README_CN.md) | **English**  \n\n[DB-Client-Node](https://github.com/spance/db-client-node) is a plugin tool designed for Dify workflows, providing database operation nodes. It currently supports PostgreSQL databases.\n\n![DB-Client-Node demo](https://f001.backblazeb2.com/file/static/dbcn-demo_en.png)\n\n## Features\n- Securely manages database connection information through Dify’s `credentials_for_provider` mechanism.\n- Supports parameterized execution of DML statements such as `SELECT` and `INSERT`.\n- Provides dynamic SQL generation with conditional logic support.\n- Implements performance-optimized batch data insertion.\n\n## Installation\nTo use `DB-Client-Node` in a Dify workflow:\n1. Install the plugin via the Dify plugin [marketplace](https://marketplace.dify.ai/plugins/spance/db_client_node) or manually download version from the [release page](https://github.com/spance/db-client-node/releases).\n2. Configure PostgreSQL credentials in Dify’s `Plugins -> Authorization` settings.\n\n![DB-Client-Node credential demo](https://f001.backblazeb2.com/file/static/dbcn-auth-demo.png)\n\n## Nodes Overview\n\n### Standard Client Nodes\nStandard client nodes are used to execute DML statements such as `SELECT` and `INSERT`. Due to limitations in Dify’s tool plugin form interface, which does not support dynamic parameters, two variants are provided:\n- **`PostgreSQL Client(5)`**: Supports up to 5 SQL parameters.\n- **`PostgreSQL Client(10)`**: Supports up to 10 SQL parameters.\n\nThese nodes are identical except for the number of supported parameters.\n\n#### Usage Examples\n\n1. **Executing SQL Without Parameters**\n   | Field       | Value                              |\n   |-------------|------------------------------------|\n   | SQL         | `SELECT * FROM messages WHERE id=123` |\n   | Parameter 0-N | *Leave blank*                    |\n\n2. **Executing SQL With Parameters**\n   | Field       | Value                              |\n   |-------------|------------------------------------|\n   | SQL         | `SELECT * FROM messages ` <br/> `WHERE name=$arg0 AND user=$arg1` |\n   | Parameter 0 | Corresponding to `$arg0`: Enter a literal value or use `/` to select a node variable |\n   | Parameter 1 | Corresponding to `$arg1`: Enter a literal value or use `/` to select a node variable |\n\n3. **Executing Dynamic SQL**\n   | Field       | Value                              |\n   |-------------|------------------------------------|\n   | SQL         | `SELECT * FROM messages ` <br/> `WHERE name=$arg0` <br/> `{% if arg1 %} AND user=$arg1 {% endif %}` |\n   | Parameter 0 | Corresponding to `$arg0`: Enter a literal value or use `/` to select a node variable |\n   | Parameter 1 | Corresponding to `$arg1`: Enter a literal value or use `/` to select a node variable |\n\n   - The `{% if %} ... {% endif %}` syntax uses Jinja2 templating to enable dynamic SQL. If the condition (e.g., `arg1`) is not met, that portion is excluded from the executed SQL; otherwise, it is included.\n\n### Batch Client Node\nThe batch client node is designed for bulk data insertion, utilizing the database’s batch submission mechanism to reduce I/O overhead and latency.\n\n#### Usage Example\n| Field             | Value                              |\n|-------------------|------------------------------------|\n| SQL               | `INSERT INTO messages (name, user, content) ` <br/> `VALUES (?, ?, ?)` |\n| Parameter Object List | Select an upstream node variable containing a JSON-serialized list of parameter objects, e.g., `List[List[Any]]` or `List[Dict[str, Any]]`. Examples: <br/> - `\"[[1,2,3],[5,6,7]]\"` <br/> - `\"[{name:1,user:2,content:3},{name:5,user:6,content:7}]\"` |\n| Key Names for Extraction | Leave blank if the parameter list is an array. For dictionary-type lists, provide a comma-separated list of keys to extract values (in order), e.g., `name,user,content` |\n\n## Node Output\n\n### Query Execution\nFor `SELECT` statements, the node provides the following return values:\n- **`data`**: The query result data, represented as a list of rows where each row is an array of column values.\n- **`columns`**: A list of column names corresponding to the result set.\n- **`json[0].data`**: An alternative representation of the query result data in the default `json` return format of the plugin tool, structured as an object with column names as keys.\n\n**Example Output:**\n```json\n{\n    \"data\": [\n        [\"row0_value0\", \"row0_value1\", \"row0_value2\"],\n        [\"row1_value0\", \"row1_value1\", \"row1_value2\"],\n        [\"row2_value0\", \"row2_value1\", \"row2_value2\"]\n    ],\n    \"columns\": [\"column0\", \"column1\", \"column2\"],\n    \"json\": [\n        {\n            \"data\": [\n                {\n                    \"column0\": \"value0\",\n                    \"column1\": \"value1\",\n                    \"column2\": \"value2\"\n                }\n            ]\n        }\n    ]\n}\n```\n\n### Update Execution\nFor `INSERT`, `UPDATE`, or `DELETE` statements, the node returns:\n- **`affected_rows`**: The number of rows affected.\n\n**Example Output:**\n```json\n{\n    \"affected_rows\": 2\n}\n```\n\n## Limitations\n- Currently supports only PostgreSQL databases.\n- The number of parameters in standard client nodes is fixed (5 or 10), limited by Dify’s form interface.\n- Dynamic SQL relies on Jinja2 syntax, which may require familiarity with templating.\n\n## Contribution Guidelines\nContributions are welcome! To participate:\n1. Fork this repository.\n2. Create a feature branch (`git checkout -b feature/your-feature`).\n3. Commit your changes (`git commit -m \"Add your feature\"`).\n4. Push to the branch (`git push origin feature/your-feature`).\n5. Submit a Pull Request.\n\nPlease ensure your code adheres to the project’s style guidelines and includes appropriate tests.\n\n## License\nThis project is released under the Apache License 2.0. See the `LICENSE` file for details.\n\n## Contact\nFor questions or support, please submit an issue in the repository.\n",
        "label": {
          "en_US": "Database Client",
          "zh_Hans": "数据库操作客户端"
        },
        "latest_package_identifier": "spance/db_client_node:0.1.47@f5c67e307064c72125fbdc5e3e51617d3041c97ae3587dc81f7bc60c71545f85",
        "latest_version": "0.1.47",
        "model": {},
        "name": "db_client_node",
        "org": "spance",
        "plugin_id": "spance/db_client_node",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/dbcn_provider.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {}
        },
        "status": "active",
        "tags": [
          {
            "name": "utilities"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": "localhost",
              "help": null,
              "label": {
                "en_US": "Host address of the database",
                "zh_Hans": "数据库的主机地址"
              },
              "name": "db_host",
              "options": null,
              "placeholder": null,
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": "5432",
              "help": null,
              "label": {
                "en_US": "Port number of the database",
                "zh_Hans": "数据库的端口号"
              },
              "name": "db_port",
              "options": null,
              "placeholder": null,
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Name of the database",
                "zh_Hans": "数据库的名称"
              },
              "name": "db_name",
              "options": null,
              "placeholder": null,
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Username for database access",
                "zh_Hans": "数据库访问的用户名"
              },
              "name": "db_user",
              "options": null,
              "placeholder": null,
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Password for database access",
                "zh_Hans": "数据库访问的密码"
              },
              "name": "db_password",
              "options": null,
              "placeholder": null,
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": "100",
              "help": null,
              "label": {
                "en_US": "Max fetched rows",
                "zh_Hans": "最大读取行数"
              },
              "name": "max_fetched_rows",
              "options": null,
              "placeholder": null,
              "required": false,
              "scope": null,
              "type": "text-input",
              "url": null
            }
          ],
          "identity": {
            "author": "spance",
            "description": {
              "en_US": "Provide workflow nodes with the ability to read and write databases.",
              "zh_Hans": "在工作流中提供读写数据库能力的节点。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Database Client",
              "zh_Hans": "数据库操作客户端"
            },
            "name": "db_client_node",
            "tags": [
              "utilities"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "PostgreSQL Client",
                  "zh_Hans": "读写PostgreSQL客户端，最多5个参数。"
                },
                "llm": "A Dify plugin tool to operate PostgreSQL database."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "spance",
                "label": {
                  "en_US": "PostgreSQL Client(5)",
                  "zh_Hans": "PostgreSQL 客户端(5)"
                },
                "name": "postgres_node_5"
              },
              "output_schema": {
                "properties": {
                  "affected_rows": {
                    "type": "number"
                  },
                  "columns": {
                    "items": {
                      "type": "string"
                    },
                    "type": "array"
                  },
                  "data": {
                    "items": {
                      "type": "object"
                    },
                    "type": "array"
                  }
                },
                "type": "object"
              },
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The SQL query to execute (allow literal arg, or `$arg0~N` as parameters)",
                    "zh_Hans": "要执行的SQL查询（参数使用变量`$arg0~N`表示，或使用字面值）"
                  },
                  "label": {
                    "en_US": "SQL Query",
                    "zh_Hans": "SQL查询"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Enter the parameter corresponding to the SQL variables.",
                    "zh_Hans": "输入变量对应的参数。"
                  },
                  "label": {
                    "en_US": "arg0",
                    "zh_Hans": "参数0"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "arg0",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Enter the parameter corresponding to the SQL variables.",
                    "zh_Hans": "输入变量对应的参数。"
                  },
                  "label": {
                    "en_US": "arg1",
                    "zh_Hans": "参数1"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "arg1",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Enter the parameter corresponding to the SQL variables.",
                    "zh_Hans": "输入变量对应的参数。"
                  },
                  "label": {
                    "en_US": "arg2",
                    "zh_Hans": "参数2"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "arg2",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Enter the parameter corresponding to the SQL variables.",
                    "zh_Hans": "输入变量对应的参数。"
                  },
                  "label": {
                    "en_US": "arg3",
                    "zh_Hans": "参数3"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "arg3",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Enter the parameter corresponding to the SQL variables.",
                    "zh_Hans": "输入变量对应的参数。"
                  },
                  "label": {
                    "en_US": "arg4",
                    "zh_Hans": "参数4"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "arg4",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "PostgreSQL Client",
                  "zh_Hans": "读写PostgreSQL客户端，最多10个参数。"
                },
                "llm": "A Dify plugin tool to operate PostgreSQL database."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "spance",
                "label": {
                  "en_US": "PostgreSQL Client(10)",
                  "zh_Hans": "PostgreSQL 客户端(10)"
                },
                "name": "postgres_node_10"
              },
              "output_schema": {
                "properties": {
                  "affected_rows": {
                    "type": "number"
                  },
                  "columns": {
                    "items": {
                      "type": "string"
                    },
                    "type": "array"
                  },
                  "data": {
                    "items": {
                      "type": "object"
                    },
                    "type": "array"
                  }
                },
                "type": "object"
              },
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The SQL query to execute (allow literal arg, or `$arg0~N` as parameters)",
                    "zh_Hans": "要执行的SQL查询（参数使用变量`$arg0~N`表示，或使用字面值）"
                  },
                  "label": {
                    "en_US": "SQL Query",
                    "zh_Hans": "SQL查询"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Enter the parameter corresponding to the SQL variables.",
                    "zh_Hans": "输入变量对应的参数。"
                  },
                  "label": {
                    "en_US": "arg0",
                    "zh_Hans": "参数0"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "arg0",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Enter the parameter corresponding to the SQL variables.",
                    "zh_Hans": "输入变量对应的参数。"
                  },
                  "label": {
                    "en_US": "arg1",
                    "zh_Hans": "参数1"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "arg1",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Enter the parameter corresponding to the SQL variables.",
                    "zh_Hans": "输入变量对应的参数。"
                  },
                  "label": {
                    "en_US": "arg2",
                    "zh_Hans": "参数2"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "arg2",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Enter the parameter corresponding to the SQL variables.",
                    "zh_Hans": "输入变量对应的参数。"
                  },
                  "label": {
                    "en_US": "arg3",
                    "zh_Hans": "参数3"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "arg3",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Enter the parameter corresponding to the SQL variables.",
                    "zh_Hans": "输入变量对应的参数。"
                  },
                  "label": {
                    "en_US": "arg4",
                    "zh_Hans": "参数4"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "arg4",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Enter the parameter corresponding to the SQL variables.",
                    "zh_Hans": "输入变量对应的参数。"
                  },
                  "label": {
                    "en_US": "arg5",
                    "zh_Hans": "参数5"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "arg5",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Enter the parameter corresponding to the SQL variables.",
                    "zh_Hans": "输入变量对应的参数。"
                  },
                  "label": {
                    "en_US": "arg6",
                    "zh_Hans": "参数6"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "arg6",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Enter the parameter corresponding to the SQL variables.",
                    "zh_Hans": "输入变量对应的参数。"
                  },
                  "label": {
                    "en_US": "arg7",
                    "zh_Hans": "参数7"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "arg7",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Enter the parameter corresponding to the SQL variables.",
                    "zh_Hans": "输入变量对应的参数。"
                  },
                  "label": {
                    "en_US": "arg8",
                    "zh_Hans": "参数8"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "arg8",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Enter the parameter corresponding to the SQL variables.",
                    "zh_Hans": "输入变量对应的参数。"
                  },
                  "label": {
                    "en_US": "arg9",
                    "zh_Hans": "参数9"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "arg9",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "PostgreSQL Batch Client",
                  "zh_Hans": "读写PostgreSQL批量操作客户端"
                },
                "llm": "A Dify plugin tool to operate PostgreSQL database."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "spance",
                "label": {
                  "en_US": "PostgreSQL Batch Client",
                  "zh_Hans": "PostgreSQL 批量客户端"
                },
                "name": "postgres_batch_node"
              },
              "output_schema": {
                "properties": {
                  "affected_rows": {
                    "type": "number"
                  }
                },
                "type": "object"
              },
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The SQL batch query to execute (e.g. INSERT...values( ?, ?, ... ))",
                    "zh_Hans": "批量Insert查询（e.g. INSERT...values( ?, ?, ... )）"
                  },
                  "label": {
                    "en_US": "SQL Query",
                    "zh_Hans": "SQL查询"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The data-list of the batch. e.g. List[List[Any]] or List[Dict[str, Any]]",
                    "zh_Hans": "json序列化后的参数对象列表，形如：List[List[Any]] 或 List[Dict[str, Any]]"
                  },
                  "label": {
                    "en_US": "Parameters",
                    "zh_Hans": "参数对象列表"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "args",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "extract values by the Keys from Dict[str, Any].",
                    "zh_Hans": "当参数元素为字典类型，提供一个键名列表用于从字典中提取值元素集合（逗号分隔）."
                  },
                  "label": {
                    "en_US": "Keys of a parameter",
                    "zh_Hans": "取值的键名"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "keys_of_obj",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-02T01:34:16Z",
        "version_updated_at": "2025-04-02T01:34:16Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Feishu cloud document, requires the following permissions: docx:document、drive:drive、docs:document.content:read.",
          "zh_Hans": "飞书云文档，需要开通以下权限: docx:document、drive:drive、docs:document.content:read。"
        },
        "category": "tool",
        "created_at": "2025-02-26T10:40:39Z",
        "endpoint": {},
        "icon": "langgenius/packages/feishu_document/_assets/icon.svg",
        "index_id": "langgenius___feishu_document",
        "install_count": 2097,
        "introduction": "",
        "label": {
          "en_US": "Feishu Cloud Document",
          "zh_Hans": "飞书云文档"
        },
        "latest_package_identifier": "langgenius/feishu_document:0.0.1@5c16426317d871a0abf4d81bec1d1ef1a5b7f34491d429a453c13bdc1fb2fa82",
        "latest_version": "0.0.1",
        "model": {},
        "name": "feishu_document",
        "org": "langgenius",
        "plugin_id": "langgenius/feishu_document",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/feishu_document.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "social"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "APP ID"
              },
              "name": "app_id",
              "options": null,
              "placeholder": {
                "en_US": "Please input your feishu app id",
                "zh_Hans": "请输入你的飞书 app id"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": "https://open.larkoffice.com/app"
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "APP Secret"
              },
              "name": "app_secret",
              "options": null,
              "placeholder": {
                "en_US": "Please input your app secret",
                "zh_Hans": "请输入你的飞书 app secret"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            }
          ],
          "identity": {
            "author": "Doug Lea",
            "description": {
              "en_US": "Lark cloud document, requires the following permissions: docx:document、drive:drive、docs:document.content:read.\n",
              "zh_Hans": "飞书云文档，需要开通以下权限: docx:document、drive:drive、docs:document.content:read。\n"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Lark Cloud Document",
              "zh_Hans": "飞书云文档"
            },
            "name": "feishu_document",
            "tags": [
              "social",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Create Lark document",
                  "zh_Hans": "创建飞书文档，支持创建空文档和带内容的文档，支持 markdown 语法创建。应用需要开启机器人能力(https://open.feishu.cn/document/faq/trouble-shooting/how-to-enable-bot-ability)。"
                },
                "llm": "A tool for creating Feishu documents."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Create Lark document",
                  "zh_Hans": "创建飞书文档"
                },
                "name": "create_document"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Document title, only supports plain text content.",
                    "zh_Hans": "文档标题，只支持纯文本内容。"
                  },
                  "label": {
                    "en_US": "Document title",
                    "zh_Hans": "文档标题"
                  },
                  "llm_description": "文档标题，只支持纯文本内容，可以为空。",
                  "max": null,
                  "min": null,
                  "name": "title",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Document content, supports markdown syntax, can be empty.",
                    "zh_Hans": "文档内容，支持 markdown 语法，可以为空。"
                  },
                  "label": {
                    "en_US": "Document content",
                    "zh_Hans": "文档内容"
                  },
                  "llm_description": "文档内容，支持 markdown 语法，可以为空。",
                  "max": null,
                  "min": null,
                  "name": "content",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The token of the folder where the document is located. If it is not passed or is empty, it means the root directory. For Example: https://svi136aogf123.feishu.cn/drive/folder/JgR9fiG9AlPt8EdsSNpcGjIInbf\n",
                    "zh_Hans": "文档所在文件夹的 Token，不传或传空表示根目录。例如：https://svi136aogf123.feishu.cn/drive/folder/JgR9fiG9AlPt8EdsSNpcGjIInbf。"
                  },
                  "label": {
                    "en_US": "folder_token",
                    "zh_Hans": "文档所在文件夹的 Token"
                  },
                  "llm_description": "文档所在文件夹的 Token，不传或传空表示根目录。例如：https://svi136aogf123.feishu.cn/drive/folder/JgR9fiG9AlPt8EdsSNpcGjIInbf。",
                  "max": null,
                  "min": null,
                  "name": "folder_token",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get document content",
                  "zh_Hans": "获取飞书云文档的内容"
                },
                "llm": "A tool for retrieving content from Feishu cloud documents."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Get Document Content",
                  "zh_Hans": "获取飞书云文档的内容"
                },
                "name": "get_document_content"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for a Feishu document. You can also input the document's URL.",
                    "zh_Hans": "飞书文档的唯一标识，支持输入文档的 URL。"
                  },
                  "label": {
                    "en_US": "document_id",
                    "zh_Hans": "飞书文档的唯一标识"
                  },
                  "llm_description": "飞书文档的唯一标识，支持输入文档的 URL。",
                  "max": null,
                  "min": null,
                  "name": "document_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "markdown",
                  "form": "form",
                  "human_description": {
                    "en_US": "Format of the document return, optional values are text, markdown, can be empty, default is markdown.",
                    "zh_Hans": "文档返回格式，可选值有 text、markdown，可以为空，默认值为 markdown。"
                  },
                  "label": {
                    "en_US": "mode",
                    "zh_Hans": "文档返回格式"
                  },
                  "llm_description": "文档返回格式，可选值有 text、markdown，可以为空，默认值为 markdown。",
                  "max": null,
                  "min": null,
                  "name": "mode",
                  "options": [
                    {
                      "label": {
                        "en_US": "text",
                        "zh_Hans": "text"
                      },
                      "value": "text"
                    },
                    {
                      "label": {
                        "en_US": "markdown",
                        "zh_Hans": "markdown"
                      },
                      "value": "markdown"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "0",
                  "form": "form",
                  "human_description": {
                    "en_US": "Specifies the language for MentionUser, optional values are [0, 1]. 0: User's default name, 1: User's English name, default is 0.\n",
                    "zh_Hans": "指定返回的 MentionUser，即@用户的语言，可选值有 [0,1]。0: 该用户的默认名称，1: 该用户的英文名称，默认值为 0。\n"
                  },
                  "label": {
                    "en_US": "lang",
                    "zh_Hans": "指定@用户的语言"
                  },
                  "llm_description": "指定返回的 MentionUser，即@用户的语言，可选值有 [0,1]。0: 该用户的默认名称，1: 该用户的英文名称，默认值为 0。\n",
                  "max": null,
                  "min": null,
                  "name": "lang",
                  "options": [
                    {
                      "label": {
                        "en_US": "User's default name",
                        "zh_Hans": "用户的默认名称"
                      },
                      "value": "0"
                    },
                    {
                      "label": {
                        "en_US": "User's English name",
                        "zh_Hans": "用户的英文名称"
                      },
                      "value": "1"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Adding new content to Lark documents",
                  "zh_Hans": "在飞书文档中新增内容"
                },
                "llm": "A tool for adding new content to Lark documents."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Write Document",
                  "zh_Hans": "在飞书文档中新增内容"
                },
                "name": "write_document"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for a Feishu document. You can also input the document's URL.",
                    "zh_Hans": "飞书文档的唯一标识，支持输入文档的 URL。"
                  },
                  "label": {
                    "en_US": "document_id",
                    "zh_Hans": "飞书文档的唯一标识"
                  },
                  "llm_description": "飞书文档的唯一标识，支持输入文档的 URL。",
                  "max": null,
                  "min": null,
                  "name": "document_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Plain text or Markdown content. Note that embedded tables in the document should not have merged cells.",
                    "zh_Hans": "纯文本或 Markdown 内容。注意文档的内嵌套表格不允许有单元格合并。"
                  },
                  "label": {
                    "en_US": "Plain text or Markdown content",
                    "zh_Hans": "纯文本或 Markdown 内容"
                  },
                  "llm_description": "纯文本或 Markdown 内容，注意文档的内嵌套表格不允许有单元格合并。",
                  "max": null,
                  "min": null,
                  "name": "content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "end",
                  "form": "form",
                  "human_description": {
                    "en_US": "Content insertion position, optional values are start, end. 'start' means adding content at the beginning of the document; 'end' means adding content at the end of the document. The default value is end.",
                    "zh_Hans": "内容添加位置，可选值有 start、end。start 表示在文档开头添加内容；end 表示在文档结尾添加内容，默认值为 end。"
                  },
                  "label": {
                    "en_US": "position",
                    "zh_Hans": "内容添加位置"
                  },
                  "llm_description": "内容添加位置，可选值有 start、end。start 表示在文档开头添加内容；end 表示在文档结尾添加内容，默认值为 end。",
                  "max": null,
                  "min": null,
                  "name": "position",
                  "options": [
                    {
                      "label": {
                        "en_US": "document start",
                        "zh_Hans": "文档开始"
                      },
                      "value": "start"
                    },
                    {
                      "label": {
                        "en_US": "document end",
                        "zh_Hans": "文档结束"
                      },
                      "value": "end"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "List document blocks",
                  "zh_Hans": "获取飞书文档所有块的富文本内容并分页返回"
                },
                "llm": "A tool to get all blocks of Feishu documents"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "List Document Blocks",
                  "zh_Hans": "获取飞书文档所有块"
                },
                "name": "list_document_blocks"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for a Feishu document. You can also input the document's URL.",
                    "zh_Hans": "飞书文档的唯一标识，支持输入文档的 URL。"
                  },
                  "label": {
                    "en_US": "document_id",
                    "zh_Hans": "飞书文档的唯一标识"
                  },
                  "llm_description": "飞书文档的唯一标识，支持输入文档的 URL。",
                  "max": null,
                  "min": null,
                  "name": "document_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "open_id",
                  "form": "form",
                  "human_description": {
                    "en_US": "User ID type, optional values are open_id, union_id, user_id, with a default value of open_id.",
                    "zh_Hans": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。"
                  },
                  "label": {
                    "en_US": "user_id_type",
                    "zh_Hans": "用户 ID 类型"
                  },
                  "llm_description": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。",
                  "max": null,
                  "min": null,
                  "name": "user_id_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "open_id",
                        "zh_Hans": "open_id"
                      },
                      "value": "open_id"
                    },
                    {
                      "label": {
                        "en_US": "union_id",
                        "zh_Hans": "union_id"
                      },
                      "value": "union_id"
                    },
                    {
                      "label": {
                        "en_US": "user_id",
                        "zh_Hans": "user_id"
                      },
                      "value": "user_id"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 500,
                  "form": "form",
                  "human_description": {
                    "en_US": "Paging size, the default and maximum value is 500.",
                    "zh_Hans": "分页大小, 默认值和最大值为 500。"
                  },
                  "label": {
                    "en_US": "page_size",
                    "zh_Hans": "分页大小"
                  },
                  "llm_description": "分页大小, 表示一次请求最多返回多少条数据，默认值和最大值为 500。",
                  "max": null,
                  "min": null,
                  "name": "page_size",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Pagination token used to navigate through query results, allowing retrieval of additional items in subsequent requests.",
                    "zh_Hans": "分页标记，用于分页查询结果，以便下次遍历时获取更多项。"
                  },
                  "label": {
                    "en_US": "page_token",
                    "zh_Hans": "分页标记"
                  },
                  "llm_description": "分页标记，第一次请求不填，表示从头开始遍历；分页查询结果还有更多项时会同时返回新的 page_token，下次遍历可采用该 page_token 获取查询结果。",
                  "max": null,
                  "min": null,
                  "name": "page_token",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-26T10:40:43Z",
        "version_updated_at": "2025-02-26T10:40:43Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "A tool that enables step-by-step reasoning, helping non-reasoning models solve problems methodically.",
          "zh_Hans": "一个通过逐步推理帮助非推理模型有条理地解决问题的工具。"
        },
        "category": "tool",
        "created_at": "2025-03-23T00:58:23Z",
        "endpoint": {},
        "icon": "kalochin/packages/think/_assets/icon.svg",
        "index_id": "kalochin___think",
        "install_count": 2072,
        "introduction": "## Description\n\nThe \"think\" tool creates a dedicated space for LLMs to perform structured thinking during complex tasks. This tool enhances the LLM's problem-solving performance by providing a sandbox for reasoning through complex situations.\n\nWhen using multiple tools or making multi-step decisions, LLMs benefit from having a place to analyze information, verify policy compliance, and plan sequential actions. The \"think\" tool provides this space without retrieving new information or changing any data - it simply logs the thought process.\n\nThis tool is a simple implementation inspired by Anthropic's \"think\" tool research. For more information, please see: https://www.anthropic.com/engineering/claude-think-tool\n\n## Optimal Scenarios for Using the Think Tool\n\nResearch and testing have shown that the think tool provides significant advantages in several key scenarios:\n\n1. **Analysis of Tool Results**: Particularly valuable when the LLM needs to carefully evaluate outputs from previous tool calls before proceeding, especially in situations where strategy adjustments may be necessary.\n\n2. **Regulatory and Guidelines Adherence**: Essential in contexts with strict policies or complex regulations that must be carefully followed and verified.\n\n3. **Multi-step Decision Processes**: Most beneficial in scenarios where actions build sequentially, with each decision affecting subsequent options and where errors could have cascading consequences.\n\n## Effective Implementation Strategies\n\nTo maximize the benefits of the think tool in your LLM implementation:\n\n1. **Create Context-Specific Examples**\n   Develop tailored examples that demonstrate:\n   - Appropriate reasoning depth for your use case\n   - Techniques for deconstructing complex tasks\n   - Frameworks for addressing common scenarios\n   - Methods for ensuring comprehensive information gathering\n\n2. **Integrate Detailed Guidance in System Instructions**\n   For complex implementations, incorporate comprehensive think tool instructions within the system prompt rather than the tool description. This approach helps the LLM better incorporate structured thinking into its overall problem-solving process.\n\n## Limitations and When to Skip the Think Tool\n\nThe think tool does have limitations and isn't beneficial in all scenarios. Consider the additional token usage when deciding whether to implement it. The tool offers minimal benefits in:\n\n- **Simple or Parallel Tool Operations**: Use cases requiring only single tool calls or non-sequential multiple tool operations typically don't benefit from the additional reflection.\n\n- **Straightforward Task Execution**: Scenarios with minimal constraints or where the LLM's standard reasoning is already sufficient for the task at hand.\n\n## Implementation Guide\n\nIncorporate the think tool into your LLM environment through these steps:\n\n1. **Begin with Complex Scenarios**: Identify challenging use cases where the LLM currently experiences difficulties with policy compliance or complex reasoning chains.\n\n2. **Configure the Tool for Your Domain**: Implement a customized think tool specific to your needs, including relevant examples and use cases in your system instructions.\n\n3. **Evaluate and Adjust**: Observe how the LLM utilizes the tool in real-world scenarios and refine your implementation to encourage more effective reasoning patterns.\n\n## Maximizing Benefits with Proper Prompting\n\nTo get the most value from the think tool, consider adding specific instructions to your system prompt about when and how to use it:\n\n```\n## Using the think tool\n\nBefore taking any action or responding to the user after receiving tool results, use the think tool as a scratchpad to:\n- List the specific rules that apply to the current request\n- Check if all required information is collected\n- Verify that the planned action complies with all policies\n- Iterate over tool results for correctness \n\nHere are some examples of what to iterate over inside the think tool:\n<think_tool_example_1>\nUser wants to [specific scenario]\n- Need to verify: [key information]\n- Check relevant rules: [list rules]\n- Verify [important conditions]\n- Plan: [outline steps]\n</think_tool_example_1>\n```\n\nDomain-specific examples in your prompts significantly improve how effectively the LLM uses the think tool. Consider including examples tailored to your specific use case.\n\n## Credits\n\nOriginal concept by Anthropic  \nTool author: [Kalo Chin](https://github.com/fdb02983rhy)  \nRepository: [https://github.com/fdb02983rhy/dify-think-plugin](https://github.com/fdb02983rhy/dify-think-plugin)\n\n## License\n\nThis project is licensed under the MIT License.",
        "label": {
          "en_US": "The \"Think\" Tool",
          "zh_Hans": "一个\"思考\"工具"
        },
        "latest_package_identifier": "kalochin/think:0.0.2@7db53d0e76992b05053ad8e21225efab2da2b6a55678214429eb9c42ac41a8a8",
        "latest_version": "0.0.2",
        "model": {},
        "name": "think",
        "org": "kalochin",
        "plugin_id": "kalochin/think",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/think.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "kalochin",
            "description": {
              "en_US": "A tool that enables step-by-step reasoning, helping non-reasoning LLMs solve problems methodically.",
              "zh_Hans": "一个通过逐步推理帮助非推理LLM有条理地解决问题的工具。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "The \"Think\" Tool",
              "zh_Hans": "The \"Think\" Tool"
            },
            "name": "think",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool that allows LLMs to think. It will not obtain new information or change any data, but just log the thought.",
                  "zh_Hans": "一个允许LLM思考的工具。它不会获取新信息或更改任何数据，只会记录思考过程。"
                },
                "llm": "Use the tool to think about something. It will not obtain new information or change the database, but just append the thought to the log. Use it when complex reasoning or some cache memory is needed."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "kalochin",
                "label": {
                  "en_US": "Think",
                  "zh_Hans": "思考"
                },
                "name": "think"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "A thought to think about.",
                    "zh_Hans": "需要思考的内容。"
                  },
                  "label": {
                    "en_US": "Thought",
                    "zh_Hans": "思考内容"
                  },
                  "llm_description": "A thought to think about.",
                  "max": null,
                  "min": null,
                  "name": "thought",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-25T02:35:15Z",
        "version_updated_at": "2025-03-25T02:35:15Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Get official developer documentations on DevDocs.",
          "zh_Hans": "从DevDocs获取官方开发者文档。"
        },
        "category": "tool",
        "created_at": "2024-12-02T15:01:21Z",
        "endpoint": {},
        "icon": "langgenius/packages/devdocs/_assets/icon.svg",
        "index_id": "langgenius___devdocs",
        "install_count": 2071,
        "introduction": "# Overview\n[DevDocs](https://devdocs.io) is a comprehensive online documentation platform designed for developers. It provides a unified interface for accessing documentation across various programming languages, frameworks, and tools.\n\n# Configure\n1. Install DevDocs from Dify Marketplace.\n2. Add DevDocs tool to your workflow.\n3. Preview the documentation you want to interact with in [DevDocs](https://devdocs.io/).\n4. Fill in **Documentation name** and **Topic name**.\n\n![](_assets/devdocs.png)",
        "label": {
          "en_US": "DevDocs",
          "zh_Hans": "DevDocs"
        },
        "latest_package_identifier": "langgenius/devdocs:0.0.2@5e1109b00787364f47f879bd8fef488e200498105fbfea16b9eed0e7c5ee1cbb",
        "latest_version": "0.0.2",
        "model": {},
        "name": "devdocs",
        "org": "langgenius",
        "plugin_id": "langgenius/devdocs",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/devdocs.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "search"
          }
        ],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "Richards Tu",
            "description": {
              "en_US": "Get official developer documentations on DevDocs.",
              "zh_Hans": "从DevDocs获取官方开发者文档。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "DevDocs",
              "zh_Hans": "DevDocs"
            },
            "name": "devdocs",
            "tags": [
              "search",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tools for searching for a specific topic and path in DevDocs based on the provided documentation name and topic. Don't for get to add some shots in the system prompt; for example, the documentation name should be like \\\"vuex~4\\\", \\\"css\\\", or \\\"python~3.12\\\", while the topic should be like \\\"guide/actions\\\" for Vuex 4, \\\"display-box\\\" for CSS, or \\\"library/code\\\" for Python 3.12.",
                  "zh_Hans": "一个用于根据提供的文档名称和主题，在DevDocs中搜索特定主题和路径的工具。不要忘记在系统提示词中添加一些示例；例如，文档名称应该是\\\"vuex~4\\\"、\\\"css\\\"或\\\"python~3.12\\\"，而主题应该是\\\"guide/actions\\\"用于Vuex 4，\\\"display-box\\\"用于CSS，或\\\"library/code\\\"用于Python 3.12。"
                },
                "llm": "A tools for searching for specific developer documentation in DevDocs based on the provided documentation name and topic."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Richards Tu",
                "label": {
                  "en_US": "Search Developer Docs",
                  "zh_Hans": "搜索开发者文档"
                },
                "name": "searchDevDocs"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The name of the documentation.",
                    "zh_Hans": "文档名称。"
                  },
                  "label": {
                    "en_US": "Documentation name",
                    "zh_Hans": "文档名称"
                  },
                  "llm_description": "The name of the documentation, such as \\\"vuex~4\\\", \\\"css\\\", or \\\"python~3.12\\\". The exact value should be identified by the user.",
                  "max": null,
                  "min": null,
                  "name": "doc",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The path of the section/topic.",
                    "zh_Hans": "文档主题的路径。"
                  },
                  "label": {
                    "en_US": "Topic name",
                    "zh_Hans": "主题名称"
                  },
                  "llm_description": "The path of the section/topic, such as \\\"guide/actions\\\" for Vuex 4, \\\"display-box\\\" for CSS, or \\\"library/code\\\" for Python 3.12.",
                  "max": null,
                  "min": null,
                  "name": "topic",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:07:41Z",
        "version_updated_at": "2025-02-17T07:07:41Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Convert your Dify Models into OpenAI compatible API",
          "ja_JP": "DifyモデルをOpenAI互換APIに変換",
          "pt_BR": "Converter seus modelos Dify em uma API compatível com OpenAI",
          "zh_Hans": "将您的Dify模型转换为OpenAI兼容API"
        },
        "category": "extension",
        "created_at": "2025-01-03T10:05:07Z",
        "endpoint": {
          "endpoints": [
            {
              "hidden": false,
              "method": "POST",
              "path": "/v1/chat/completions"
            },
            {
              "hidden": false,
              "method": "POST",
              "path": "/v1/embeddings"
            }
          ],
          "settings": [
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "API key",
                "pt_BR": "API key",
                "zh_Hans": "API key"
              },
              "name": "api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your API key",
                "pt_BR": "Please input your API key",
                "zh_Hans": "请输入你的 API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "LLM",
                "pt_BR": "LLM",
                "zh_Hans": "LLM"
              },
              "name": "llm",
              "options": null,
              "placeholder": {
                "en_US": "Please select a LLM",
                "pt_BR": "Please select a LLM",
                "zh_Hans": "请选择一个 LLM"
              },
              "required": false,
              "scope": "llm",
              "type": "model-selector",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Text Embedding",
                "pt_BR": "Text Embedding",
                "zh_Hans": "文本嵌入"
              },
              "name": "text_embedding",
              "options": null,
              "placeholder": {
                "en_US": "Please select a Text Embedding Model",
                "pt_BR": "Please select a Text Embedding Model",
                "zh_Hans": "请选择一个文本嵌入模型"
              },
              "required": false,
              "scope": "text-embedding",
              "type": "model-selector",
              "url": null
            }
          ]
        },
        "icon": "langgenius/packages/oaicompat_dify_model/_assets/icon.svg",
        "index_id": "langgenius___oaicompat_dify_model",
        "install_count": 2050,
        "introduction": "## oaicompat_dify_model\n\n**Author:** langgenius\n**Version:** 0.0.1\n**Type:** extension\n\n### Description\n\n\n\n",
        "label": {
          "en_US": "OpenAI Compatible Dify Models",
          "ja_JP": "OpenAI Compatible Dify Models",
          "pt_BR": "OpenAI Compatible Dify Models",
          "zh_Hans": "OpenAI Compatible Dify Models"
        },
        "latest_package_identifier": "langgenius/oaicompat_dify_model:0.0.5@986eea3a982822f2b51d5e47afbeeb58a0ab299f9648920045f9d888fd514dc5",
        "latest_version": "0.0.5",
        "model": {},
        "name": "oaicompat_dify_model",
        "org": "langgenius",
        "plugin_id": "langgenius/oaicompat_dify_model",
        "plugins": {
          "agent_strategies": null,
          "endpoints": [
            "group/oaicompat_dify_model.yaml"
          ],
          "models": null,
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "endpoint": {
              "enabled": true
            },
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": true,
              "rerank": false,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-03-14T01:47:45Z",
        "version_updated_at": "2025-03-14T01:47:45Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Bocha is a Chinese search engine for AI, you can get enhanced search details from billions of web documents, including weather, news, wikis, healthcare, train tickets, images, and more.",
          "ja_JP": "検索API、リランクAPI、AGIのための世界的なエンジン。あなたのLLMアプリケーションを世界と接続し、クリーンで正確かつ高品質なコンテキストにアクセスできます。",
          "pt_BR": "API de Busca, API de Reordenação, O motor mundial para AGI. Conecte suas aplicações LLM ao mundo e acesse contextos limpos, precisos e de alta qualidade.",
          "zh_Hans": "博查是一个给AI用的中文搜索引擎，让你的AI应用从近百亿网页和生态内容源中获取高质量的世界知识，涵盖天气、新闻、百科、医疗、火车票、图片等多种领域。"
        },
        "category": "tool",
        "created_at": "2025-01-13T06:29:03Z",
        "endpoint": {},
        "icon": "seekerliu/packages/bocha/_assets/icon.svg",
        "index_id": "seekerliu___bocha",
        "install_count": 2026,
        "introduction": "# Bocha\n\n## Overview\nBocha is a Chinese search engine for AI, you can get enhanced search details from billions of web documents, including weather, news, wikis, healthcare, train tickets, images, and more.\n\nBocha offers two tools: Bocha Web Search and Bocha AI Search, designed to connect your LLM applications to the world, and access clean, accurate, high-quality context.\n\n### **1. Bocha Web Search**\nSearch with Bocha Web Search API and get enhanced search details, including page titles, urls, snippets, site names, site icons, publication dates, images, and more.\n\n### **2. Bocha AI Search**\nSearch with Bocha AI Search API, recognizes the semantics of search terms and additionally returns structured modal cards with content from vertical domains.\n\n## Configuration\n\n### **1. Apply for an API Key**  \nApply for an API Key at [Bocha AI Open Platform](https://open.bochaai.com).\n\n### **2. Get Bocha Tools from Plugin Marketplace**  \nThe Bocha tools can be found in the Plugin Marketplace. Please install them.\n\n### **3. Fill in the Configuration in Dify**  \nOn the Dify navigation page, go to **Tools > Bocha > Authentication** to enter the API Key.\n\n![Authentication](./_assets/Bocha_1.PNG)\n\n### **4. Using the Tool**  \nYou can use the Bocha tool in the following application types:\n\n![Using the tool](./_assets/Bocha_2.PNG)\n\n#### **Chatflow / Workflow Applications**  \nBoth Chatflow and Workflow applications support adding Bocha series tool nodes, providing two tools:\n  - Bocha Web Search\n  - Bocha AI Search\n\n#### **Agent Applications**  \nSelect the Bocha tool you need to add in the Agent application, then enter commands to call the tool.\n",
        "label": {
          "en_US": "Bocha",
          "ja_JP": "Bocha",
          "pt_BR": "Bocha",
          "zh_Hans": "博查"
        },
        "latest_package_identifier": "seekerliu/bocha:0.0.1@2929331141313ed18ab98af1ef07377d58c8dace1a624d2a1a30d5a2a5ef98ee",
        "latest_version": "0.0.1",
        "model": {},
        "name": "bocha",
        "org": "seekerliu",
        "plugin_id": "seekerliu/bocha",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/bocha.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {}
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "Bocha API key",
                "ja_JP": "Bocha API key",
                "pt_BR": "Bocha API key",
                "zh_Hans": "博查 API Key"
              },
              "name": "bocha_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Bocha API key",
                "ja_JP": "Please input your Bocha API key",
                "pt_BR": "Please input your Bocha API key",
                "zh_Hans": "请输入你的博查 API Key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://open.bochaai.com"
            }
          ],
          "identity": {
            "author": "seekerliu",
            "description": {
              "en_US": "Bocha is a Chinese search engine for AI, you can get enhanced search details from billions of web documents, including weather, news, wikis, healthcare, train tickets, images, and more.",
              "ja_JP": "Bocha is a Chinese search engine for AI, you can get enhanced search details from billions of web documents, including weather, news, wikis, healthcare, train tickets, images, and more.",
              "pt_BR": "Bocha is a Chinese search engine for AI, you can get enhanced search details from billions of web documents, including weather, news, wikis, healthcare, train tickets, images, and more.",
              "zh_Hans": "博查是一个给AI用的中文搜索引擎，让你的AI应用从近百亿网页和生态内容源中获取高质量的世界知识，涵盖天气、新闻、百科、医疗、火车票、图片等多种领域。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Bocha",
              "ja_JP": "Bocha",
              "pt_BR": "Bocha",
              "zh_Hans": "博查"
            },
            "name": "bocha",
            "tags": [
              "search"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Search with Bocha Web Search and get enhanced search details from billions of web documents, including page titles, urls, summaries, site names, site icons, publication dates, image links, and more",
                  "ja_JP": "Bocha Web Searchで検索し、数十億のウェブドキュメントからページタイトル、URL、要約、サイト名、サイトアイコン、公開日、画像リンクなどの詳細な検索結果を取得します",
                  "pt_BR": "Pesquise com o Bocha Web Search e obtenha detalhes aprimorados de bilhões de documentos da web, incluindo títulos de páginas, URLs, resumos, nomes de sites, ícones de sites, datas de publicação, links de imagens e muito mais",
                  "zh_Hans": "从博查搜索全网信息和网页链接，返回结果包括网页标题、网页URL、网页摘要、网站名称、网站图标、发布时间、图片链接等"
                },
                "llm": "使用博查搜索引擎(Web Search API)搜索互联网网页，输入应为搜索查询字符串，输出将返回搜索结果的详细信息，包括网页标题、网页URL、网页摘要、网站名称、网站图标、网页发布时间等"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "seekerliu",
                "label": {
                  "en_US": "Bocha Web Search",
                  "ja_JP": "Bocha Web Search",
                  "pt_BR": "Bocha Web Search",
                  "zh_Hans": "Bocha Web Search"
                },
                "name": "BochaWebSearch"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The keywords or phrases to search",
                    "ja_JP": "検索キーワードまたはフレーズ",
                    "pt_BR": "As palavras-chave ou frases para pesquisar",
                    "zh_Hans": "搜索关键词或语句"
                  },
                  "label": {
                    "en_US": "query",
                    "ja_JP": "query",
                    "pt_BR": "query",
                    "zh_Hans": "query"
                  },
                  "llm_description": "搜索关键词或语句",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "noLimit",
                  "form": "llm",
                  "human_description": {
                    "en_US": "The time range for the search results. Available options noLimit, oneYear, oneMonth, oneWeek, oneDay. Default is noLimit",
                    "ja_JP": "検索結果の時間範囲。利用可能なオプションは noLimit, oneYear, oneMonth, oneWeek, oneDay です。デフォルトは noLimit です",
                    "pt_BR": "O intervalo de tempo para os resultados da pesquisa. Opções disponíveis noLimit, oneYear, oneMonth, oneWeek, oneDay. O padrão é noLimit",
                    "zh_Hans": "搜索的时间范围，可选值为 noLimit, oneYear, oneMonth, oneWeek, oneDay。默认为 noLimit"
                  },
                  "label": {
                    "en_US": "freshness",
                    "ja_JP": "freshness",
                    "pt_BR": "freshness",
                    "zh_Hans": "freshness"
                  },
                  "llm_description": "搜索的时间范围，可选值为 noLimit, oneYear, oneMonth, oneWeek, oneDay。默认为 noLimit",
                  "max": null,
                  "min": null,
                  "name": "freshness",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 10,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Number of search results to retrieve (1-10), default is 10",
                    "ja_JP": "検索結果の数(1-10)、デフォルトは10",
                    "pt_BR": "Número de resultados de pesquisa para recuperar (1-10), padrão é 10",
                    "zh_Hans": "搜索结果的数量(1-10)，默认为10"
                  },
                  "label": {
                    "en_US": "count",
                    "ja_JP": "count",
                    "pt_BR": "count",
                    "zh_Hans": "count"
                  },
                  "llm_description": "搜索结果的数量(1-10)，默认为10",
                  "max": 10,
                  "min": 1,
                  "name": "count",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Search with Bocha AI Search, recognizes the semantics of search terms and additionally returns structured modal cards with content from vertical domains",
                  "ja_JP": "Bocha AI Searchで検索し、検索語の意味を認識し、さらに垂直領域のコンテンツを含む構造化されたモーダルカードを返します",
                  "pt_BR": "Pesquise com o Bocha AI Search, reconhece a semântica dos termos de pesquisa e retorna cartões modais estruturados com conteúdo de domínios verticais",
                  "zh_Hans": "在博查网页搜索的基础上，AI识别搜索词语义并额外返回垂直领域内容的结构化模态卡，例如天气卡、日历卡、百科卡等"
                },
                "llm": "使用博查AI搜索引擎(AI Search API)搜索互联网网页，输入应为搜索查询字符串，输出将返回搜索结果的详细信息，包括网页、图片以及垂直领域内容的模态卡"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "seekerliu",
                "label": {
                  "en_US": "Bocha AI Search",
                  "ja_JP": "Bocha AI Search",
                  "pt_BR": "Bocha AI Search",
                  "zh_Hans": "Bocha AI Search"
                },
                "name": "BochaAISearch"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The keywords or phrases to search",
                    "ja_JP": "検索キーワードまたはフレーズ",
                    "pt_BR": "As palavras-chave ou frases para pesquisar",
                    "zh_Hans": "搜索关键词或语句，例如：北京天气"
                  },
                  "label": {
                    "en_US": "query",
                    "ja_JP": "query",
                    "pt_BR": "query",
                    "zh_Hans": "query"
                  },
                  "llm_description": "搜索关键词或语句，例如：北京天气",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "noLimit",
                  "form": "llm",
                  "human_description": {
                    "en_US": "The time range for the search results. Available options noLimit, oneYear, oneMonth, oneWeek, oneDay. Default is noLimit",
                    "ja_JP": "検索結果の時間範囲。利用可能なオプションは noLimit, oneYear, oneMonth, oneWeek, oneDay です。デフォルトは noLimit です",
                    "pt_BR": "O intervalo de tempo para os resultados da pesquisa. Opções disponíveis noLimit, oneYear, oneMonth, oneWeek, oneDay. O padrão é noLimit",
                    "zh_Hans": "搜索的时间范围，可选值为 noLimit, oneYear, oneMonth, oneWeek, oneDay。默认为 noLimit"
                  },
                  "label": {
                    "en_US": "freshness",
                    "ja_JP": "freshness",
                    "pt_BR": "freshness",
                    "zh_Hans": "freshness"
                  },
                  "llm_description": "搜索的时间范围，可选值为 noLimit, oneYear, oneMonth, oneWeek, oneDay。默认为 noLimit",
                  "max": null,
                  "min": null,
                  "name": "freshness",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-01-13T06:29:09Z",
        "version_updated_at": "2025-01-13T06:29:09Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Feishu base, requires the following permissions: bitable:app.",
          "zh_Hans": "飞书多维表格，需要开通以下权限: bitable:app。"
        },
        "category": "tool",
        "created_at": "2025-02-26T09:32:06Z",
        "endpoint": {},
        "icon": "langgenius/packages/feishu_base/_assets/icon.png",
        "index_id": "langgenius___feishu_base",
        "install_count": 1996,
        "introduction": "",
        "label": {
          "en_US": "Feishu Base",
          "zh_Hans": "飞书多维表格"
        },
        "latest_package_identifier": "langgenius/feishu_base:0.0.1@00d7b356f3e8ac9980850be25444d2112abe0f3cf22c540b1d2c77603589d2ee",
        "latest_version": "0.0.1",
        "model": {},
        "name": "feishu_base",
        "org": "langgenius",
        "plugin_id": "langgenius/feishu_base",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/feishu_base.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "social"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "APP ID"
              },
              "name": "app_id",
              "options": null,
              "placeholder": {
                "en_US": "Please input your feishu app id",
                "zh_Hans": "请输入你的飞书 app id"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": "https://open.larkoffice.com/app"
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "APP Secret"
              },
              "name": "app_secret",
              "options": null,
              "placeholder": {
                "en_US": "Please input your app secret",
                "zh_Hans": "请输入你的飞书 app secret"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            }
          ],
          "identity": {
            "author": "Doug Lea",
            "description": {
              "en_US": "Feishu base, requires the following permissions: bitable:app.\n",
              "zh_Hans": "飞书多维表格，需要开通以下权限: bitable:app。\n"
            },
            "icon": "icon.png",
            "label": {
              "en_US": "Feishu Base",
              "zh_Hans": "飞书多维表格"
            },
            "name": "feishu_base",
            "tags": [
              "social",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Batch Delete Data Tables from Multidimensional Table",
                  "zh_Hans": "批量删除多维表格中的数据表"
                },
                "llm": "A tool for batch deleting data tables from a multidimensional table. (批量删除多维表格中的数据表)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Delete Tables",
                  "zh_Hans": "删除数据表"
                },
                "name": "delete_tables"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for the multidimensional table, supports inputting document URL.",
                    "zh_Hans": "多维表格的唯一标识符，支持输入文档 URL。"
                  },
                  "label": {
                    "en_US": "app_token",
                    "zh_Hans": "app_token"
                  },
                  "llm_description": "多维表格的唯一标识符，支持输入文档 URL。",
                  "max": null,
                  "min": null,
                  "name": "app_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "IDs of the tables to be deleted. Each operation supports deleting up to 50 tables. Example: [\"tbl1TkhyTWDkSoZ3\"]. Ensure that either table_ids or table_names is not empty.\n",
                    "zh_Hans": "待删除的数据表的 ID，每次操作最多支持删除 50 个数据表。示例值：[\"tbl1TkhyTWDkSoZ3\"]。请确保 table_ids 和 table_names 至少有一个不为空。"
                  },
                  "label": {
                    "en_US": "Table IDs",
                    "zh_Hans": "数据表 ID"
                  },
                  "llm_description": "待删除的数据表的 ID，每次操作最多支持删除 50 个数据表。示例值：[\"tbl1TkhyTWDkSoZ3\"]。请确保 table_ids 和 table_names 至少有一个不为空。",
                  "max": null,
                  "min": null,
                  "name": "table_ids",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Names of the tables to be deleted. Each operation supports deleting up to 50 tables. Example: [\"Table1\", \"Table2\"]. Ensure that either table_names or table_ids is not empty.\n",
                    "zh_Hans": "待删除的数据表的名称，每次操作最多支持删除 50 个数据表。示例值：[\"数据表1\", \"数据表2\"]。请确保 table_names 和 table_ids 至少有一个不为空。"
                  },
                  "label": {
                    "en_US": "Table Names",
                    "zh_Hans": "数据表名称"
                  },
                  "llm_description": "待删除的数据表的名称，每次操作最多支持删除 50 个数据表。示例值：[\"数据表1\", \"数据表2\"]。请确保 table_names 和 table_ids 至少有一个不为空。",
                  "max": null,
                  "min": null,
                  "name": "table_names",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get All Data Tables under Multidimensional Table",
                  "zh_Hans": "获取多维表格下的所有数据表"
                },
                "llm": "A tool for getting all data tables under a multidimensional table. (获取多维表格下的所有数据表)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "List Tables",
                  "zh_Hans": "列出数据表"
                },
                "name": "list_tables"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for the multidimensional table, supports inputting document URL.",
                    "zh_Hans": "多维表格的唯一标识符，支持输入文档 URL。"
                  },
                  "label": {
                    "en_US": "app_token",
                    "zh_Hans": "app_token"
                  },
                  "llm_description": "多维表格的唯一标识符，支持输入文档 URL。",
                  "max": null,
                  "min": null,
                  "name": "app_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 20,
                  "form": "form",
                  "human_description": {
                    "en_US": "Page size, default value: 20, maximum value: 100.\n",
                    "zh_Hans": "分页大小，默认值：20，最大值：100。"
                  },
                  "label": {
                    "en_US": "page_size",
                    "zh_Hans": "分页大小"
                  },
                  "llm_description": "分页大小，默认值：20，最大值：100。",
                  "max": null,
                  "min": null,
                  "name": "page_size",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Page token, leave empty for the first request to start from the beginning; a new page_token will be returned if there are more items in the paginated query results, which can be used for the next traversal. Example value: \"tblsRc9GRRXKqhvW\".\n",
                    "zh_Hans": "分页标记，第一次请求不填，表示从头开始遍历；分页查询结果还有更多项时会同时返回新的 page_token，下次遍历可采用该 page_token 获取查询结果。示例值：\"tblsRc9GRRXKqhvW\"。"
                  },
                  "label": {
                    "en_US": "page_token",
                    "zh_Hans": "分页标记"
                  },
                  "llm_description": "分页标记，第一次请求不填，表示从头开始遍历；分页查询结果还有更多项时会同时返回新的 page_token，下次遍历可采用该 page_token 获取查询结果。示例值：\"tblsRc9GRRXKqhvW\"。",
                  "max": null,
                  "min": null,
                  "name": "page_token",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Create Multidimensional Table in Specified Directory",
                  "zh_Hans": "在指定目录下创建多维表格"
                },
                "llm": "A tool for creating a multidimensional table in a specified directory. (在指定目录下创建多维表格)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Create Base",
                  "zh_Hans": "创建多维表格"
                },
                "name": "create_base"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Name of the multidimensional table App. Example value: \"A new multidimensional table\".\n",
                    "zh_Hans": "多维表格 App 名字，示例值：\"一篇新的多维表格\"。"
                  },
                  "label": {
                    "en_US": "name",
                    "zh_Hans": "多维表格 App 名字"
                  },
                  "llm_description": "多维表格 App 名字，示例值：\"一篇新的多维表格\"。",
                  "max": null,
                  "min": null,
                  "name": "name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Folder where the multidimensional table App belongs. Default is empty, meaning the table will be created in the root directory of the cloud space. Example values: Fa3sfoAgDlMZCcdcJy1cDFg8nJc or https://svi136aogf123.feishu.cn/drive/folder/Fa3sfoAgDlMZCcdcJy1cDFg8nJc.\nThe folder_token must be an existing folder and supports inputting folder token or folder URL.\n",
                    "zh_Hans": "多维表格 App 归属文件夹。默认为空，表示多维表格将被创建在云空间根目录。示例值: Fa3sfoAgDlMZCcdcJy1cDFg8nJc 或者 https://svi136aogf123.feishu.cn/drive/folder/Fa3sfoAgDlMZCcdcJy1cDFg8nJc。\nfolder_token 必须是已存在的文件夹，支持输入文件夹 token 或者文件夹 URL。\n"
                  },
                  "label": {
                    "en_US": "folder_token",
                    "zh_Hans": "多维表格 App 归属文件夹"
                  },
                  "llm_description": "多维表格 App 归属文件夹。默认为空，表示多维表格将被创建在云空间根目录。示例值: Fa3sfoAgDlMZCcdcJy1cDFg8nJc 或者 https://svi136aogf123.feishu.cn/drive/folder/Fa3sfoAgDlMZCcdcJy1cDFg8nJc。\nfolder_token 必须是已存在的文件夹，支持输入文件夹 token 或者文件夹 URL。\n",
                  "max": null,
                  "min": null,
                  "name": "folder_token",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Add Multiple Records to Multidimensional Table",
                  "zh_Hans": "在多维表格数据表中新增多条记录"
                },
                "llm": "A tool for adding multiple records to a multidimensional table. (在多维表格数据表中新增多条记录)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Add Records",
                  "zh_Hans": "新增多条记录"
                },
                "name": "add_records"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for the multidimensional table, supports inputting document URL.",
                    "zh_Hans": "多维表格的唯一标识符，支持输入文档 URL。"
                  },
                  "label": {
                    "en_US": "app_token",
                    "zh_Hans": "app_token"
                  },
                  "llm_description": "多维表格的唯一标识符，支持输入文档 URL。",
                  "max": null,
                  "min": null,
                  "name": "app_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for the multidimensional table data, either table_id or table_name must be provided, cannot be empty simultaneously.",
                    "zh_Hans": "多维表格数据表的唯一标识符，table_id 和 table_name 至少需要提供一个，不能同时为空。"
                  },
                  "label": {
                    "en_US": "table_id",
                    "zh_Hans": "table_id"
                  },
                  "llm_description": "多维表格数据表的唯一标识符，table_id 和 table_name 至少需要提供一个，不能同时为空。",
                  "max": null,
                  "min": null,
                  "name": "table_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Name of the multidimensional table data, either table_name or table_id must be provided, cannot be empty simultaneously.",
                    "zh_Hans": "多维表格数据表的名称，table_name 和 table_id 至少需要提供一个，不能同时为空。"
                  },
                  "label": {
                    "en_US": "table_name",
                    "zh_Hans": "table_name"
                  },
                  "llm_description": "多维表格数据表的名称，table_name 和 table_id 至少需要提供一个，不能同时为空。",
                  "max": null,
                  "min": null,
                  "name": "table_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "List of records to be added in this request. Example value: [{\"multi-line-text\":\"text content\",\"single_select\":\"option 1\",\"date\":1674206443000}]\nFor supported field types, refer to the integration guide (https://open.larkoffice.com/document/server-docs/docs/bitable-v1/notification). For data structures of different field types, refer to the data structure overview (https://open.larkoffice.com/document/server-docs/docs/bitable-v1/bitable-structure).\n",
                    "zh_Hans": "本次请求将要新增的记录列表，示例值：[{\"多行文本\":\"文本内容\",\"单选\":\"选项 1\",\"日期\":1674206443000}]。\n当前接口支持的字段类型请参考接入指南(https://open.larkoffice.com/document/server-docs/docs/bitable-v1/notification)，不同类型字段的数据结构请参考数据结构概述(https://open.larkoffice.com/document/server-docs/docs/bitable-v1/bitable-structure)。\n"
                  },
                  "label": {
                    "en_US": "records",
                    "zh_Hans": "记录列表"
                  },
                  "llm_description": "本次请求将要新增的记录列表，示例值：[{\"多行文本\":\"文本内容\",\"单选\":\"选项 1\",\"日期\":1674206443000}]。\n当前接口支持的字段类型请参考接入指南(https://open.larkoffice.com/document/server-docs/docs/bitable-v1/notification)，不同类型字段的数据结构请参考数据结构概述(https://open.larkoffice.com/document/server-docs/docs/bitable-v1/bitable-structure)。\n",
                  "max": null,
                  "min": null,
                  "name": "records",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "open_id",
                  "form": "form",
                  "human_description": {
                    "en_US": "User ID type, optional values are open_id, union_id, user_id, with a default value of open_id.",
                    "zh_Hans": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。"
                  },
                  "label": {
                    "en_US": "user_id_type",
                    "zh_Hans": "用户 ID 类型"
                  },
                  "llm_description": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。",
                  "max": null,
                  "min": null,
                  "name": "user_id_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "open_id",
                        "zh_Hans": "open_id"
                      },
                      "value": "open_id"
                    },
                    {
                      "label": {
                        "en_US": "union_id",
                        "zh_Hans": "union_id"
                      },
                      "value": "union_id"
                    },
                    {
                      "label": {
                        "en_US": "user_id",
                        "zh_Hans": "user_id"
                      },
                      "value": "user_id"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Query records in a multidimensional table, up to 500 rows per query.",
                  "zh_Hans": "查询多维表格数据表中的记录，单次最多查询 500 行记录。"
                },
                "llm": "A tool for querying records in a multidimensional table, up to 500 rows per query. (查询多维表格数据表中的记录，单次最多查询 500 行记录)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Search Records",
                  "zh_Hans": "查询记录"
                },
                "name": "search_records"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for the multidimensional table, supports inputting document URL.",
                    "zh_Hans": "多维表格的唯一标识符，支持输入文档 URL。"
                  },
                  "label": {
                    "en_US": "app_token",
                    "zh_Hans": "app_token"
                  },
                  "llm_description": "多维表格的唯一标识符，支持输入文档 URL。",
                  "max": null,
                  "min": null,
                  "name": "app_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for the multidimensional table data, either table_id or table_name must be provided, cannot be empty simultaneously.",
                    "zh_Hans": "多维表格数据表的唯一标识符，table_id 和 table_name 至少需要提供一个，不能同时为空。"
                  },
                  "label": {
                    "en_US": "table_id",
                    "zh_Hans": "table_id"
                  },
                  "llm_description": "多维表格数据表的唯一标识符，table_id 和 table_name 至少需要提供一个，不能同时为空。",
                  "max": null,
                  "min": null,
                  "name": "table_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Name of the multidimensional table data, either table_name or table_id must be provided, cannot be empty simultaneously.",
                    "zh_Hans": "多维表格数据表的名称，table_name 和 table_id 至少需要提供一个，不能同时为空。"
                  },
                  "label": {
                    "en_US": "table_name",
                    "zh_Hans": "table_name"
                  },
                  "llm_description": "多维表格数据表的名称，table_name 和 table_id 至少需要提供一个，不能同时为空。",
                  "max": null,
                  "min": null,
                  "name": "table_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for a view in a multidimensional table. It can be found in the URL's query parameter with the key 'view'. For example: https://svi136aogf123.feishu.cn/base/KWC8bYsYXahYqGsTtqectNn9n3e?table=tblE8a2fmBIEflaE&view=vewlkAVpRx.\n",
                    "zh_Hans": "多维表格中视图的唯一标识，可在多维表格的 URL 地址栏中找到，query 参数中 key 为 view 的部分。例如：https://svi136aogf123.feishu.cn/base/KWC8bYsYXahYqGsTtqectNn9n3e?table=tblE8a2fmBIEflaE&view=vewlkAVpRx。"
                  },
                  "label": {
                    "en_US": "view_id",
                    "zh_Hans": "视图唯一标识"
                  },
                  "llm_description": "多维表格中视图的唯一标识，可在多维表格的 URL 地址栏中找到，query 参数中 key 为 view 的部分。例如：https://svi136aogf123.feishu.cn/base/KWC8bYsYXahYqGsTtqectNn9n3e?table=tblE8a2fmBIEflaE&view=vewlkAVpRx。",
                  "max": null,
                  "min": null,
                  "name": "view_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Field names to specify which fields to include in the returned records. Example value: [\"Field1\", \"Field2\"].\n",
                    "zh_Hans": "字段名称，用于指定本次查询返回记录中包含的字段。示例值：[\"字段1\",\"字段2\"]。"
                  },
                  "label": {
                    "en_US": "field_names",
                    "zh_Hans": "字段名称"
                  },
                  "llm_description": "字段名称，用于指定本次查询返回记录中包含的字段。示例值：[\"字段1\",\"字段2\"]。",
                  "max": null,
                  "min": null,
                  "name": "field_names",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sorting conditions, for example: [{\"field_name\":\"Multiline Text\",\"desc\":true}].\n",
                    "zh_Hans": "排序条件，例如：[{\"field_name\":\"多行文本\",\"desc\":true}]。"
                  },
                  "label": {
                    "en_US": "sort",
                    "zh_Hans": "排序条件"
                  },
                  "llm_description": "排序条件，例如：[{\"field_name\":\"多行文本\",\"desc\":true}]。",
                  "max": null,
                  "min": null,
                  "name": "sort",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Object containing filter information. For details on how to fill in the filter, refer to the record filter parameter guide (https://open.larkoffice.com/document/uAjLw4CM/ukTMukTMukTM/reference/bitable-v1/app-table-record/record-filter-guide).",
                    "zh_Hans": "包含条件筛选信息的对象。了解如何填写 filter，参考记录筛选参数填写指南(https://open.larkoffice.com/document/uAjLw4CM/ukTMukTMukTM/reference/bitable-v1/app-table-record/record-filter-guide)。"
                  },
                  "label": {
                    "en_US": "filter",
                    "zh_Hans": "筛选条件"
                  },
                  "llm_description": "包含条件筛选信息的对象。了解如何填写 filter，参考记录筛选参数填写指南(https://open.larkoffice.com/document/uAjLw4CM/ukTMukTMukTM/reference/bitable-v1/app-table-record/record-filter-guide)。",
                  "max": null,
                  "min": null,
                  "name": "filter",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to return automatically calculated fields. Default is false, meaning they are not returned.",
                    "zh_Hans": "是否返回自动计算的字段。默认为 false，表示不返回。"
                  },
                  "label": {
                    "en_US": "automatic_fields",
                    "zh_Hans": "automatic_fields"
                  },
                  "llm_description": "是否返回自动计算的字段。默认为 false，表示不返回。",
                  "max": null,
                  "min": null,
                  "name": "automatic_fields",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": "open_id",
                  "form": "form",
                  "human_description": {
                    "en_US": "User ID type, optional values are open_id, union_id, user_id, with a default value of open_id.",
                    "zh_Hans": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。"
                  },
                  "label": {
                    "en_US": "user_id_type",
                    "zh_Hans": "用户 ID 类型"
                  },
                  "llm_description": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。",
                  "max": null,
                  "min": null,
                  "name": "user_id_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "open_id",
                        "zh_Hans": "open_id"
                      },
                      "value": "open_id"
                    },
                    {
                      "label": {
                        "en_US": "union_id",
                        "zh_Hans": "union_id"
                      },
                      "value": "union_id"
                    },
                    {
                      "label": {
                        "en_US": "user_id",
                        "zh_Hans": "user_id"
                      },
                      "value": "user_id"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 20,
                  "form": "form",
                  "human_description": {
                    "en_US": "Page size, default value: 20, maximum value: 500.\n",
                    "zh_Hans": "分页大小，默认值：20，最大值：500。"
                  },
                  "label": {
                    "en_US": "page_size",
                    "zh_Hans": "分页大小"
                  },
                  "llm_description": "分页大小，默认值：20，最大值：500。",
                  "max": null,
                  "min": null,
                  "name": "page_size",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Page token, leave empty for the first request to start from the beginning; a new page_token will be returned if there are more items in the paginated query results, which can be used for the next traversal. Example value: \"tblsRc9GRRXKqhvW\".\n",
                    "zh_Hans": "分页标记，第一次请求不填，表示从头开始遍历；分页查询结果还有更多项时会同时返回新的 page_token，下次遍历可采用该 page_token 获取查询结果。示例值：\"tblsRc9GRRXKqhvW\"。"
                  },
                  "label": {
                    "en_US": "page_token",
                    "zh_Hans": "分页标记"
                  },
                  "llm_description": "分页标记，第一次请求不填，表示从头开始遍历；分页查询结果还有更多项时会同时返回新的 page_token，下次遍历可采用该 page_token 获取查询结果。示例值：\"tblsRc9GRRXKqhvW\"。",
                  "max": null,
                  "min": null,
                  "name": "page_token",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Delete Multiple Records from Multidimensional Table",
                  "zh_Hans": "删除多维表格数据表中的多条记录"
                },
                "llm": "A tool for deleting multiple records from a multidimensional table. (删除多维表格数据表中的多条记录)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Delete Records",
                  "zh_Hans": "删除多条记录"
                },
                "name": "delete_records"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for the multidimensional table, supports inputting document URL.",
                    "zh_Hans": "多维表格的唯一标识符，支持输入文档 URL。"
                  },
                  "label": {
                    "en_US": "app_token",
                    "zh_Hans": "app_token"
                  },
                  "llm_description": "多维表格的唯一标识符，支持输入文档 URL。",
                  "max": null,
                  "min": null,
                  "name": "app_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for the multidimensional table data, either table_id or table_name must be provided, cannot be empty simultaneously.",
                    "zh_Hans": "多维表格数据表的唯一标识符，table_id 和 table_name 至少需要提供一个，不能同时为空。"
                  },
                  "label": {
                    "en_US": "table_id",
                    "zh_Hans": "table_id"
                  },
                  "llm_description": "多维表格数据表的唯一标识符，table_id 和 table_name 至少需要提供一个，不能同时为空。",
                  "max": null,
                  "min": null,
                  "name": "table_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Name of the multidimensional table data, either table_name or table_id must be provided, cannot be empty simultaneously.",
                    "zh_Hans": "多维表格数据表的名称，table_name 和 table_id 至少需要提供一个，不能同时为空。"
                  },
                  "label": {
                    "en_US": "table_name",
                    "zh_Hans": "table_name"
                  },
                  "llm_description": "多维表格数据表的名称，table_name 和 table_id 至少需要提供一个，不能同时为空。",
                  "max": null,
                  "min": null,
                  "name": "table_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "List of IDs for the records to be deleted, example value: [\"recwNXzPQv\"].\n",
                    "zh_Hans": "删除的多条记录 ID 列表，示例值：[\"recwNXzPQv\"]。"
                  },
                  "label": {
                    "en_US": "Record IDs",
                    "zh_Hans": "记录 ID 列表"
                  },
                  "llm_description": "删除的多条记录 ID 列表，示例值：[\"recwNXzPQv\"]。",
                  "max": null,
                  "min": null,
                  "name": "record_ids",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "open_id",
                  "form": "form",
                  "human_description": {
                    "en_US": "User ID type, optional values are open_id, union_id, user_id, with a default value of open_id.",
                    "zh_Hans": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。"
                  },
                  "label": {
                    "en_US": "user_id_type",
                    "zh_Hans": "用户 ID 类型"
                  },
                  "llm_description": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。",
                  "max": null,
                  "min": null,
                  "name": "user_id_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "open_id",
                        "zh_Hans": "open_id"
                      },
                      "value": "open_id"
                    },
                    {
                      "label": {
                        "en_US": "union_id",
                        "zh_Hans": "union_id"
                      },
                      "value": "union_id"
                    },
                    {
                      "label": {
                        "en_US": "user_id",
                        "zh_Hans": "user_id"
                      },
                      "value": "user_id"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Add a Data Table to Multidimensional Table",
                  "zh_Hans": "在多维表格中新增一个数据表"
                },
                "llm": "A tool for adding a data table to a multidimensional table. (在多维表格中新增一个数据表)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Create Table",
                  "zh_Hans": "新增数据表"
                },
                "name": "create_table"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for the multidimensional table, supports inputting document URL.",
                    "zh_Hans": "多维表格的唯一标识符，支持输入文档 URL。"
                  },
                  "label": {
                    "en_US": "app_token",
                    "zh_Hans": "app_token"
                  },
                  "llm_description": "多维表格的唯一标识符，支持输入文档 URL。",
                  "max": null,
                  "min": null,
                  "name": "app_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The name of the data table, length range: 1 character to 100 characters.\n",
                    "zh_Hans": "数据表名称，长度范围：1 字符 ～ 100 字符。"
                  },
                  "label": {
                    "en_US": "Table Name",
                    "zh_Hans": "数据表名称"
                  },
                  "llm_description": "数据表名称，长度范围：1 字符 ～ 100 字符。",
                  "max": null,
                  "min": null,
                  "name": "table_name",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The name of the default table view, defaults to \"Table\" if not filled.",
                    "zh_Hans": "默认表格视图的名称，不填则默认为\"表格\"。"
                  },
                  "label": {
                    "en_US": "Default View Name",
                    "zh_Hans": "默认表格视图的名称"
                  },
                  "llm_description": "默认表格视图的名称，不填则默认为\"表格\"。",
                  "max": null,
                  "min": null,
                  "name": "default_view_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Initial fields of the data table, format: [ { \"field_name\": \"Multi-line Text\",\"type\": 1 },{ \"field_name\": \"Number\",\"type\": 2 },{ \"field_name\": \"Single Select\",\"type\": 3 },{ \"field_name\": \"Multiple Select\",\"type\": 4 },{ \"field_name\": \"Date\",\"type\": 5 } ]. For field details, refer to: https://open.larkoffice.com/document/server-docs/docs/bitable-v1/app-table-field/guide\n",
                    "zh_Hans": "数据表的初始字段，格式为：[{\"field_name\":\"多行文本\",\"type\":1},{\"field_name\":\"数字\",\"type\":2},{\"field_name\":\"单选\",\"type\":3},{\"field_name\":\"多选\",\"type\":4},{\"field_name\":\"日期\",\"type\":5}]。字段详情参考：https://open.larkoffice.com/document/server-docs/docs/bitable-v1/app-table-field/guide"
                  },
                  "label": {
                    "en_US": "Initial Fields",
                    "zh_Hans": "初始字段"
                  },
                  "llm_description": "数据表的初始字段，格式为：[{\"field_name\":\"多行文本\",\"type\":1},{\"field_name\":\"数字\",\"type\":2},{\"field_name\":\"单选\",\"type\":3},{\"field_name\":\"多选\",\"type\":4},{\"field_name\":\"日期\",\"type\":5}]。字段详情参考：https://open.larkoffice.com/document/server-docs/docs/bitable-v1/app-table-field/guide",
                  "max": null,
                  "min": null,
                  "name": "fields",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Batch Retrieve Records from Multidimensional Table",
                  "zh_Hans": "批量获取多维表格数据表中的记录信息"
                },
                "llm": "A tool for batch retrieving records from a multidimensional table, supporting up to 100 records per call. (批量获取多维表格数据表中的记录信息，单次调用最多支持查询 100 条记录)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Read Records",
                  "zh_Hans": "批量获取记录"
                },
                "name": "read_records"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for the multidimensional table, supports inputting document URL.",
                    "zh_Hans": "多维表格的唯一标识符，支持输入文档 URL。"
                  },
                  "label": {
                    "en_US": "app_token",
                    "zh_Hans": "app_token"
                  },
                  "llm_description": "多维表格的唯一标识符，支持输入文档 URL。",
                  "max": null,
                  "min": null,
                  "name": "app_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for the multidimensional table data, either table_id or table_name must be provided, cannot be empty simultaneously.",
                    "zh_Hans": "多维表格数据表的唯一标识符，table_id 和 table_name 至少需要提供一个，不能同时为空。"
                  },
                  "label": {
                    "en_US": "table_id",
                    "zh_Hans": "table_id"
                  },
                  "llm_description": "多维表格数据表的唯一标识符，table_id 和 table_name 至少需要提供一个，不能同时为空。",
                  "max": null,
                  "min": null,
                  "name": "table_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Name of the multidimensional table data, either table_name or table_id must be provided, cannot be empty simultaneously.",
                    "zh_Hans": "多维表格数据表的名称，table_name 和 table_id 至少需要提供一个，不能同时为空。"
                  },
                  "label": {
                    "en_US": "table_name",
                    "zh_Hans": "table_name"
                  },
                  "llm_description": "多维表格数据表的名称，table_name 和 table_id 至少需要提供一个，不能同时为空。",
                  "max": null,
                  "min": null,
                  "name": "table_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "List of record IDs, which can be obtained by calling the \"Query Records API\".",
                    "zh_Hans": "记录 ID 列表，可以通过调用\"查询记录接口\"获取。"
                  },
                  "label": {
                    "en_US": "record_ids",
                    "zh_Hans": "记录 ID 列表"
                  },
                  "llm_description": "记录 ID 列表，可以通过调用\"查询记录接口\"获取。",
                  "max": null,
                  "min": null,
                  "name": "record_ids",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "open_id",
                  "form": "form",
                  "human_description": {
                    "en_US": "User ID type, optional values are open_id, union_id, user_id, with a default value of open_id.",
                    "zh_Hans": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。"
                  },
                  "label": {
                    "en_US": "user_id_type",
                    "zh_Hans": "用户 ID 类型"
                  },
                  "llm_description": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。",
                  "max": null,
                  "min": null,
                  "name": "user_id_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "open_id",
                        "zh_Hans": "open_id"
                      },
                      "value": "open_id"
                    },
                    {
                      "label": {
                        "en_US": "union_id",
                        "zh_Hans": "union_id"
                      },
                      "value": "union_id"
                    },
                    {
                      "label": {
                        "en_US": "user_id",
                        "zh_Hans": "user_id"
                      },
                      "value": "user_id"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get Metadata Information of Specified Multidimensional Table",
                  "zh_Hans": "获取指定多维表格的元数据信息"
                },
                "llm": "A tool for getting metadata information of a specified multidimensional table. (获取指定多维表格的元数据信息)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Get Base Info",
                  "zh_Hans": "获取多维表格元数据"
                },
                "name": "get_base_info"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for the multidimensional table, supports inputting document URL.",
                    "zh_Hans": "多维表格的唯一标识符，支持输入文档 URL。"
                  },
                  "label": {
                    "en_US": "app_token",
                    "zh_Hans": "app_token"
                  },
                  "llm_description": "多维表格的唯一标识符，支持输入文档 URL。",
                  "max": null,
                  "min": null,
                  "name": "app_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Update Multiple Records in Multidimensional Table",
                  "zh_Hans": "更新多维表格数据表中的多条记录"
                },
                "llm": "A tool for updating multiple records in a multidimensional table. (更新多维表格数据表中的多条记录)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Update Records",
                  "zh_Hans": "更新多条记录"
                },
                "name": "update_records"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for the multidimensional table, supports inputting document URL.",
                    "zh_Hans": "多维表格的唯一标识符，支持输入文档 URL。"
                  },
                  "label": {
                    "en_US": "app_token",
                    "zh_Hans": "app_token"
                  },
                  "llm_description": "多维表格的唯一标识符，支持输入文档 URL。",
                  "max": null,
                  "min": null,
                  "name": "app_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for the multidimensional table data, either table_id or table_name must be provided, cannot be empty simultaneously.",
                    "zh_Hans": "多维表格数据表的唯一标识符，table_id 和 table_name 至少需要提供一个，不能同时为空。"
                  },
                  "label": {
                    "en_US": "table_id",
                    "zh_Hans": "table_id"
                  },
                  "llm_description": "多维表格数据表的唯一标识符，table_id 和 table_name 至少需要提供一个，不能同时为空。",
                  "max": null,
                  "min": null,
                  "name": "table_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Name of the multidimensional table data, either table_name or table_id must be provided, cannot be empty simultaneously.",
                    "zh_Hans": "多维表格数据表的名称，table_name 和 table_id 至少需要提供一个，不能同时为空。"
                  },
                  "label": {
                    "en_US": "table_name",
                    "zh_Hans": "table_name"
                  },
                  "llm_description": "多维表格数据表的名称，table_name 和 table_id 至少需要提供一个，不能同时为空。",
                  "max": null,
                  "min": null,
                  "name": "table_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "List of records to be updated in this request. Example value: [{\"fields\":{\"multi-line-text\":\"text content\",\"single_select\":\"option 1\",\"date\":1674206443000},\"record_id\":\"recupK4f4RM5RX\"}].\nFor supported field types, refer to the integration guide (https://open.larkoffice.com/document/server-docs/docs/bitable-v1/notification). For data structures of different field types, refer to the data structure overview (https://open.larkoffice.com/document/server-docs/docs/bitable-v1/bitable-structure).\n",
                    "zh_Hans": "本次请求将要更新的记录列表，示例值：[{\"fields\":{\"多行文本\":\"文本内容\",\"单选\":\"选项 1\",\"日期\":1674206443000},\"record_id\":\"recupK4f4RM5RX\"}]。\n当前接口支持的字段类型请参考接入指南(https://open.larkoffice.com/document/server-docs/docs/bitable-v1/notification)，不同类型字段的数据结构请参考数据结构概述(https://open.larkoffice.com/document/server-docs/docs/bitable-v1/bitable-structure)。\n"
                  },
                  "label": {
                    "en_US": "records",
                    "zh_Hans": "记录列表"
                  },
                  "llm_description": "本次请求将要更新的记录列表，示例值：[{\"fields\":{\"多行文本\":\"文本内容\",\"单选\":\"选项 1\",\"日期\":1674206443000},\"record_id\":\"recupK4f4RM5RX\"}]。\n当前接口支持的字段类型请参考接入指南(https://open.larkoffice.com/document/server-docs/docs/bitable-v1/notification)，不同类型字段的数据结构请参考数据结构概述(https://open.larkoffice.com/document/server-docs/docs/bitable-v1/bitable-structure)。\n",
                  "max": null,
                  "min": null,
                  "name": "records",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "open_id",
                  "form": "form",
                  "human_description": {
                    "en_US": "User ID type, optional values are open_id, union_id, user_id, with a default value of open_id.",
                    "zh_Hans": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。"
                  },
                  "label": {
                    "en_US": "user_id_type",
                    "zh_Hans": "用户 ID 类型"
                  },
                  "llm_description": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。",
                  "max": null,
                  "min": null,
                  "name": "user_id_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "open_id",
                        "zh_Hans": "open_id"
                      },
                      "value": "open_id"
                    },
                    {
                      "label": {
                        "en_US": "union_id",
                        "zh_Hans": "union_id"
                      },
                      "value": "union_id"
                    },
                    {
                      "label": {
                        "en_US": "user_id",
                        "zh_Hans": "user_id"
                      },
                      "value": "user_id"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-26T09:32:11Z",
        "version_updated_at": "2025-02-26T09:32:11Z"
      },
      {
        "agent_strategy": {},
        "badges": [
          "partner"
        ],
        "brief": {
          "en_US": "TTS tools provided by Fish Audio.",
          "zh_Hans": "Fish Audio 提供的 TTS 工具。"
        },
        "category": "tool",
        "created_at": "2025-01-09T12:03:05Z",
        "endpoint": {},
        "icon": "langgenius/packages/fish_audio_tool/_assets/fishaudio.jpeg",
        "index_id": "langgenius___fish_audio_tool",
        "install_count": 1872,
        "introduction": "## Overview\n\n**Fish Audio** is an advanced text-to-speech (TTS) tool powered by the Fish Audio API. It enables you to convert text into high-quality speech, offering customizable voice options for various use cases. Whether building virtual assistants, creating audiobooks, or generating voiceovers, Fish Audio provides reliable and efficient TTS functionality to enhance your applications.\n\n## Configuration\n\nTo get started with Fish Audio, follow these steps:\n\n1. **Install Fish Audio Tool**\nGo to the Plugin Marketplace and install the Fish Audio tool to integrate its TTS functionality into your applications.\n\n2. **Apply for Fish Audio API Key**\nVisit the [Fish Audio API Keys](https://fish.audio/zh-CN/go-api/api-keys) page to generate an API Key. Make sure your account has the necessary permissions to access the TTS service.\n\n3. **Authorize Fish Audio**\nNavigate to **Tools > Fish Audio > To Authorize** your application and enter the API Key to activate the tool.\n\n![](./_assets/fishaudio-01.png)\n\n## Tool Features\n\nThe Fish Audio tool provides one primary action: **TTS (Text-to-Speech)**.\n\n### TTS\n\nConverts text into speech using the Fish Audio API. To use the TTS action, you need to provide the following parameters:\n\n* **Text**: The text content you want to convert into speech.\n* **Voice ID**: The unique voice identifier to be used for generating speech. Fish Audio supports multiple voice options, allowing for customization.\n\n<img src=\"./_assets/fishaudio-02.png\" width=\"400\" />\n\n## Usage\n\nFish Audio can seamlessly integrate **Chatflow / Workflow Apps** and **Agent Apps**.\n\n### Chatflow / Workflow Apps\n\n1. Add the Fish Audio TTS node to your Chatflow or Workflow pipeline.\n2. Configure the node by providing the text content and selecting the Voice ID.\n3. When the pipeline runs, the TTS action generates speech audio, which can be played or used as part of the workflow output.\n\n![](./_assets/fishaudio-03.png)\n\n### Agent Apps\n\n1. Add the Fish Audio TTS tool to your Agent application.\n2. During interactions, send the text content through the chat interface.\n3. The TTS tool will convert the text into speech and return the generated audio to the user.\n\n![](./_assets/fishaudio-04.png)\n",
        "label": {
          "en_US": "Fish Audio Tool"
        },
        "latest_package_identifier": "langgenius/fish_audio_tool:0.0.6@dd6b3a3bdbf7e60dc0ea83274b4f00489797171f3ddb07b979db8f4423ab08ca",
        "latest_version": "0.0.6",
        "model": {},
        "name": "fish_audio_tool",
        "org": "langgenius",
        "plugin_id": "langgenius/fish_audio_tool",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/fishaudio.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "utilities"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "Fish Audio api key",
                "pt_BR": "Fish Audio api key",
                "zh_Hans": "Fish Audio api key"
              },
              "name": "api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Fish Audio api key",
                "pt_BR": "Please input your Fish Audio api key",
                "zh_Hans": "请输入你的 Fish Audio api key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://fish.audio/zh-CN/go-api/api-keys"
            },
            {
              "default": "https://api.fish.audio",
              "helper": null,
              "label": {
                "en_US": "Fish Audio endpoint",
                "pt_BR": "Fish Audio endpoint",
                "zh_Hans": "Fish Audio endpoint"
              },
              "name": "api_base",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Fish Audio endpoint",
                "pt_BR": "Please input your Fish Audio endpoint",
                "zh_Hans": "请输入你的 Fish Audio 端点"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": "normal",
              "helper": null,
              "label": {
                "en_US": "Fish Audio balance mode",
                "pt_BR": "Fishaio balance mode",
                "zh_Hans": "Fish Audio 平衡模式"
              },
              "name": "latency",
              "options": [
                {
                  "label": {
                    "en_US": "normal",
                    "zh_Hans": "normal"
                  },
                  "value": "normal"
                },
                {
                  "label": {
                    "en_US": "balance",
                    "zh_Hans": "balance"
                  },
                  "value": "balance"
                }
              ],
              "placeholder": {
                "en_US": "Please input your Fish Audio balance mode",
                "pt_BR": "Please input your Fish Audio balance mode",
                "zh_Hans": "请输入你的 Fish Audio 平衡模式"
              },
              "required": true,
              "scope": null,
              "type": "select",
              "url": null
            }
          ],
          "identity": {
            "author": "langgenius",
            "description": {
              "en_US": "TTS tools provided by Fish Audio.",
              "pt_BR": "TTS tools provided by Fish Audio.",
              "zh_Hans": "Fish Audio 提供的 TTS 工具。"
            },
            "icon": "fishaudio.jpeg",
            "label": {
              "en_US": "Fish Audio Tool",
              "pt_BR": "Fish Audio Tool",
              "zh_Hans": "Fish Audio Tool"
            },
            "name": "fishaudio",
            "tags": [
              "utilities"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A text-to-speech tool using the Fish Audio API",
                  "pt_BR": "A text-to-speech tool using the Fish Audio API",
                  "zh_Hans": "一个使用 Fish Audio API 将文本转换为语音的工具"
                },
                "llm": "A text-to-speech tool using the Fish Audio API"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "TTS",
                  "pt_BR": "TTS",
                  "zh_Hans": "文本转语音"
                },
                "name": "tts"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "text content",
                    "pt_BR": "text content",
                    "zh_Hans": "文本内容"
                  },
                  "label": {
                    "en_US": "Text",
                    "pt_BR": "text",
                    "zh_Hans": "内容"
                  },
                  "llm_description": "text content",
                  "max": null,
                  "min": null,
                  "name": "content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Fish Audio voice id",
                    "pt_BR": "Fish Audio voice id",
                    "zh_Hans": "Fish Audio 的声音 ID"
                  },
                  "label": {
                    "en_US": "voice id",
                    "pt_BR": "text",
                    "zh_Hans": "声音 ID"
                  },
                  "llm_description": "Fish Audio voice id",
                  "max": null,
                  "min": null,
                  "name": "voice_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "wav",
                  "form": "form",
                  "human_description": {
                    "en_US": "audio format",
                    "pt_BR": "audio format",
                    "zh_Hans": "声音格式"
                  },
                  "label": {
                    "en_US": "format",
                    "zh_Hans": "类型"
                  },
                  "llm_description": "audio format",
                  "max": null,
                  "min": null,
                  "name": "format",
                  "options": [
                    {
                      "label": {
                        "en_US": "mp3",
                        "zh_Hans": "mp3"
                      },
                      "value": "mp3"
                    },
                    {
                      "label": {
                        "en_US": "wav",
                        "zh_Hans": "wav"
                      },
                      "value": "wav"
                    },
                    {
                      "label": {
                        "en_US": "pcm",
                        "zh_Hans": "pcm"
                      },
                      "value": "pcm"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-25T07:31:53Z",
        "version_updated_at": "2025-02-17T07:05:16Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Azure DALL-E art",
          "pt_BR": "Azure DALL-E art",
          "zh_Hans": "Azure DALL-E 绘画"
        },
        "category": "tool",
        "created_at": "2024-12-04T04:39:45Z",
        "endpoint": {},
        "icon": "langgenius/packages/azuredalle/_assets/icon.png",
        "index_id": "langgenius___azuredalle",
        "install_count": 1850,
        "introduction": "# Azure DALL-E\n\n## Overview\n\nAzure DALL-E is a service that provides access to advanced AI models for image generation. It allows developers and users to create images from textual descriptions, utilizing a powerful text-to-image model. The service offers features for image variations, inpainting, and outpainting, enabling diverse creative applications.\n\n## Configuration\n\n### 1. Apply for Azure DALL-E Account\nPlease follow [Azure instruction](https://learn.microsoft.com/en-us/azure/ai-services/openai/dall-e-quickstart?tabs=dalle3%2Ccommand-line%2Ckeyless%2Cjavascript-keyless%2Ctypescript-keyless&pivots=programming-language-studio) to sign in an Azure account, and to get API key, Deployment Name, etc.\n\n### 2. Get Azure DALL-E tools from Plugin Marketplace\nThe Azure DALL-E tools could be found at the Plugin Marketplace, please install it.\n\n### 3. Fill in the configuration in Dify\nOn the Dify navigation page, click `Tools > Azure DALL-E > To Authorize` and fill the API Key.\n\n![](./_assets/azureD_1.png)\n\n### 4. Use Tool\nYou can use the Azure DALL-E tool in the following application types.\n\n![](./_assets/azureD_2.png)\n\n#### Chatflow / Workflow applications\nBoth Chatflow and Workflow applications support adding a Azure DALL-E tool node for data processing tasks.\n\n#### Agent applications\nAdd the Azure DALL-E tool in the Agent application, then enter data processing commands to call this tool.",
        "label": {
          "en_US": "Azure DALL-E",
          "pt_BR": "Azure DALL-E",
          "zh_Hans": "Azure DALL-E 绘画"
        },
        "latest_package_identifier": "langgenius/azuredalle:0.0.3@be0f1462517bff2bfafa56996d7d138056739259b9fd56f2070364c9b8d8fd73",
        "latest_version": "0.0.3",
        "model": {},
        "name": "azuredalle",
        "org": "langgenius",
        "plugin_id": "langgenius/azuredalle",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/azuredalle.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "image"
          },
          {
            "name": "productivity"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Please input your Azure OpenAI API key",
                "pt_BR": "Introduza a sua chave de API OpenAI do Azure",
                "zh_Hans": "请输入你的 Azure OpenAI API key"
              },
              "label": {
                "en_US": "API key",
                "pt_BR": "API key",
                "zh_Hans": "密钥"
              },
              "name": "azure_openai_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Azure OpenAI API key",
                "pt_BR": "Introduza a sua chave de API OpenAI do Azure",
                "zh_Hans": "请输入你的 Azure OpenAI API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "help": {
                "en_US": "Please input the name of your Azure Openai DALL-E API deployment",
                "pt_BR": "Insira o nome da implantação da API DALL-E do Azure Openai",
                "zh_Hans": "请输入你的 Azure Openai DALL-E API 部署名称"
              },
              "label": {
                "en_US": "Deployment Name",
                "pt_BR": "Nome da Implantação",
                "zh_Hans": "部署名称"
              },
              "name": "azure_openai_api_model_name",
              "options": null,
              "placeholder": {
                "en_US": "Please input the name of your Azure Openai DALL-E API deployment",
                "pt_BR": "Insira o nome da implantação da API DALL-E do Azure Openai",
                "zh_Hans": "请输入你的 Azure Openai DALL-E API 部署名称"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "help": {
                "en_US": "Please input your Azure OpenAI API Version,e.g. 2023-12-01-preview",
                "pt_BR": "Introduza a versão da API OpenAI do Azure,e.g. 2023-12-01-preview",
                "zh_Hans": "请输入你的 Azure OpenAI API 版本，例如：2023-12-01-preview"
              },
              "label": {
                "en_US": "API Version",
                "pt_BR": "API Version",
                "zh_Hans": "API 版本"
              },
              "name": "azure_openai_api_version",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Azure OpenAI API Version,e.g. 2023-12-01-preview",
                "pt_BR": "Introduza a versão da API OpenAI do Azure,e.g. 2023-12-01-preview",
                "zh_Hans": "请输入你的 Azure OpenAI API 版本，例如：2023-12-01-preview"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "help": {
                "en_US": "Please input your Azure OpenAI Endpoint URL, e.g. https://xxx.openai.azure.com/",
                "pt_BR": "Introduza a URL do Azure OpenAI Endpoint, e.g. https://xxx.openai.azure.com/",
                "zh_Hans": "请输入你的 Azure OpenAI API域名，例如：https://xxx.openai.azure.com/"
              },
              "label": {
                "en_US": "API Endpoint URL",
                "pt_BR": "API Endpoint URL",
                "zh_Hans": "API 域名"
              },
              "name": "azure_openai_base_url",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Azure OpenAI Endpoint URL, e.g. https://xxx.openai.azure.com/",
                "pt_BR": "Introduza a URL do Azure OpenAI Endpoint, e.g. https://xxx.openai.azure.com/",
                "zh_Hans": "请输入你的 Azure OpenAI API域名，例如：https://xxx.openai.azure.com/"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            }
          ],
          "identity": {
            "author": "Leslie",
            "description": {
              "en_US": "Azure DALL-E art",
              "pt_BR": "Azure DALL-E art",
              "zh_Hans": "Azure DALL-E 绘画"
            },
            "icon": "icon.png",
            "label": {
              "en_US": "Azure DALL-E",
              "pt_BR": "Azure DALL-E",
              "zh_Hans": "Azure DALL-E 绘画"
            },
            "name": "azuredalle",
            "tags": [
              "image",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "DALL-E is a text to image tool",
                  "pt_BR": "DALL-E é uma ferramenta de texto para imagem",
                  "zh_Hans": "DALL-E 是一个文本到图像的工具"
                },
                "llm": "DALL-E is a tool used to generate images from text"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Leslie",
                "label": {
                  "en_US": "Azure DALL-E 3",
                  "pt_BR": "Azure DALL-E 3",
                  "zh_Hans": "Azure DALL-E 3 绘画"
                },
                "name": "azure_dalle3"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Image prompt, you can check the official documentation of DallE 3",
                    "pt_BR": "Imagem prompt, você pode verificar a documentação oficial do DallE 3",
                    "zh_Hans": "图像提示词，您可以查看 DallE 3 的官方文档"
                  },
                  "label": {
                    "en_US": "Prompt",
                    "pt_BR": "Prompt",
                    "zh_Hans": "提示词"
                  },
                  "llm_description": "Image prompt of DallE 3, you should describe the image you want to generate as a list of words as possible as detailed",
                  "max": null,
                  "min": null,
                  "name": "prompt",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Image generation seed ID to ensure consistency of series generated images",
                    "pt_BR": "ID de semente de geração de imagem para garantir a consistência das imagens geradas em série",
                    "zh_Hans": "图像生成种子ID，确保系列生成图像的一致性"
                  },
                  "label": {
                    "en_US": "Seed ID",
                    "pt_BR": "ID da semente",
                    "zh_Hans": "种子ID"
                  },
                  "llm_description": "If the user requests image consistency, extract the seed ID from the user's question or context.The seed id consists of an 8-bit string containing uppercase and lowercase letters and numbers",
                  "max": null,
                  "min": null,
                  "name": "seed_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "square",
                  "form": "form",
                  "human_description": {
                    "en_US": "selecting the image size",
                    "pt_BR": "seleccionar o tamanho da imagem",
                    "zh_Hans": "选择图像大小"
                  },
                  "label": {
                    "en_US": "Image size",
                    "pt_BR": "Tamanho da imagem",
                    "zh_Hans": "图像大小"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "size",
                  "options": [
                    {
                      "label": {
                        "en_US": "Squre(1024x1024)",
                        "pt_BR": "Squire(1024x1024)",
                        "zh_Hans": "方(1024x1024)"
                      },
                      "value": "square"
                    },
                    {
                      "label": {
                        "en_US": "Vertical(1024x1792)",
                        "pt_BR": "Vertical(1024x1792)",
                        "zh_Hans": "竖屏(1024x1792)"
                      },
                      "value": "vertical"
                    },
                    {
                      "label": {
                        "en_US": "Horizontal(1792x1024)",
                        "pt_BR": "Horizontal(1792x1024)",
                        "zh_Hans": "横屏(1792x1024)"
                      },
                      "value": "horizontal"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 1,
                  "form": "form",
                  "human_description": {
                    "en_US": "selecting the number of images",
                    "pt_BR": "seleccionar o número de imagens",
                    "zh_Hans": "选择图像数量"
                  },
                  "label": {
                    "en_US": "Number of images",
                    "pt_BR": "Número de imagens",
                    "zh_Hans": "图像数量"
                  },
                  "llm_description": "",
                  "max": 1,
                  "min": 1,
                  "name": "n",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "standard",
                  "form": "form",
                  "human_description": {
                    "en_US": "selecting the image quality",
                    "pt_BR": "seleccionar a qualidade da imagem",
                    "zh_Hans": "选择图像质量"
                  },
                  "label": {
                    "en_US": "Image quality",
                    "pt_BR": "Qualidade da imagem",
                    "zh_Hans": "图像质量"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "quality",
                  "options": [
                    {
                      "label": {
                        "en_US": "Standard",
                        "pt_BR": "Normal",
                        "zh_Hans": "标准"
                      },
                      "value": "standard"
                    },
                    {
                      "label": {
                        "en_US": "HD",
                        "pt_BR": "HD",
                        "zh_Hans": "高清"
                      },
                      "value": "hd"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "vivid",
                  "form": "form",
                  "human_description": {
                    "en_US": "selecting the image style",
                    "pt_BR": "seleccionar o estilo da imagem",
                    "zh_Hans": "选择图像风格"
                  },
                  "label": {
                    "en_US": "Image style",
                    "pt_BR": "Estilo da imagem",
                    "zh_Hans": "图像风格"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "style",
                  "options": [
                    {
                      "label": {
                        "en_US": "Vivid",
                        "pt_BR": "Vívido",
                        "zh_Hans": "生动"
                      },
                      "value": "vivid"
                    },
                    {
                      "label": {
                        "en_US": "Natural",
                        "pt_BR": "Natural",
                        "zh_Hans": "自然"
                      },
                      "value": "natural"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-26T03:21:37Z",
        "version_updated_at": "2025-03-26T03:21:37Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Execute commands on remote servers via SSH using password or key-based authentication.",
          "ja_JP": "パスワードまたは鍵ベースの認証を使用して、SSHを介してリモートサーバーでコマンドを実行します。",
          "pt_BR": "Execute comandos em servidores remotos via SSH usando autenticação por senha ou chave.",
          "zh_Hans": "通过SSH使用密码或密钥认证在远程服务器上执行命令。"
        },
        "category": "tool",
        "created_at": "2025-03-12T10:26:22Z",
        "endpoint": {},
        "icon": "stvlynn/packages/ssh/_assets/icon.svg",
        "index_id": "stvlynn___ssh",
        "install_count": 1849,
        "introduction": "# SSH Command Execution Plugin\n\n**Author:** [Steven Lynn](https://github.com/stvlynn)\n**Version:** 0.0.1\n**Type:** tool\n\n## Description\n\nThe SSH Command Execution Plugin allows users to execute commands on remote servers via SSH protocol. It supports both password and private key authentication methods.\n![](./_assets/image.png)\n\n> Don't know where to start? Try this [DSL Template](https://raw.githubusercontent.com/stvlynn/SSH-Dify-Plugin/refs/heads/main/example.yml) !\n\n## Features\n\n- Supports password and private key authentication\n- Executes remote commands and returns standard output and standard error\n- Securely handles connection and authentication errors\n\n## Parameters\n\n| Parameter | Type | Required | Description |\n|-----------|------|----------|-------------|\n| host | string | Yes | Hostname or IP address of the remote server |\n| port | number | Yes | SSH port, default is 22 |\n| username | string | Yes | Username for authentication |\n| auth_type | select | Yes | Authentication type: password or key |\n| password | string | Conditional | Password for password authentication (required if auth_type is password) |\n| private_key | string | Conditional | Private key content for key authentication (required if auth_type is key) |\n| passphrase | string | No | Passphrase for the private key (if the key is encrypted) |\n| command | string | Yes | Command to execute on the remote server |\n\n## Safety Tip\n\nKeep your instance IP and password safe in **Environment Varriable -> secret**!\n\n![](./_assets/environment.png)\n\n## Input and Output Example\n\n### Input:\n```json\n{\n  \"private_key\": \"\",\n  \"passphrase\": \"\",\n  \"host\": \"192.************1\",\n  \"port\": \"22\",\n  \"username\": \"root\",\n  \"auth_type\": \"password\",\n  \"password\": \"T************87\",\n  \"command\": \"neofetch\"\n}\n```\n\n### Output:\n```json\n{\n  \"text\": \"\",\n  \"files\": [],\n  \"json\": [\n    {\n      \"stderr\": \"\",\n      \"stdout\": \"***some output***\",\n      \"success\": true\n    }\n  ]\n}\n```\n\n## Security Considerations\n\n- Ensure you have permission to access the target server\n- Sensitive information such as private keys and passwords should be kept secure\n- Follow the principle of least privilege, granting only necessary execution permissions\n\n## License\n\n[MIT](./LICENSE)\n\n\n\n",
        "label": {
          "en_US": "SSH Command Execution",
          "ja_JP": "SSHコマンド実行",
          "pt_BR": "Execução de Comando SSH",
          "zh_Hans": "SSH命令执行"
        },
        "latest_package_identifier": "stvlynn/ssh:0.0.1@d2766ba5e973307c812902bea58def8cb1bef7220dab0c6887dc1d74df5b8c6e",
        "latest_version": "0.0.1",
        "model": {},
        "name": "ssh",
        "org": "stvlynn",
        "plugin_id": "stvlynn/ssh",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/ssh.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {}
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "stvlynn",
            "description": {
              "en_US": "ssh",
              "pt_BR": "ssh",
              "zh_Hans": "ssh"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "ssh",
              "pt_BR": "ssh",
              "zh_Hans": "ssh"
            },
            "name": "ssh",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Execute commands on remote servers via SSH",
                  "pt_BR": "Execute comandos em servidores remotos via SSH",
                  "zh_Hans": "通过SSH在远程服务器上执行命令"
                },
                "llm": "A tool to execute commands on remote servers via SSH using either password or key-based authentication."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "stvlynn",
                "label": {
                  "en_US": "SSH Command Execution",
                  "pt_BR": "Execução de Comando SSH",
                  "zh_Hans": "SSH命令执行"
                },
                "name": "ssh"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The hostname or IP address of the remote server",
                    "pt_BR": "O nome do host ou endereço IP do servidor remoto",
                    "zh_Hans": "远程服务器的主机名或IP地址"
                  },
                  "label": {
                    "en_US": "Host",
                    "pt_BR": "Host",
                    "zh_Hans": "主机"
                  },
                  "llm_description": "The hostname or IP address of the remote server to connect to via SSH.",
                  "max": null,
                  "min": null,
                  "name": "host",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The SSH port of the remote server (default 22)",
                    "pt_BR": "A porta SSH do servidor remoto (padrão 22)",
                    "zh_Hans": "远程服务器的SSH端口（默认22）"
                  },
                  "label": {
                    "en_US": "Port",
                    "pt_BR": "Porta",
                    "zh_Hans": "端口"
                  },
                  "llm_description": "The SSH port of the remote server. Default is 22.",
                  "max": null,
                  "min": null,
                  "name": "port",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The username to authenticate with",
                    "pt_BR": "O nome de usuário para autenticação",
                    "zh_Hans": "用于认证的用户名"
                  },
                  "label": {
                    "en_US": "Username",
                    "pt_BR": "Nome de usuário",
                    "zh_Hans": "用户名"
                  },
                  "llm_description": "The username to authenticate with on the remote server.",
                  "max": null,
                  "min": null,
                  "name": "username",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "password",
                  "form": "form",
                  "human_description": {
                    "en_US": "Choose between password or private key authentication",
                    "pt_BR": "Escolha entre autenticação por senha ou chave privada",
                    "zh_Hans": "选择密码或私钥认证"
                  },
                  "label": {
                    "en_US": "Authentication Type",
                    "pt_BR": "Tipo de Autenticação",
                    "zh_Hans": "认证类型"
                  },
                  "llm_description": "The authentication method to use (password or private key).",
                  "max": null,
                  "min": null,
                  "name": "auth_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "Password",
                        "pt_BR": "Senha",
                        "zh_Hans": "密码"
                      },
                      "value": "password"
                    },
                    {
                      "label": {
                        "en_US": "Private Key",
                        "pt_BR": "Chave Privada",
                        "zh_Hans": "私钥"
                      },
                      "value": "key"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The password for password authentication (required if auth_type is password)",
                    "pt_BR": "A senha para autenticação por senha (obrigatório se o tipo de autenticação for senha)",
                    "zh_Hans": "用于密码认证的密码（如果认证类型为密码则必填）"
                  },
                  "label": {
                    "en_US": "Password",
                    "pt_BR": "Senha",
                    "zh_Hans": "密码"
                  },
                  "llm_description": "The password for password authentication. Required if auth_type is password.",
                  "max": null,
                  "min": null,
                  "name": "password",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The private key for key authentication (required if auth_type is key)",
                    "pt_BR": "A chave privada para autenticação por chave (obrigatório se o tipo de autenticação for chave)",
                    "zh_Hans": "用于密钥认证的私钥（如果认证类型为私钥则必填）"
                  },
                  "label": {
                    "en_US": "Private Key",
                    "pt_BR": "Chave Privada",
                    "zh_Hans": "私钥"
                  },
                  "llm_description": "The private key content for key-based authentication. Required if auth_type is key.",
                  "max": null,
                  "min": null,
                  "name": "private_key",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The passphrase for the private key (if the key is encrypted)",
                    "pt_BR": "A frase-senha para a chave privada (se a chave estiver criptografada)",
                    "zh_Hans": "私钥的密码（如果私钥已加密）"
                  },
                  "label": {
                    "en_US": "Passphrase",
                    "pt_BR": "Frase-senha",
                    "zh_Hans": "密钥口令"
                  },
                  "llm_description": "The passphrase for the private key if it is encrypted. Optional.",
                  "max": null,
                  "min": null,
                  "name": "passphrase",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The command to execute on the remote server",
                    "pt_BR": "O comando a ser executado no servidor remoto",
                    "zh_Hans": "在远程服务器上执行的命令"
                  },
                  "label": {
                    "en_US": "Command",
                    "pt_BR": "Comando",
                    "zh_Hans": "命令"
                  },
                  "llm_description": "The command to execute on the remote server.",
                  "max": null,
                  "min": null,
                  "name": "command",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-12T10:26:33Z",
        "version_updated_at": "2025-03-12T10:26:33Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Feishu Spreadsheet, requires the following permissions: sheets:spreadsheet.\n",
          "zh_Hans": "飞书电子表格，需要开通以下权限: sheets:spreadsheet。\n"
        },
        "category": "tool",
        "created_at": "2025-02-26T10:44:28Z",
        "endpoint": {},
        "icon": "langgenius/packages/feishu_spreadsheet/_assets/icon.png",
        "index_id": "langgenius___feishu_spreadsheet",
        "install_count": 1789,
        "introduction": "",
        "label": {
          "en_US": "Feishu Spreadsheet",
          "zh_Hans": "飞书电子表格"
        },
        "latest_package_identifier": "langgenius/feishu_spreadsheet:0.0.1@6b4da2c3bcab1aace954e92a8120bf09692951bc68c993debbd64cfb398fd30d",
        "latest_version": "0.0.1",
        "model": {},
        "name": "feishu_spreadsheet",
        "org": "langgenius",
        "plugin_id": "langgenius/feishu_spreadsheet",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/feishu_spreadsheet.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "social"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "APP ID"
              },
              "name": "app_id",
              "options": null,
              "placeholder": {
                "en_US": "Please input your feishu app id",
                "zh_Hans": "请输入你的飞书 app id"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": "https://open.larkoffice.com/app"
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "APP Secret"
              },
              "name": "app_secret",
              "options": null,
              "placeholder": {
                "en_US": "Please input your app secret",
                "zh_Hans": "请输入你的飞书 app secret"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            }
          ],
          "identity": {
            "author": "Doug Lea",
            "description": {
              "en_US": "Feishu Spreadsheet, requires the following permissions: sheets:spreadsheet.\n",
              "zh_Hans": "飞书电子表格，需要开通以下权限: sheets:spreadsheet。\n"
            },
            "icon": "icon.png",
            "label": {
              "en_US": "Feishu Spreadsheet",
              "zh_Hans": "飞书电子表格"
            },
            "name": "feishu_spreadsheet",
            "tags": [
              "social",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Create Spreadsheet",
                  "zh_Hans": "创建电子表格"
                },
                "llm": "A tool for creating spreadsheets. (创建电子表格)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Create Spreadsheet",
                  "zh_Hans": "创建电子表格"
                },
                "name": "create_spreadsheet"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The title of the spreadsheet",
                    "zh_Hans": "电子表格的标题"
                  },
                  "label": {
                    "en_US": "Spreadsheet Title",
                    "zh_Hans": "电子表格标题"
                  },
                  "llm_description": "电子表格的标题",
                  "max": null,
                  "min": null,
                  "name": "title",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The token of the folder, supports folder URL input, e.g., https://bytedance.larkoffice.com/drive/folder/CxHEf4DCSlNkL2dUTCJcPRgentg",
                    "zh_Hans": "文件夹 token，支持文件夹 URL 输入，如：https://bytedance.larkoffice.com/drive/folder/CxHEf4DCSlNkL2dUTCJcPRgentg"
                  },
                  "label": {
                    "en_US": "Folder Token",
                    "zh_Hans": "文件夹 token"
                  },
                  "llm_description": "文件夹 token，支持文件夹 URL 输入，如：https://bytedance.larkoffice.com/drive/folder/CxHEf4DCSlNkL2dUTCJcPRgentg",
                  "max": null,
                  "min": null,
                  "name": "folder_token",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Add Rows",
                  "zh_Hans": "新增多行至工作表最后"
                },
                "llm": "A tool for adding multiple rows to the end of a spreadsheet. (新增多行至工作表最后)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Add Rows",
                  "zh_Hans": "新增多行至工作表最后"
                },
                "name": "add_rows"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Spreadsheet token, supports input of spreadsheet URL.",
                    "zh_Hans": "电子表格 token，支持输入电子表格 url。"
                  },
                  "label": {
                    "en_US": "spreadsheet_token",
                    "zh_Hans": "电子表格 token"
                  },
                  "llm_description": "电子表格 token，支持输入电子表格 url。",
                  "max": null,
                  "min": null,
                  "name": "spreadsheet_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet ID, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表 ID，与 sheet_name 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_id",
                    "zh_Hans": "工作表 ID"
                  },
                  "llm_description": "工作表 ID，与 sheet_name 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet name, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表名称，与 sheet_id 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_name",
                    "zh_Hans": "工作表名称"
                  },
                  "llm_description": "工作表名称，与 sheet_id 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Number of rows to add, range (0-5000].",
                    "zh_Hans": "要增加行数，范围(0-5000]。"
                  },
                  "label": {
                    "en_US": "length",
                    "zh_Hans": "要增加行数"
                  },
                  "llm_description": "要增加行数，范围(0-5000]。",
                  "max": null,
                  "min": null,
                  "name": "length",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Content of the new rows, array of objects in string format, each array represents a row of table data, format like: [ [ \"ID\",\"Name\",\"Age\" ],[ 1,\"Zhang San\",10 ],[ 2,\"Li Si\",11 ] ].\n",
                    "zh_Hans": "新增行的表格内容，数组对象字符串，每个数组一行表格数据，格式,如：[[\"编号\",\"姓名\",\"年龄\"],[1,\"张三\",10],[2,\"李四\",11]]。"
                  },
                  "label": {
                    "en_US": "values",
                    "zh_Hans": "新增行的表格内容"
                  },
                  "llm_description": "新增行的表格内容，数组对象字符串，每个数组一行表格数据，格式,如：[[\"编号\",\"姓名\",\"年龄\"],[1,\"张三\",10],[2,\"李四\",11]]。",
                  "max": null,
                  "min": null,
                  "name": "values",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Read Rows",
                  "zh_Hans": "读取工作表行数据"
                },
                "llm": "A tool for reading row data from a spreadsheet. (读取工作表行数据)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Read Rows",
                  "zh_Hans": "读取工作表行数据"
                },
                "name": "read_rows"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Spreadsheet token, supports input of spreadsheet URL.",
                    "zh_Hans": "电子表格 token，支持输入电子表格 url。"
                  },
                  "label": {
                    "en_US": "spreadsheet_token",
                    "zh_Hans": "电子表格 token"
                  },
                  "llm_description": "电子表格 token，支持输入电子表格 url。",
                  "max": null,
                  "min": null,
                  "name": "spreadsheet_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet ID, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表 ID，与 sheet_name 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_id",
                    "zh_Hans": "工作表 ID"
                  },
                  "llm_description": "工作表 ID，与 sheet_name 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet name, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表名称，与 sheet_id 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_name",
                    "zh_Hans": "工作表名称"
                  },
                  "llm_description": "工作表名称，与 sheet_id 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "open_id",
                  "form": "form",
                  "human_description": {
                    "en_US": "User ID type, optional values are open_id, union_id, user_id, with a default value of open_id.",
                    "zh_Hans": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。"
                  },
                  "label": {
                    "en_US": "user_id_type",
                    "zh_Hans": "用户 ID 类型"
                  },
                  "llm_description": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。",
                  "max": null,
                  "min": null,
                  "name": "user_id_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "open_id",
                        "zh_Hans": "open_id"
                      },
                      "value": "open_id"
                    },
                    {
                      "label": {
                        "en_US": "union_id",
                        "zh_Hans": "union_id"
                      },
                      "value": "union_id"
                    },
                    {
                      "label": {
                        "en_US": "user_id",
                        "zh_Hans": "user_id"
                      },
                      "value": "user_id"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Starting row number, starting from 1.",
                    "zh_Hans": "起始行号，从 1 开始。"
                  },
                  "label": {
                    "en_US": "start_row",
                    "zh_Hans": "起始行号"
                  },
                  "llm_description": "起始行号，从 1 开始。",
                  "max": null,
                  "min": null,
                  "name": "start_row",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Number of rows to read.",
                    "zh_Hans": "读取行数"
                  },
                  "label": {
                    "en_US": "num_rows",
                    "zh_Hans": "读取行数"
                  },
                  "llm_description": "读取行数",
                  "max": null,
                  "min": null,
                  "name": "num_rows",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Read Table",
                  "zh_Hans": "自定义读取电子表格行列数据"
                },
                "llm": "A tool for custom reading of row and column data from a spreadsheet. (自定义读取电子表格行列数据)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Read Table",
                  "zh_Hans": "自定义读取电子表格行列数据"
                },
                "name": "read_table"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Spreadsheet token, supports input of spreadsheet URL.",
                    "zh_Hans": "电子表格 token，支持输入电子表格 url。"
                  },
                  "label": {
                    "en_US": "spreadsheet_token",
                    "zh_Hans": "电子表格 token"
                  },
                  "llm_description": "电子表格 token，支持输入电子表格 url。",
                  "max": null,
                  "min": null,
                  "name": "spreadsheet_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet ID, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表 ID，与 sheet_name 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_id",
                    "zh_Hans": "工作表 ID"
                  },
                  "llm_description": "工作表 ID，与 sheet_name 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet name, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表名称，与 sheet_id 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_name",
                    "zh_Hans": "工作表名称"
                  },
                  "llm_description": "工作表名称，与 sheet_id 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "open_id",
                  "form": "form",
                  "human_description": {
                    "en_US": "User ID type, optional values are open_id, union_id, user_id, with a default value of open_id.",
                    "zh_Hans": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。"
                  },
                  "label": {
                    "en_US": "user_id_type",
                    "zh_Hans": "用户 ID 类型"
                  },
                  "llm_description": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。",
                  "max": null,
                  "min": null,
                  "name": "user_id_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "open_id",
                        "zh_Hans": "open_id"
                      },
                      "value": "open_id"
                    },
                    {
                      "label": {
                        "en_US": "union_id",
                        "zh_Hans": "union_id"
                      },
                      "value": "union_id"
                    },
                    {
                      "label": {
                        "en_US": "user_id",
                        "zh_Hans": "user_id"
                      },
                      "value": "user_id"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Starting row number, starting from 1.",
                    "zh_Hans": "起始行号，从 1 开始。"
                  },
                  "label": {
                    "en_US": "start_row",
                    "zh_Hans": "起始行号"
                  },
                  "llm_description": "起始行号，从 1 开始。",
                  "max": null,
                  "min": null,
                  "name": "start_row",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Number of rows to read.",
                    "zh_Hans": "读取行数"
                  },
                  "label": {
                    "en_US": "num_rows",
                    "zh_Hans": "读取行数"
                  },
                  "llm_description": "读取行数",
                  "max": null,
                  "min": null,
                  "name": "num_rows",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Data range, format like: A1:B2, can be empty when query=all.\n",
                    "zh_Hans": "取数范围,格式如:A1:B2，query=all 时可为空。"
                  },
                  "label": {
                    "en_US": "range",
                    "zh_Hans": "取数范围"
                  },
                  "llm_description": "取数范围,格式如:A1:B2，query=all 时可为空。",
                  "max": null,
                  "min": null,
                  "name": "range",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Pass \"all\" to query all data in the table, but no more than 100 columns.",
                    "zh_Hans": "传 all，表示查询表格所有数据，但最多查询 100 列数据。"
                  },
                  "label": {
                    "en_US": "query",
                    "zh_Hans": "查询"
                  },
                  "llm_description": "传 all，表示查询表格所有数据，但最多查询 100 列数据。",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get Spreadsheet",
                  "zh_Hans": "获取电子表格信息"
                },
                "llm": "A tool for getting information from spreadsheets. (获取电子表格信息)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Get Spreadsheet",
                  "zh_Hans": "获取电子表格信息"
                },
                "name": "get_spreadsheet"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Spreadsheet token, supports input of spreadsheet URL.",
                    "zh_Hans": "电子表格 token，支持输入电子表格 URL。"
                  },
                  "label": {
                    "en_US": "Spreadsheet Token",
                    "zh_Hans": "电子表格 token"
                  },
                  "llm_description": "电子表格 token，支持输入电子表格 URL。",
                  "max": null,
                  "min": null,
                  "name": "spreadsheet_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "open_id",
                  "form": "form",
                  "human_description": {
                    "en_US": "User ID type, optional values are open_id, union_id, user_id, with a default value of open_id.",
                    "zh_Hans": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。"
                  },
                  "label": {
                    "en_US": "user_id_type",
                    "zh_Hans": "用户 ID 类型"
                  },
                  "llm_description": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。",
                  "max": null,
                  "min": null,
                  "name": "user_id_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "open_id",
                        "zh_Hans": "open_id"
                      },
                      "value": "open_id"
                    },
                    {
                      "label": {
                        "en_US": "union_id",
                        "zh_Hans": "union_id"
                      },
                      "value": "union_id"
                    },
                    {
                      "label": {
                        "en_US": "user_id",
                        "zh_Hans": "user_id"
                      },
                      "value": "user_id"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Read Cols",
                  "zh_Hans": "读取工作表列数据"
                },
                "llm": "A tool for reading column data from a spreadsheet. (读取工作表列数据)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Read Cols",
                  "zh_Hans": "读取工作表列数据"
                },
                "name": "read_cols"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Spreadsheet token, supports input of spreadsheet URL.",
                    "zh_Hans": "电子表格 token，支持输入电子表格 url。"
                  },
                  "label": {
                    "en_US": "spreadsheet_token",
                    "zh_Hans": "电子表格 token"
                  },
                  "llm_description": "电子表格 token，支持输入电子表格 url。",
                  "max": null,
                  "min": null,
                  "name": "spreadsheet_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet ID, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表 ID，与 sheet_name 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_id",
                    "zh_Hans": "工作表 ID"
                  },
                  "llm_description": "工作表 ID，与 sheet_name 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet name, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表名称，与 sheet_id 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_name",
                    "zh_Hans": "工作表名称"
                  },
                  "llm_description": "工作表名称，与 sheet_id 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "open_id",
                  "form": "form",
                  "human_description": {
                    "en_US": "User ID type, optional values are open_id, union_id, user_id, with a default value of open_id.",
                    "zh_Hans": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。"
                  },
                  "label": {
                    "en_US": "user_id_type",
                    "zh_Hans": "用户 ID 类型"
                  },
                  "llm_description": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。",
                  "max": null,
                  "min": null,
                  "name": "user_id_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "open_id",
                        "zh_Hans": "open_id"
                      },
                      "value": "open_id"
                    },
                    {
                      "label": {
                        "en_US": "union_id",
                        "zh_Hans": "union_id"
                      },
                      "value": "union_id"
                    },
                    {
                      "label": {
                        "en_US": "user_id",
                        "zh_Hans": "user_id"
                      },
                      "value": "user_id"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Starting column number, starting from 1.",
                    "zh_Hans": "起始列号，从 1 开始。"
                  },
                  "label": {
                    "en_US": "start_col",
                    "zh_Hans": "起始列号"
                  },
                  "llm_description": "起始列号，从 1 开始。",
                  "max": null,
                  "min": null,
                  "name": "start_col",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Number of columns to read.",
                    "zh_Hans": "读取列数"
                  },
                  "label": {
                    "en_US": "num_cols",
                    "zh_Hans": "读取列数"
                  },
                  "llm_description": "读取列数",
                  "max": null,
                  "min": null,
                  "name": "num_cols",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Add Cols",
                  "zh_Hans": "新增多列至工作表最后"
                },
                "llm": "A tool for adding multiple columns to the end of a spreadsheet. (新增多列至工作表最后)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Add Cols",
                  "zh_Hans": "新增多列至工作表最后"
                },
                "name": "add_cols"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Spreadsheet token, supports input of spreadsheet URL.",
                    "zh_Hans": "电子表格 token，支持输入电子表格 url。"
                  },
                  "label": {
                    "en_US": "spreadsheet_token",
                    "zh_Hans": "电子表格 token"
                  },
                  "llm_description": "电子表格 token，支持输入电子表格 url。",
                  "max": null,
                  "min": null,
                  "name": "spreadsheet_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet ID, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表 ID，与 sheet_name 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_id",
                    "zh_Hans": "工作表 ID"
                  },
                  "llm_description": "工作表 ID，与 sheet_name 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet name, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表名称，与 sheet_id 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_name",
                    "zh_Hans": "工作表名称"
                  },
                  "llm_description": "工作表名称，与 sheet_id 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Number of columns to add, range (0-5000].",
                    "zh_Hans": "要增加的列数，范围(0-5000]。"
                  },
                  "label": {
                    "en_US": "length",
                    "zh_Hans": "要增加的列数"
                  },
                  "llm_description": "要增加的列数，范围(0-5000]。",
                  "max": null,
                  "min": null,
                  "name": "length",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Content of the new columns, array of objects in string format, each array represents a row of table data, format like: [ [ \"ID\",\"Name\",\"Age\" ],[ 1,\"Zhang San\",10 ],[ 2,\"Li Si\",11 ] ].\n",
                    "zh_Hans": "新增列的单元格内容，数组对象字符串，每个数组一行表格数据，格式：[[\"编号\",\"姓名\",\"年龄\"],[1,\"张三\",10],[2,\"李四\",11]]。"
                  },
                  "label": {
                    "en_US": "values",
                    "zh_Hans": "新增列的单元格内容"
                  },
                  "llm_description": "新增列的单元格内容，数组对象字符串，每个数组一行表格数据，格式：[[\"编号\",\"姓名\",\"年龄\"],[1,\"张三\",10],[2,\"李四\",11]]。",
                  "max": null,
                  "min": null,
                  "name": "values",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "List Spreadsheet Sheets",
                  "zh_Hans": "列出电子表格所有工作表"
                },
                "llm": "A tool for listing all sheets in a spreadsheet. (列出电子表格所有工作表)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "List Spreadsheet Sheets",
                  "zh_Hans": "列出电子表格所有工作表"
                },
                "name": "list_spreadsheet_sheets"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Spreadsheet token, supports input of spreadsheet URL.",
                    "zh_Hans": "电子表格 token，支持输入电子表格 URL。"
                  },
                  "label": {
                    "en_US": "Spreadsheet Token",
                    "zh_Hans": "电子表格 token"
                  },
                  "llm_description": "电子表格 token，支持输入电子表格 URL。",
                  "max": null,
                  "min": null,
                  "name": "spreadsheet_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-26T10:44:33Z",
        "version_updated_at": "2025-02-26T10:44:33Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "WolframAlpha is a powerful computational knowledge engine.",
          "pt_BR": "WolframAlpha is a powerful computational knowledge engine.",
          "zh_Hans": "WolframAlpha 是一个强大的计算知识引擎。"
        },
        "category": "tool",
        "created_at": "2024-12-02T14:48:06Z",
        "endpoint": {},
        "icon": "langgenius/packages/wolframalpha/_assets/icon.svg",
        "index_id": "langgenius___wolframalpha",
        "install_count": 1758,
        "introduction": "# Overview\nWolfram Alpha is a computational knowledge engine and popular web service that generates answers by computing the relevant data, rather than searching the web for likely hits. Unlike traditional search engines that return a list of web pages, Wolfram Alpha provides a more structured and integrated approach to finding and presenting information.\n\n# Configuration\n## Create an App in WolframAlpha\n1. Log in to [WolframAlpha Developer Portal](https://developer.wolframalpha.com/access). Please register an WolframAlpha account if you don't have one.\n2. Click **Get an App ID**.\n\n![](./_assets/wolframalpha_developer.png)\n\n3. Fill in the Name and Description. Select **Full Results API** in API.\n\n![](./_assets/wolframalpha_create_app.png)\n\n4. Copy **APP ID**.\n\n## Configure WolframAlpha tool\n\n1. Install WolframAlpha from Marketplace. \n2. Add WolframAlpha node to your workflow.\n3. Fill in the WolframAlpha AppID.\n4. Input Query string for calculation. Please refer to [WolframAlpha's documentation](https://products.wolframalpha.com/api/documentation) for further help. \n\n![](./_assets/wolframalpha_doc.png)",
        "label": {
          "en_US": "WolframAlpha",
          "pt_BR": "WolframAlpha",
          "zh_Hans": "WolframAlpha"
        },
        "latest_package_identifier": "langgenius/wolframalpha:0.0.4@22d83ac5203d06f397247eaa5ff13dad41a91f540a0c0eb80d25898bffd9ae35",
        "latest_version": "0.0.4",
        "model": {},
        "name": "wolframalpha",
        "org": "langgenius",
        "plugin_id": "langgenius/wolframalpha",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/wolframalpha.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "utilities"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Get your WolframAlpha AppID from WolframAlpha, please use \"full results\" api access.",
                "pt_BR": "Get your WolframAlpha AppID from WolframAlpha, please use \"full results\" api access.",
                "zh_Hans": "从 WolframAlpha 获取您的 WolframAlpha AppID，请使用 \"full results\" API。"
              },
              "label": {
                "en_US": "WolframAlpha AppID",
                "pt_BR": "WolframAlpha AppID",
                "zh_Hans": "WolframAlpha AppID"
              },
              "name": "appid",
              "options": null,
              "placeholder": {
                "en_US": "Please input your WolframAlpha AppID",
                "pt_BR": "Please input your WolframAlpha AppID",
                "zh_Hans": "请输入你的 WolframAlpha AppID"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://products.wolframalpha.com/api"
            }
          ],
          "identity": {
            "author": "langgenius",
            "description": {
              "en_US": "WolframAlpha is a powerful computational knowledge engine.",
              "pt_BR": "WolframAlpha is a powerful computational knowledge engine.",
              "zh_Hans": "WolframAlpha 是一个强大的计算知识引擎。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "WolframAlpha",
              "pt_BR": "WolframAlpha",
              "zh_Hans": "WolframAlpha"
            },
            "name": "wolframalpha",
            "tags": [
              "productivity",
              "utilities"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "WolframAlpha is a powerful computational knowledge engine.",
                  "pt_BR": "WolframAlpha is a powerful computational knowledge engine.",
                  "zh_Hans": "WolframAlpha 是一个强大的计算知识引擎。"
                },
                "llm": "WolframAlpha is a powerful computational knowledge engine. one single query can get the answer of a question."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "WolframAlpha",
                  "pt_BR": "WolframAlpha",
                  "zh_Hans": "WolframAlpha"
                },
                "name": "wolframalpha"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "used for calculating",
                    "pt_BR": "used for calculating",
                    "zh_Hans": "用于计算最终结果"
                  },
                  "label": {
                    "en_US": "Query string",
                    "pt_BR": "Query string",
                    "zh_Hans": "计算语句"
                  },
                  "llm_description": "a single query for calculating",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-01T08:44:38Z",
        "version_updated_at": "2025-04-01T08:44:38Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Serper is a powerful real-time search engine tool API that provides structured data from Google Search.",
          "pt_BR": "Serper is a powerful real-time search engine tool API that provides structured data from Google Search.",
          "zh_Hans": "Serper 是一个强大的实时搜索引擎工具API，可提供来自 Google 搜索引擎搜索的结构化数据。"
        },
        "category": "tool",
        "created_at": "2024-11-29T13:43:30Z",
        "endpoint": {},
        "icon": "langgenius/packages/serper/_assets/icon.svg",
        "index_id": "langgenius___serper",
        "install_count": 1756,
        "introduction": "# Overview\n[Serper](https://serpapi.com) is a search tool designed to query and retrieve information from the web using a simple and efficient interface. \n\nIt allows users to input a query string and fetch search results programmatically, making it ideal for integrating web search capabilities into workflows or applications. \n\nWith Serper, you can automate the process of retrieving relevant information from the internet without manually using a browser.\n# Configure\n1. Install Serper from Dify Marketplace.\n![](./_assets/serper_install.PNG)\n2. Create an account in Serper and [get an API key](https://serper.dev/api-key).\n3. Add Serper to your workflow. Click \"To authorize\" and paste the API key.\n4. Input your query string, such as `Top programming languages 2025`.\n![](./_assets/serper_test.PNG)",
        "label": {
          "en_US": "Serper",
          "pt_BR": "Serper",
          "zh_Hans": "Serper"
        },
        "latest_package_identifier": "langgenius/serper:0.0.2@4e0d70360c68b17b7504b65f6f14ecd00a40b8b138b716ff72f3bfd8139961ab",
        "latest_version": "0.0.2",
        "model": {},
        "name": "serper",
        "org": "langgenius",
        "plugin_id": "langgenius/serper",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/serper.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "search"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "Serper API key",
                "pt_BR": "Serper API key",
                "zh_Hans": "Serper API key"
              },
              "name": "serperapi_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Serper API key",
                "pt_BR": "Please input your Serper API key",
                "zh_Hans": "请输入你的 Serper API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://serper.dev/api-key"
            }
          ],
          "identity": {
            "author": "zhuhao",
            "description": {
              "en_US": "Serper is a powerful real-time search engine tool API that provides structured data from Google Search.",
              "pt_BR": "Serper is a powerful real-time search engine tool API that provides structured data from Google Search.",
              "zh_Hans": "Serper 是一个强大的实时搜索引擎工具API，可提供来自 Google 搜索引擎搜索的结构化数据。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Serper",
              "pt_BR": "Serper",
              "zh_Hans": "Serper"
            },
            "name": "serper",
            "tags": [
              "search"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool for performing a Google search and extracting snippets and webpages.Input should be a search query.",
                  "pt_BR": "A tool for performing a Google search and extracting snippets and webpages.Input should be a search query.",
                  "zh_Hans": "一个用于执行 Google 搜索并提取片段和网页的工具。输入应该是一个搜索查询。"
                },
                "llm": "A tool for performing a Google search and extracting snippets and webpages.Input should be a search query."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "zhuhao",
                "label": {
                  "en_US": "Serper",
                  "pt_BR": "Serper",
                  "zh_Hans": "Serper"
                },
                "name": "serper"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "used for searching",
                    "pt_BR": "used for searching",
                    "zh_Hans": "用于搜索网页内容"
                  },
                  "label": {
                    "en_US": "Query string",
                    "pt_BR": "Query string",
                    "zh_Hans": "查询语句"
                  },
                  "llm_description": "key words for searching",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:18:31Z",
        "version_updated_at": "2025-02-17T07:18:31Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "a key-value storage tool allow you save and get data across different apps.",
          "zh_Hans": "一个键值存储工具,允许你在不同的应用之间保存和获取数据。"
        },
        "category": "tool",
        "created_at": "2025-03-21T08:54:34Z",
        "endpoint": {
          "endpoints": [
            {
              "hidden": false,
              "method": "GET",
              "path": "/file"
            }
          ],
          "settings": [
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "API key"
              },
              "name": "api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your API key",
                "zh_Hans": "请输入你的 API key"
              },
              "required": false,
              "scope": null,
              "type": "secret-input",
              "url": null
            }
          ]
        },
        "icon": "hjlarry/packages/storage/_assets/icon.svg",
        "index_id": "hjlarry___storage",
        "install_count": 1746,
        "introduction": "## storage\n\n**Author:** hjlarry  \n**Version:** 0.0.1  \n**Type:** extension  \n**Repo:** :[https://github.com/hjlarry/dify-plugin-storage](https://github.com/hjlarry/dify-plugin-storage)\n\n### Description\n\nThis plugin is a key-value storage tool allow you save and get data across different apps.\n\n\n### Example Usage\n\n#### 1. Persistent Token Management Across Applications\n\nSimilar to Redis or the conversation variables in Dify, you can use tools that allow data persistence across different applications. For instance, when requesting an API service in your Dify workflow, you might first need to obtain a temporary token. You can utilize the set_string tool to save this token.\n\nWhen users execute your workflow, they can retrieve the token using the get_string tool, minimizing the need to repeatedly request a new temporary token. This capability ensures that data can be shared seamlessly across applications and stored for long-term use.\n\n\n#### 2. Secure File Sharing from Dify App\n\nDue to security, direct access to a file's URL in Dify is restricted; the preview file URL is valid for only 300 seconds. To address this, you can use the save_file tool to store the file persistently and share it via a generated endpoint.\n\nThe shared url will look like this: `https://daemon-plugin.dify.dev/rbmcB5EZRdDAlOqTt3H9ApgWcjzfD9Jg/file?key=your-file-key`.\n\nTo enhance security, you can include an api_key in the endpoint, resulting in a URL like: `https://daemon-plugin.dify.dev/rbmcB5EZRdDAlOqTt3H9ApgWcjzfD9Jg/file?key=your-file-key&api_key=your-api-key`. If you need to restrict access to the file, simply change the api_key, rendering the original URL inaccessible.\n",
        "label": {
          "en_US": "Storage",
          "zh_Hans": "存储"
        },
        "latest_package_identifier": "hjlarry/storage:0.0.2@5a3b82a4fcf8f729948a1e531ccef72f9f9577224a86727711def0f07061c52d",
        "latest_version": "0.0.2",
        "model": {},
        "name": "storage",
        "org": "hjlarry",
        "plugin_id": "hjlarry/storage",
        "plugins": {
          "agent_strategies": null,
          "endpoints": [
            "provider/file.yaml"
          ],
          "models": null,
          "tools": [
            "provider/storage.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "endpoint": {
              "enabled": true
            },
            "storage": {
              "enabled": true,
              "size": 1073741824
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "hjlarry",
            "description": {
              "en_US": "a key-value storage tool allow you save and get data across different apps.",
              "pt_BR": "a key-value storage tool allow you save and get data across different apps.",
              "zh_Hans": "a key-value storage tool allow you save and get data across different apps."
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "storage",
              "pt_BR": "storage",
              "zh_Hans": "storage"
            },
            "name": "storage",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "To get a key-value string.",
                  "zh_Hans": "获取一个键值字符串。"
                },
                "llm": "To get a key-value string."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "hjlarry",
                "label": {
                  "en_US": "get string",
                  "zh_Hans": "获取字符串"
                },
                "name": "get_string"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "To get a key's value.",
                    "zh_Hans": "获取一个键的值。"
                  },
                  "label": {
                    "en_US": "Key",
                    "zh_Hans": "键"
                  },
                  "llm_description": "To get a key's value.",
                  "max": null,
                  "min": null,
                  "name": "key",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "To set a key-value string.",
                  "zh_Hans": "设置一个键值字符串。"
                },
                "llm": "To set a key-value string."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "hjlarry",
                "label": {
                  "en_US": "set string",
                  "zh_Hans": "设置字符串"
                },
                "name": "set_string"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The key of the string to be set",
                    "zh_Hans": "要设置的键"
                  },
                  "label": {
                    "en_US": "Key",
                    "zh_Hans": "键"
                  },
                  "llm_description": "Key",
                  "max": null,
                  "min": null,
                  "name": "key",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The value of the string to be set",
                    "zh_Hans": "要设置的值"
                  },
                  "label": {
                    "en_US": "Value",
                    "zh_Hans": "值"
                  },
                  "llm_description": "Value",
                  "max": null,
                  "min": null,
                  "name": "value",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Limit the size of the string.",
                    "zh_Hans": "限制用户设置字符串的大小。"
                  },
                  "label": {
                    "en_US": "Size",
                    "zh_Hans": "大小"
                  },
                  "llm_description": "Size",
                  "max": null,
                  "min": null,
                  "name": "size",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "To get a key-value file.",
                  "zh_Hans": "通过键获取文件。"
                },
                "llm": "To get a key-value file."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "hjlarry",
                "label": {
                  "en_US": "get file",
                  "zh_Hans": "获取文件"
                },
                "name": "get_file"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "To get a key-value file.",
                    "zh_Hans": "通过键获取文件。"
                  },
                  "label": {
                    "en_US": "Key",
                    "zh_Hans": "键"
                  },
                  "llm_description": "To get a key-value file.",
                  "max": null,
                  "min": null,
                  "name": "key",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "To set a key-value file.",
                  "zh_Hans": "设置一个键值文件。"
                },
                "llm": "To set a key-value file."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "hjlarry",
                "label": {
                  "en_US": "set file",
                  "zh_Hans": "设置文件"
                },
                "name": "set_file"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Key of the file to be set",
                    "zh_Hans": "要设置的文件的键"
                  },
                  "label": {
                    "en_US": "Key",
                    "zh_Hans": "键"
                  },
                  "llm_description": "Key",
                  "max": null,
                  "min": null,
                  "name": "key",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "File to be set",
                    "zh_Hans": "要设置的文件"
                  },
                  "label": {
                    "en_US": "File",
                    "zh_Hans": "文件"
                  },
                  "llm_description": "File",
                  "max": null,
                  "min": null,
                  "name": "file",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "file"
                },
                {
                  "auto_generate": null,
                  "default": 10,
                  "form": "form",
                  "human_description": {
                    "en_US": "Limit the size of the uploaded file. (default:10MB)",
                    "zh_Hans": "限制用户上传文件的大小。(默认:10MB)"
                  },
                  "label": {
                    "en_US": "Size",
                    "zh_Hans": "大小"
                  },
                  "llm_description": "Size",
                  "max": null,
                  "min": null,
                  "name": "size",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "To delete a key.",
                  "zh_Hans": "删除一个键。"
                },
                "llm": "To delete a key."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "hjlarry",
                "label": {
                  "en_US": "delete key",
                  "zh_Hans": "删除键"
                },
                "name": "delete_key"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "To delete a key.",
                    "zh_Hans": "删除一个键。"
                  },
                  "label": {
                    "en_US": "Key",
                    "zh_Hans": "键"
                  },
                  "llm_description": "To delete a key.",
                  "max": null,
                  "min": null,
                  "name": "key",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-21T08:54:38Z",
        "version_updated_at": "2025-03-21T08:54:38Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Models provided by stepfun, such as step-1-8k, step-1-32k、step-1v-8k、step-1v-32k, step-1-128k and step-1-256k",
          "zh_Hans": "阶跃星辰提供的模型，例如 step-1-8k、step-1-32k、step-1v-8k、step-1v-32k、step-1-128k 和 step-1-256k。"
        },
        "category": "model",
        "created_at": "2024-11-28T10:37:11Z",
        "endpoint": {},
        "icon": "langgenius/packages/stepfun/_assets/icon_s_en.png",
        "index_id": "langgenius___stepfun",
        "install_count": 1690,
        "introduction": "",
        "label": {
          "en_US": "Stepfun",
          "zh_Hans": "阶跃星辰"
        },
        "latest_package_identifier": "langgenius/stepfun:0.0.2@a1de96a4faac9ac6f9b952a7b27dfa52cafd8f55d4ebeed53e663d9355136207",
        "latest_version": "0.0.2",
        "model": {
          "background": "#FFFFFF",
          "configurate_methods": [
            "predefined-model",
            "customizable-model"
          ],
          "description": {
            "en_US": "Models provided by stepfun, such as step-1-8k, step-1-32k、step-1v-8k、step-1v-32k, step-1-128k and step-1-256k",
            "zh_Hans": "阶跃星辰提供的模型，例如 step-1-8k、step-1-32k、step-1v-8k、step-1v-32k、step-1-128k 和 step-1-256k。"
          },
          "help": {
            "title": {
              "en_US": "Get your API Key from stepfun",
              "zh_Hans": "从 stepfun 获取 API Key"
            },
            "url": {
              "en_US": "https://platform.stepfun.com/interface-key"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.png"
          },
          "icon_small": {
            "en_US": "icon_s_en.png"
          },
          "label": {
            "en_US": "Stepfun",
            "zh_Hans": "阶跃星辰"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              },
              {
                "default": "8192",
                "label": {
                  "en_US": "Model context size",
                  "zh_Hans": "模型上下文长度"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Model context size",
                  "zh_Hans": "在此输入您的模型上下文长度"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "context_size"
              },
              {
                "default": "8192",
                "label": {
                  "en_US": "Upper bound for max tokens",
                  "zh_Hans": "最大 token 上限"
                },
                "max_length": 0,
                "options": [],
                "placeholder": null,
                "required": false,
                "show_on": [],
                "type": "text-input",
                "variable": "max_tokens"
              },
              {
                "default": "no_call",
                "label": {
                  "en_US": "Function calling"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Not supported",
                      "zh_Hans": "不支持"
                    },
                    "show_on": [],
                    "value": "no_call"
                  },
                  {
                    "label": {
                      "en_US": "Tool Call",
                      "zh_Hans": "Tool Call"
                    },
                    "show_on": [],
                    "value": "tool_call"
                  }
                ],
                "placeholder": null,
                "required": false,
                "show_on": [],
                "type": "select",
                "variable": "function_calling_type"
              }
            ],
            "model": {
              "label": {
                "en_US": "Model Name",
                "zh_Hans": "模型名称"
              },
              "placeholder": {
                "en_US": "Enter your model name",
                "zh_Hans": "输入模型名称"
              }
            }
          },
          "models": [
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "step-1-128k",
                "zh_Hans": "step-1-128k"
              },
              "model": "step-1-128k",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 128000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.04",
                "output": "0.2",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "step-1-256k",
                "zh_Hans": "step-1-256k"
              },
              "model": "step-1-256k",
              "model_properties": {
                "context_size": 256000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 256000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.095",
                "output": "0.3",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "multi-tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "step-1-32k",
                "zh_Hans": "step-1-32k"
              },
              "model": "step-1-32k",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 32000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.015",
                "output": "0.07",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "multi-tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "step-1-8k",
                "zh_Hans": "step-1-8k"
              },
              "model": "step-1-8k",
              "model_properties": {
                "context_size": 8000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 8000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.005",
                "output": "0.02",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "step-1-flash",
                "zh_Hans": "step-1-flash"
              },
              "model": "step-1-flash",
              "model_properties": {
                "context_size": 8000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 8000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.001",
                "output": "0.004",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "vision",
                "tool-call",
                "multi-tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "step-1v-32k",
                "zh_Hans": "step-1v-32k"
              },
              "model": "step-1v-32k",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 32000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.015",
                "output": "0.07",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "vision",
                "tool-call",
                "multi-tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "step-1v-8k",
                "zh_Hans": "step-1v-8k"
              },
              "model": "step-1v-8k",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.005",
                "output": "0.02",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call",
                "multi-tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "step-2-16k",
                "zh_Hans": "step-2-16k"
              },
              "model": "step-2-16k",
              "model_properties": {
                "context_size": 16000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 16000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.038",
                "output": "0.12",
                "unit": "0.001"
              }
            }
          ],
          "position": {
            "llm": [
              "step-1-8k",
              "step-1-32k",
              "step-1-128k",
              "step-1-256k",
              "step-1-flash",
              "step-2-16k",
              "step-1v-8k",
              "step-1v-32k"
            ]
          },
          "provider": "stepfun",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              }
            ]
          },
          "supported_model_types": [
            "llm"
          ]
        },
        "name": "stepfun",
        "org": "langgenius",
        "plugin_id": "langgenius/stepfun",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/stepfun.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "image"
          },
          {
            "name": "productivity"
          }
        ],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-02-17T06:58:20Z",
        "version_updated_at": "2025-02-17T06:58:20Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Slack Webhook",
          "pt_BR": "Slack Webhook",
          "zh_Hans": "Slack Webhook"
        },
        "category": "tool",
        "created_at": "2024-12-03T09:19:17Z",
        "endpoint": {},
        "icon": "langgenius/packages/slack/_assets/icon.svg",
        "index_id": "langgenius___slack",
        "install_count": 1634,
        "introduction": "# Overview\nSlack is a cloud-based team communication platform designed to enhance collaboration and streamline workflows within organizations. \n\nYou can use the Slack tool to send messages in a channel via a bot with the output variables from Dify workflow.\n\n# Configure\nCreate an application in Slack\n1. Log in to the [Slack API platform](https://api.slack.com/apps).\n2. Click **Create an App**.\n![](./_assets/slack_create_app.PNG)\n3. Click **From scratch**.\n4. Enter the App Name and select a workspace, then click **Create App**.\n![](./_assets/slack_name_app.png)\n5. Go to app settings page. Click **Incoming Webhooks** in the app settings page's left navigation bar. \n6. Enable **Activate Incoming Webhooks**. At the bottom of the page, click Add New Webhook to Workspace and select an app publishing channel.\n![](./_assets/slack_incoming_webhooks.PNG)\n7. Return to **Incoming Webhooks**, and copy the webhook URL.\n\n## Configure Slack tool\n1. Install Slack tool from Marketplace.\n![](./_assets/slack_install.PNG)\n2. Add Slack node to workflows.\n3. Paste **Incoming Webhook**.",
        "label": {
          "en_US": "Slack",
          "pt_BR": "Slack",
          "zh_Hans": "Slack"
        },
        "latest_package_identifier": "langgenius/slack:0.0.4@4a166067bb3a67e02d256bb1602f445eb7f526e973b1cf773e644f375052e43a",
        "latest_version": "0.0.4",
        "model": {},
        "name": "slack",
        "org": "langgenius",
        "plugin_id": "langgenius/slack",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/slack.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "social"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "Slack Webhook URL",
                "pt_BR": "URL do Webhook do Slack",
                "zh_Hans": "Slack Webhook URL"
              },
              "name": "webhook_url",
              "options": null,
              "placeholder": null,
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            }
          ],
          "identity": {
            "author": "Pan YANG",
            "description": {
              "en_US": "Slack Webhook",
              "pt_BR": "Slack Webhook",
              "zh_Hans": "Slack Webhook"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Slack",
              "pt_BR": "Slack",
              "zh_Hans": "Slack"
            },
            "name": "slack",
            "tags": [
              "social",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Sending a message on Slack via the Incoming Webhook",
                  "pt_BR": "Sending a message on Slack via the Incoming Webhook",
                  "zh_Hans": "通过入站 Webhook 在 Slack 上发送消息"
                },
                "llm": "A tool for sending messages to a chat on Slack."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Pan YANG",
                "label": {
                  "en_US": "Incoming Webhook to send message",
                  "pt_BR": "Incoming Webhook to send message",
                  "zh_Hans": "通过入站 Webhook 发送消息"
                },
                "name": "slack_webhook"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Slack Incoming Webhook url",
                    "pt_BR": "Slack Incoming Webhook url",
                    "zh_Hans": "Slack 入站 Webhook 的 url"
                  },
                  "label": {
                    "en_US": "Slack Incoming Webhook url",
                    "pt_BR": "Slack Incoming Webhook url",
                    "zh_Hans": "Slack 入站 Webhook 的 url"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "webhook_url",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Content to sent to the channel or person.",
                    "pt_BR": "Content to sent to the channel or person.",
                    "zh_Hans": "消息内容文本"
                  },
                  "label": {
                    "en_US": "content",
                    "pt_BR": "content",
                    "zh_Hans": "消息内容"
                  },
                  "llm_description": "Content of the message",
                  "max": null,
                  "min": null,
                  "name": "content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:13:49Z",
        "version_updated_at": "2025-02-17T07:13:49Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Write the database metadata into the dify knowledge.",
          "zh_Hans": "此工具将数据库表结构写入知识库"
        },
        "category": "tool",
        "created_at": "2025-03-31T12:10:45Z",
        "endpoint": {},
        "icon": "majinkai/packages/database_to_knowledge/_assets/icon.svg",
        "index_id": "majinkai___database_to_knowledge",
        "install_count": 1612,
        "introduction": "## Database to knowledge\n\n**Author:** majinkai\n**Version:** 0.0.2\n**Type:** tool\n\n### How to use\n\n1. Use the API of the knowledge base for authentication(This tool use [Get Knowledge Base List](https://docs.dify.ai/guides/knowledge-base/knowledge-and-documents-maintenance/maintain-dataset-via-api#get-knowledge-base-list) API with page 1 and limit 1 to verify `API Key`)\n![](./_assets/auth.png)\n![](./_assets/auth_success.png)\n2. Set database configuration information\n![](./_assets/config.png)\n3. Run it to test, it will create a knowledge named `some_database` and `table a,b,c` three documents\n\n### Verified databases\n* MySQL (✅)\n* Oracle (✅)\n* SQL Server (✅)\n* PostgreSQL (✅)\n* Apach Doris (✅)\n",
        "label": {
          "en_US": "Database to knowledge",
          "zh_Hans": "表结构写入知识库"
        },
        "latest_package_identifier": "majinkai/database_to_knowledge:0.0.4@e1ab2fdc5ec84b9a68650e6e042c1ac8c399c3aea31405385fb4e70ae4341099",
        "latest_version": "0.0.4",
        "model": {},
        "name": "database_to_knowledge",
        "org": "majinkai",
        "plugin_id": "majinkai/database_to_knowledge",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/database_to_knowledge.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "endpoint": {
              "enabled": true
            },
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "utilities"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Get your url from Dify knowledge API",
                "zh_Hans": "从Dify获取您的API URL"
              },
              "label": {
                "en_US": "Dify knowledge API URL",
                "zh_Hans": "Dify知识库API地址"
              },
              "name": "dify_knowledge_api_url",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Dify API URL",
                "zh_Hans": "请输入你的Dify知识库API地址"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "help": {
                "en_US": "Get your key from Dify knowledge API",
                "zh_Hans": "从Dify获取您的API密钥"
              },
              "label": {
                "en_US": "Dify knowledge API Key",
                "zh_Hans": "Dify知识库API密钥"
              },
              "name": "dify_knowledge_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Dify knowledge API key",
                "zh_Hans": "请输入你的Dify知识库API密钥"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://docs.dify.ai/guides/knowledge-base/knowledge-and-documents-maintenance/maintain-dataset-via-api#how-to-use"
            }
          ],
          "identity": {
            "author": "majinkai",
            "description": {
              "en_US": "Write the database metadata into the dify knowledge.",
              "zh_Hans": "此工具将数据库表结构写入知识库"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Database to knowledge",
              "zh_Hans": "表结构写入知识库"
            },
            "name": "database_to_knowledge",
            "tags": [
              "utilities"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Write the database metadata into the dify knowledge.",
                  "zh_Hans": "此工具将数据库表结构写入知识库"
                },
                "llm": "Write the database metadata into the dify knowledge."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "majinkai",
                "label": {
                  "en_US": "Database to knowledge",
                  "zh_Hans": "表结构写入知识库"
                },
                "name": "database_to_knowledge"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Database type",
                    "zh_Hans": "数据库类型"
                  },
                  "label": {
                    "en_US": "Database type",
                    "zh_Hans": "数据库类型"
                  },
                  "llm_description": "Database type",
                  "max": null,
                  "min": null,
                  "name": "db_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "MySQL"
                      },
                      "value": "mysql"
                    },
                    {
                      "label": {
                        "en_US": "Oracle"
                      },
                      "value": "oracle"
                    },
                    {
                      "label": {
                        "en_US": "Microsoft SQL Server"
                      },
                      "value": "mssql"
                    },
                    {
                      "label": {
                        "en_US": "PostgreSQL"
                      },
                      "value": "postgresql"
                    },
                    {
                      "label": {
                        "en_US": "Apache Doris"
                      },
                      "value": "doris"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Host",
                    "zh_Hans": "主机地址"
                  },
                  "label": {
                    "en_US": "Host",
                    "zh_Hans": "主机地址"
                  },
                  "llm_description": "Host",
                  "max": null,
                  "min": null,
                  "name": "host",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Port",
                    "zh_Hans": "端口号"
                  },
                  "label": {
                    "en_US": "Port",
                    "zh_Hans": "端口号"
                  },
                  "llm_description": "Port",
                  "max": 65535,
                  "min": 1,
                  "name": "port",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Database",
                    "zh_Hans": "数据库名"
                  },
                  "label": {
                    "en_US": "Database",
                    "zh_Hans": "数据库名"
                  },
                  "llm_description": "Database",
                  "max": null,
                  "min": null,
                  "name": "database",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Username",
                    "zh_Hans": "用户名"
                  },
                  "label": {
                    "en_US": "Username",
                    "zh_Hans": "用户名"
                  },
                  "llm_description": "Username",
                  "max": null,
                  "min": null,
                  "name": "username",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Password",
                    "zh_Hans": "密码"
                  },
                  "label": {
                    "en_US": "Password",
                    "zh_Hans": "密码"
                  },
                  "llm_description": "Password",
                  "max": null,
                  "min": null,
                  "name": "password",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Table names(Split with commas)",
                    "zh_Hans": "表名(逗号分隔)"
                  },
                  "label": {
                    "en_US": "Table names(Split with commas)",
                    "zh_Hans": "表名(逗号分隔)"
                  },
                  "llm_description": "Table names",
                  "max": null,
                  "min": null,
                  "name": "table_names",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Embedding model",
                    "zh_Hans": "Embedding 模型"
                  },
                  "label": {
                    "en_US": "Embedding model",
                    "zh_Hans": "Embedding 模型"
                  },
                  "llm_description": "which Text Embedding Model to invoke",
                  "max": null,
                  "min": null,
                  "name": "embedding_model",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": "text-embedding",
                  "template": null,
                  "type": "model-selector"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Rerank model",
                    "zh_Hans": "Rerank 模型"
                  },
                  "label": {
                    "en_US": "Rerank model",
                    "zh_Hans": "Rerank 模型"
                  },
                  "llm_description": "which Rerank Model to invoke",
                  "max": null,
                  "min": null,
                  "name": "rerank_model",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": "rerank",
                  "template": null,
                  "type": "model-selector"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-23T01:38:17Z",
        "version_updated_at": "2025-04-23T01:38:17Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Remove the markdown syntax",
          "ja_JP": "マークダウン構文を削除",
          "pt_BR": "Remover a sintaxe markdown",
          "zh_Hans": "移除Markdown语法"
        },
        "category": "tool",
        "created_at": "2025-03-04T14:59:38Z",
        "endpoint": {},
        "icon": "himicoswilson/packages/no_markdown/_assets/icon.svg",
        "index_id": "himicoswilson___no_markdown",
        "install_count": 1576,
        "introduction": "## no-markdown\n\n**Author:** himicos\n**Version:** 0.0.1\n**Type:** tool\n\n### Description\n\nA Dify plugin tool that removes markdown syntax from text while maintaining readability. It converts markdown-formatted text to clean plain text, with the option to preserve URLs in a readable format. The tool processes text in real-time using markdown2 and BeautifulSoup4, supporting multiple languages including English, Chinese, Portuguese, and Japanese.\n\nKey features:\n- Removes all markdown formatting (headers, bold, italic, lists, etc.)\n- Optional URL preservation in human-readable format\n- Real-time processing without data storage\n- Multi-language support\n\n\n\n",
        "label": {
          "en_US": "No Markdown",
          "ja_JP": "マークダウンを削除",
          "pt_BR": "Remover Markdown",
          "zh_Hans": "移除Markdown"
        },
        "latest_package_identifier": "himicoswilson/no_markdown:0.0.1@81726c953990cb0d9fa53848fddddc9b72c74a6e53e36adb18413236e9ac8e0d",
        "latest_version": "0.0.1",
        "model": {},
        "name": "no_markdown",
        "org": "himicoswilson",
        "plugin_id": "himicoswilson/no_markdown",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/no_markdown.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "himicoswilson",
            "description": {
              "en_US": "Remove the markdown syntax",
              "pt_BR": "Remover a sintaxe markdown",
              "zh_Hans": "移除Markdown语法"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "No Markdown",
              "pt_BR": "Remover Markdown",
              "zh_Hans": "移除Markdown"
            },
            "name": "no_markdown",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Remove the markdown syntax",
                  "pt_BR": "Remover a sintaxe markdown",
                  "zh_Hans": "移除Markdown语法"
                },
                "llm": "Remove the markdown syntax"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "himicoswilson",
                "label": {
                  "en_US": "No Markdown",
                  "pt_BR": "Remover Markdown",
                  "zh_Hans": "移除Markdown"
                },
                "name": "no_markdown"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Remove the text markdown syntax",
                    "pt_BR": "Remover a sintaxe markdown do texto",
                    "zh_Hans": "移除文本中的Markdown语法"
                  },
                  "label": {
                    "en_US": "Text",
                    "pt_BR": "Texto",
                    "zh_Hans": "文本"
                  },
                  "llm_description": "Remove the text markdown syntax",
                  "max": null,
                  "min": null,
                  "name": "text",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to preserve URLs in the output",
                    "pt_BR": "Se deve preservar URLs na saída",
                    "zh_Hans": "是否在输出中保留URL链接"
                  },
                  "label": {
                    "en_US": "Preserve Links",
                    "pt_BR": "Preservar Links",
                    "zh_Hans": "保留链接"
                  },
                  "llm_description": "Whether to preserve URLs in the output",
                  "max": null,
                  "min": null,
                  "name": "preserve_links",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-04T15:01:15Z",
        "version_updated_at": "2025-03-04T15:01:15Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Models provided by Fish Audio, currently support TTS and ASR.",
          "zh_Hans": "Fish Audio 提供的模型，目前支持 TTS 和 ASR。"
        },
        "category": "model",
        "created_at": "2025-01-02T07:54:02Z",
        "endpoint": {},
        "icon": "langgenius/packages/fishaudio/_assets/fishaudio.jpeg",
        "index_id": "langgenius___fishaudio",
        "install_count": 1532,
        "introduction": "# Overview\nFish Audio is an innovative platform that provides a comprehensive suite of services for audio processing, particularly focusing on text-to-speech (TTS) capabilities. It allows users to convert text into high-quality audio files, supporting various voices and customizable parameters. This platform is designed for content creators, educators, and developers seeking efficient audio solutions.\n\n# Configure\nInstall [Fish Audio](https://fish.audio/go-api/) from Dify Marketplace. Get API key from Fish Audio and fill in the configurations in Settings -> Model Providers.\n\n![](_assets/fishaudio.PNG)",
        "label": {
          "en_US": "Fish Audio"
        },
        "latest_package_identifier": "langgenius/fishaudio:0.0.3@88eba0eeb2bb007b8166890083ec3fd700ae7874b97101450e080e843c1f5592",
        "latest_version": "0.0.3",
        "model": {
          "background": "#E5E7EB",
          "configurate_methods": [
            "predefined-model",
            "customizable-model"
          ],
          "description": {
            "en_US": "Models provided by Fish Audio, currently only support TTS and ASR.",
            "zh_Hans": "Fish Audio 提供的模型，目前支持 TTS 和 ASR。"
          },
          "help": {
            "title": {
              "en_US": "Get your API key from Fish Audio",
              "zh_Hans": "从 Fish Audio 获取你的 API Key"
            },
            "url": {
              "en_US": "https://fish.audio/zh-CN/go-api/api-keys/"
            }
          },
          "icon_large": {
            "en_US": "fishaudio.jpeg"
          },
          "icon_small": {
            "en_US": "fishaudio.jpeg"
          },
          "label": {
            "en_US": "Fish Audio"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              },
              {
                "default": "https://api.fish.audio",
                "label": {
                  "en_US": "API URL"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API URL",
                  "zh_Hans": "在此输入您的 API URL"
                },
                "required": false,
                "show_on": [],
                "type": "text-input",
                "variable": "api_base"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Model ID",
                  "zh_Hans": "模型 ID"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Model ID",
                  "zh_Hans": "在此输入您的模型 ID"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "model_id"
              },
              {
                "default": "mp3",
                "label": {
                  "en_US": "Output Format",
                  "zh_Hans": "输出格式"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "MP3",
                      "zh_Hans": "MP3"
                    },
                    "show_on": [],
                    "value": "mp3"
                  },
                  {
                    "label": {
                      "en_US": "WAV",
                      "zh_Hans": "WAV"
                    },
                    "show_on": [],
                    "value": "wav"
                  },
                  {
                    "label": {
                      "en_US": "PCM",
                      "zh_Hans": "PCM"
                    },
                    "show_on": [],
                    "value": "pcm"
                  }
                ],
                "placeholder": {
                  "en_US": "Select output format",
                  "zh_Hans": "选择输出格式"
                },
                "required": false,
                "show_on": [],
                "type": "select",
                "variable": "output_format"
              }
            ],
            "model": {
              "label": {
                "en_US": "Model Name",
                "zh_Hans": "模型名称"
              },
              "placeholder": {
                "en_US": "Enter your model name",
                "zh_Hans": "输入模型名称"
              }
            }
          },
          "models": [
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "fishaudio"
              },
              "model": "fishaudio",
              "model_properties": {
                "file_upload_limit": 25,
                "supported_file_extensions": "flac,mp3,mp4,mpeg,mpga,m4a,ogg,wav,webm"
              },
              "model_type": "speech2text",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "tts-default"
              },
              "model": "tts-default",
              "model_properties": {
                "audio_type": "mp3",
                "default_voice": "54a5170264694bfc8e9ad98df7bd89c3",
                "voices": [
                  {
                    "Language": [
                      "zh"
                    ],
                    "mode": "54a5170264694bfc8e9ad98df7bd89c3",
                    "name": "丁真"
                  },
                  {
                    "Language": [
                      "zh"
                    ],
                    "mode": "7f92f8afb8ec43bf81429cc1c9199cb1",
                    "name": "AD学姐"
                  },
                  {
                    "Language": [
                      "zh"
                    ],
                    "mode": "aebaa2305aa2452fbdc8f41eec852a79",
                    "name": "雷军"
                  },
                  {
                    "Language": [
                      "zh"
                    ],
                    "mode": "0eb38bc974e1459facca38b359e13511",
                    "name": "赛马娘"
                  },
                  {
                    "Language": [
                      "zh"
                    ],
                    "mode": "e80ea225770f42f79d50aa98be3cedfc",
                    "name": "孙笑川258"
                  },
                  {
                    "Language": [
                      "zh"
                    ],
                    "mode": "e4642e5edccd4d9ab61a69e82d4f8a14",
                    "name": "蔡徐坤"
                  },
                  {
                    "Language": [
                      "zh"
                    ],
                    "mode": "59cb5986671546eaa6ca8ae6f29f6d22",
                    "name": "央视配音"
                  },
                  {
                    "Language": [
                      "zh"
                    ],
                    "mode": "99503144194c45ed8fb998ceac181dcc",
                    "name": "贝利亚"
                  },
                  {
                    "Language": [
                      "zh"
                    ],
                    "mode": "f7561ff309bd4040a59f1e600f4f4338",
                    "name": "黑手"
                  },
                  {
                    "Language": [
                      "zh"
                    ],
                    "mode": "332941d1360c48949f1b4e0cabf912cd",
                    "name": "丁真（锐刻五代版）"
                  },
                  {
                    "Language": [
                      "zh"
                    ],
                    "mode": "1aacaeb1b840436391b835fd5513f4c4",
                    "name": "芙宁娜"
                  },
                  {
                    "Language": [
                      "zh"
                    ],
                    "mode": "3b55b3d84d2f453a98d8ca9bb24182d6",
                    "name": "邓紫琪"
                  },
                  {
                    "Language": [
                      "zh"
                    ],
                    "mode": "7c66db6e457c4d53b1fe428a8c547953",
                    "name": "郭德纲"
                  },
                  {
                    "Language": [
                      "zh"
                    ],
                    "mode": "7af4d620be1c4c6686132f21940d51c5",
                    "name": "东雪莲"
                  },
                  {
                    "Language": [
                      "zh"
                    ],
                    "mode": "3d1cb00d75184099992ddbaf0fdd7387",
                    "name": "奶龙(效果最好的一个)"
                  },
                  {
                    "Language": [
                      "zh"
                    ],
                    "mode": "e1cfccf59a1c4492b5f51c7c62a8abd2",
                    "name": "永雏塔菲"
                  },
                  {
                    "Language": [
                      "zh"
                    ],
                    "mode": "c7cbda1c101c4ce8906c046f01eca1a2",
                    "name": "董宇辉"
                  },
                  {
                    "Language": [
                      "zh"
                    ],
                    "mode": "665e031efe27435780ebfa56cc7e0e0d",
                    "name": "月半猫"
                  },
                  {
                    "Language": [
                      "zh"
                    ],
                    "mode": "84ed22e0ec8746969adf08bef0407494",
                    "name": " 我叫夯大力（包像版）"
                  },
                  {
                    "Language": [
                      "zh"
                    ],
                    "mode": "1512d05841734931bf905d0520c272b1",
                    "name": "周杰伦"
                  }
                ],
                "word_limit": 1000
              },
              "model_type": "tts",
              "parameter_rules": [],
              "pricing": null
            }
          ],
          "position": {
            "tts": null
          },
          "provider": "fishaudio",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              },
              {
                "default": "https://api.fish.audio",
                "label": {
                  "en_US": "API URL"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API URL",
                  "zh_Hans": "在此输入您的 API URL"
                },
                "required": false,
                "show_on": [],
                "type": "text-input",
                "variable": "api_base"
              },
              {
                "default": "false",
                "label": {
                  "en_US": "Use Public Models"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Allow Public Models",
                      "zh_Hans": "使用公共模型"
                    },
                    "show_on": [],
                    "value": "true"
                  },
                  {
                    "label": {
                      "en_US": "Private Models Only",
                      "zh_Hans": "仅使用私有模型"
                    },
                    "show_on": [],
                    "value": "false"
                  }
                ],
                "placeholder": {
                  "en_US": "Toggle to use public models",
                  "zh_Hans": "切换以使用公共模型"
                },
                "required": false,
                "show_on": [],
                "type": "select",
                "variable": "use_public_models"
              },
              {
                "default": "normal",
                "label": {
                  "en_US": "Latency"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Low (may affect quality)",
                      "zh_Hans": "低延迟 (可能降低质量)"
                    },
                    "show_on": [],
                    "value": "balanced"
                  },
                  {
                    "label": {
                      "en_US": "Normal",
                      "zh_Hans": "标准"
                    },
                    "show_on": [],
                    "value": "normal"
                  }
                ],
                "placeholder": {
                  "en_US": "Toggle to choice latency",
                  "zh_Hans": "切换以调整延迟"
                },
                "required": false,
                "show_on": [],
                "type": "select",
                "variable": "latency"
              }
            ]
          },
          "supported_model_types": [
            "tts",
            "speech2text"
          ]
        },
        "name": "fishaudio",
        "org": "langgenius",
        "plugin_id": "langgenius/fishaudio",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/fishaudio.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": false,
              "moderation": false,
              "rerank": false,
              "speech2text": true,
              "text_embedding": false,
              "tts": true
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-02-17T06:54:57Z",
        "version_updated_at": "2025-02-17T06:54:57Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Spark Platform Toolkit",
          "pt_BR": "Pacote de Ferramentas da Plataforma Spark",
          "zh_Hans": "讯飞星火平台工具"
        },
        "category": "tool",
        "created_at": "2024-12-03T09:30:27Z",
        "endpoint": {},
        "icon": "langgenius/packages/spark/_assets/icon.svg",
        "index_id": "langgenius___spark",
        "install_count": 1501,
        "introduction": "# Apache Spark Tool\n\n## Overview\n\nApache Spark is an open-source, distributed computing system designed for big data processing and analytics. It provides high-level APIs in Java, Scala, Python, and R, and supports a wide array of data processing tasks, from SQL queries to machine learning and graph processing.\n\n## Configuration\n\n### 1. 1. Apply for Spark API Config\nPlease apply for an API Key, API Secret and APPID from the [iFLYTEK open platform](https://console.xfyun.cn/services).\n\n### 2. Get Spark tools from Plugin Marketplace\nThe Apache Spark tools could be found at the Plugin Marketplace, please install it first.\n\n### 3. Fill in the configuration in Dify\nOn the Dify navigation page, click `Tools > Spark > Authorize` to fill in the API Key.\n\n![](./_assets/spark_1.png)\n\n### 4. Use the tool\nYou can use the Apache Spark tool in the following application types:\n\n![](./_assets/spark_2.png)\n\n#### Chatflow / Workflow applications\nBoth Chatflow and Workflow applications support adding an Spark tool node for data processing tasks.\n\n#### Agent applications\nAdd the Spark tool in the Agent application, then enter data processing commands to call this tool.",
        "label": {
          "en_US": "Spark",
          "pt_BR": "Spark",
          "zh_Hans": "讯飞星火"
        },
        "latest_package_identifier": "langgenius/spark:0.0.2@2bcb4248ac24c9cd1de59ac96e16f5d47c332fb99121249071f8641987399da8",
        "latest_version": "0.0.2",
        "model": {},
        "name": "spark",
        "org": "langgenius",
        "plugin_id": "langgenius/spark",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/spark.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "image"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "Spark APIKey",
                "pt_BR": "Spark APIKey",
                "zh_Hans": "APIKey"
              },
              "name": "APIKey",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Spark APIKey",
                "pt_BR": "Please input Spark APIKey",
                "zh_Hans": "请输入你的 APIKey"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://console.xfyun.cn/services"
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "Spark APISecret",
                "pt_BR": "Spark APISecret",
                "zh_Hans": "APISecret"
              },
              "name": "APISecret",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Spark APISecret",
                "pt_BR": "Please input your Spark APISecret",
                "zh_Hans": "请输入你的 APISecret"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "Spark APPID",
                "pt_BR": "Spark APPID",
                "zh_Hans": "APPID"
              },
              "name": "APPID",
              "options": null,
              "placeholder": {
                "en_US": "Please input your APPID",
                "pt_BR": "Please input your APPID",
                "zh_Hans": "请输入你的 APPID"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            }
          ],
          "identity": {
            "author": "Onelevenvy",
            "description": {
              "en_US": "Spark Platform Toolkit",
              "pt_BR": "Pacote de Ferramentas da Plataforma Spark",
              "zh_Hans": "讯飞星火平台工具"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Spark",
              "pt_BR": "Spark",
              "zh_Hans": "讯飞星火"
            },
            "name": "spark",
            "tags": [
              "image"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Generate images based on user input, with image generation API provided by Spark",
                  "pt_BR": "Gerar imagens com base na entrada do usuário, com API de geração de imagem fornecida pela Spark",
                  "zh_Hans": "根据用户的输入生成图片，由讯飞星火提供图片生成api"
                },
                "llm": "spark_img_generation is a tool used to generate images from text"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Onelevenvy",
                "label": {
                  "en_US": "Spark Image Generation",
                  "pt_BR": "Geração de imagens Spark",
                  "zh_Hans": "图片生成"
                },
                "name": "spark_img_generation"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Image prompt",
                    "pt_BR": "Image prompt",
                    "zh_Hans": "图像提示词"
                  },
                  "label": {
                    "en_US": "Prompt",
                    "pt_BR": "Prompt",
                    "zh_Hans": "提示词"
                  },
                  "llm_description": "Image prompt of spark_img_generation tooll, you should describe the image you want to generate as a list of words as possible as detailed",
                  "max": null,
                  "min": null,
                  "name": "prompt",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:16:43Z",
        "version_updated_at": "2025-02-17T07:16:43Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "WaterCrawl is a smart web crawling tool. with this plugin, you can easily crawl websites and extract data from them. this plugin is compatible with WaterCrawl v0.3.*",
          "zh_Hans": "WaterCrawl 是一个智能的网页爬取工具，使用这个插件，你可以轻松地爬取网站，从中提取数据。这个插件与 WaterCrawl v0.3.* 兼容。"
        },
        "category": "tool",
        "created_at": "2025-03-08T16:45:10Z",
        "endpoint": {},
        "icon": "watercrawl/packages/watercrawl/_assets/icon.svg",
        "index_id": "watercrawl___watercrawl",
        "install_count": 1497,
        "introduction": "# WaterCrawl Plugin\n\n**Author:** watercrawl  \n**Version:** 0.3.1  \n**Type:** Tool  \n\n<img src=\"./_assets/Introduction.png\" width=\"300\">\n\n### Description  \nWaterCrawl is a powerful web crawling tool designed for developers. This plugin allows you to easily crawl websites and extract data from them. It is compatible with WaterCrawl v0.3.* and offers a range of features for efficient data extraction.\n\n## Features  \n#### **Scrap Tool**:\nScrapes a single URL and outputs the content in various formats (markdown, HTML, JSON, or screenshot).  \n\n\n| <img src=\"./_assets/Scrap-params.png\" width=\"300\"> | <img src=\"./_assets/Scrap-settings.png\" width=\"300\"> |\n| --- | --- |\n\n\n#### **Crawl Tool**:\nInitiates a web crawl to extract data from specified URLs with configurable options for including/excluding URL patterns and generating alt text for images.\n\n\n| <img src=\"./_assets/Crawl-params.png\" width=\"300\"> | <img src=\"./_assets/Crawl-settings.png\" width=\"300\"> |\n| --- | --- |\n\n### **Crawl Job Tool**: \nRetrieve scraping results based on a crawl request UUID and cancel ongoing scraping tasks.  \n\n<img src=\"./_assets/Crawl-job-params.png\" width=\"300\">\n\n## Installation  \nTo install the WaterCrawl plugin, follow these steps:\nDownload the latest `.difypkg` file from the [GitHub Releases](https://github.com/watercrawl/watercrawl-dify-plugin/releases) or from the Dify marketplace.\n\n\n## Authentication  \nLogin to your WaterCrawl account [here](https://app.watercrawl.dev/). Or your self-hosted WaterCrawl instance. In the dashboard go to `API Keys` and create a new key or use an existing key.\n\n<img src=\"./_assets/Authorization-watercrawl.png\" width=\"80%\">\n\nthen in the Dify plugin management page, go to `Plugins` and click on the `+ Install` button. and use `API Key` in the plugin configuration.\n\n<img src=\"./_assets/Authorization.png\" width=\"300\">\n\n## Contributing / Development  \nTo contribute to the WaterCrawl plugin, follow these steps:\n1. Clone the repository: `git clone https://github.com/watercrawl/watercrawl-dify-plugin.git`\n2. Navigate to the project directory: `cd watercrawl-dify-plugin`\n3. Make virtual environment: `python -m venv env`\n4. Activate the virtual environment: `source env/bin/activate`\n5. Install dependencies: `pip install -r requirements.txt`\n6. Copy the `.env.example` file to `.env` and fill in the necessary values.\n7. Run the plugin: `python -m main`\n\n\n### Support  \nFor support, please contact us at [support@watercrawl.dev](mailto:support@watercrawl.dev).\n\n### License  \nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n",
        "label": {
          "en_US": "WaterCrawl",
          "zh_Hans": "WaterCrawl"
        },
        "latest_package_identifier": "watercrawl/watercrawl:0.3.1@50b13e6da1b65901f4c91c191543e1419796baad885ca481b35491d77c750e3b",
        "latest_version": "0.3.1",
        "model": {},
        "name": "watercrawl",
        "org": "watercrawl",
        "plugin_id": "watercrawl/watercrawl",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/water-crawl.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "endpoint": {
              "enabled": true
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "utilities"
          },
          {
            "name": "search"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "WaterCrawl server's Base URL",
                "zh_Hans": "WaterCrawl 服务器的基本 URL"
              },
              "name": "base_url",
              "options": null,
              "placeholder": {
                "en_US": "https://app.watercrawl.dev"
              },
              "required": false,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "help": {
                "en_US": "You can get your WaterCrawl API key from your WaterCrawl dashboard. If you are using a self-hosted version, login to your self-hosted WaterCrawl instance and generate a new API key.",
                "zh_Hans": "你可以从你的 WaterCrawl 仪表板获取你的 WaterCrawl API 密钥。 如果你在本地运行 WaterCrawl，请登录你的本地 WaterCrawl 实例并生成一个新的 API 密钥。"
              },
              "label": {
                "en_US": "WaterCrawl API Key",
                "zh_Hans": "WaterCrawl API Key"
              },
              "name": "api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your WaterCrawl API key",
                "zh_Hans": "请输入您的 WaterCrawl API 密钥"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://watercrawl.dev/"
            }
          ],
          "identity": {
            "author": "watercrawl",
            "description": {
              "en_US": "WaterCrawl is a smart web crawling tool. with this plugin, you can easily crawl websites and extract data from them. this plugin is compatible with WaterCrawl v0.3.*",
              "zh_Hans": "WaterCrawl 是一个智能的网页爬取工具，使用这个插件，你可以轻松地爬取网站，从中提取数据。这个插件与 WaterCrawl v0.3.* 兼容。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "WaterCrawl",
              "zh_Hans": "WaterCrawl"
            },
            "name": "watercrawl",
            "tags": [
              "search",
              "utilities"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Transform a url to LLM ready text"
                },
                "llm": "This tool is designed to scrap a single URL and output the content in selected format. The format can be markdown, html, json, or screenshot. If you choose screenshot, the output will be a screenshot of the page."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "watercrawl",
                "label": {
                  "en_US": "Scrap Single URL"
                },
                "name": "WaterCrawlScrap"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Enter the URL you want to scrap"
                  },
                  "label": {
                    "en_US": "URL"
                  },
                  "llm_description": "The URL of the website that needs to be crawled. This is a required parameter.",
                  "max": null,
                  "min": null,
                  "name": "url",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "markdown",
                  "form": "llm",
                  "human_description": {
                    "en_US": "Choose the format of the output"
                  },
                  "label": {
                    "en_US": "Format"
                  },
                  "llm_description": "The format of the output, such as markdown, html, or json. if you choose screenshot, the output will be a screenshot of the page. try to use markdown for most of the time.",
                  "max": null,
                  "min": null,
                  "name": "format",
                  "options": [
                    {
                      "label": {
                        "en_US": "Markdown"
                      },
                      "value": "markdown"
                    },
                    {
                      "label": {
                        "en_US": "HTML"
                      },
                      "value": "html"
                    },
                    {
                      "label": {
                        "en_US": "JSON"
                      },
                      "value": "json"
                    },
                    {
                      "label": {
                        "en_US": "Screenshot"
                      },
                      "value": "screenshot"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Include links in the output"
                  },
                  "label": {
                    "en_US": "Include links"
                  },
                  "llm_description": "Whether to include links in the output this link extracted from the page.",
                  "max": null,
                  "min": null,
                  "name": "include_links",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": 15000,
                  "form": "form",
                  "human_description": {
                    "en_US": "Set the timeout for the request"
                  },
                  "label": {
                    "en_US": "Timeout"
                  },
                  "llm_description": "The timeout for the request, in milliseconds. Default is 300ms.",
                  "max": null,
                  "min": null,
                  "name": "timeout",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 1000,
                  "form": "form",
                  "human_description": {
                    "en_US": "After opening the page, wait for the page to load for the specified time"
                  },
                  "label": {
                    "en_US": "Wait Timeout"
                  },
                  "llm_description": "The timeout for waiting for the page to load, in milliseconds. Default is 1000ms.",
                  "max": null,
                  "min": null,
                  "name": "wait_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Recursively search through a urls subdomains, and gather the content.",
                  "zh_Hans": "递归爬取一个网址的子域名，并收集内容。"
                },
                "llm": "This tool initiates a web crawl to extract data from a specified URL. It allows configuring crawler options such as including or excluding URL patterns, generating alt text for images using LLMs (paid plan required), limiting the maximum number of pages to crawl, and returning only the main content of the page. The tool can return either a list of crawled documents or a list of URLs based on the provided options."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "watercrawl",
                "label": {
                  "en_US": "Crawl",
                  "zh_Hans": "深度爬取"
                },
                "name": "crawl"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The base URL to start crawling from.",
                    "zh_Hans": "要爬取网站的起始URL。"
                  },
                  "label": {
                    "en_US": "Start URL",
                    "zh_Hans": "起始URL"
                  },
                  "llm_description": "The URL of the website that needs to be crawled. This is a required parameter.",
                  "max": null,
                  "min": null,
                  "name": "url",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "If you choose not to wait, it will directly return a crawl request json object. You can use this object uuid to check the crawling results or cancel the crawling task, which is usually very useful for a large-scale crawling task.",
                    "zh_Hans": "如果你选择不等待，它将直接返回爬取请求json对象。你可以使用这个对象uuid来检查爬取结果或取消爬取任务，通常对大规模爬取任务很有用。"
                  },
                  "label": {
                    "en_US": "Wait For Results",
                    "zh_Hans": "等待爬取结果"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "wait_for_results",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Pages matching these patterns will be skipped. Example: /blog/*, */about/*",
                    "zh_Hans": "匹配这些模式的页面将被跳过。示例：/blog/*, */about/*"
                  },
                  "label": {
                    "en_US": "URL patterns to exclude",
                    "zh_Hans": "要排除的URL模式"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "exclude_paths",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Only pages matching these patterns will be crawled. Example: /blog/*, /about/*",
                    "zh_Hans": "只有与这些模式匹配的页面才会被爬取。示例：/blog/*, /about/*"
                  },
                  "label": {
                    "en_US": "URL patterns to include",
                    "zh_Hans": "要包含的URL模式"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "include_paths",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 2,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Maximum depth to crawl relative to the entered URL. A max depth of 0 scrapes only the entered URL. A max depth of 1 scrapes the entered URL and all pages one level deep. A max depth of 2 scrapes the entered URL and all pages up to two levels deep. Higher values follow the same pattern.",
                    "zh_Hans": "相对于输入的URL，爬取的最大深度。max_depth为0时，仅抓取输入的URL。max_depth为1时，抓取输入的URL以及所有一级深层页面。max_depth为2时，抓取输入的URL以及所有两级深层页面。更高值遵循相同模式。"
                  },
                  "label": {
                    "en_US": "Maximum crawl depth",
                    "zh_Hans": "爬取深度"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": 0,
                  "name": "max_depth",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 5,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Specify the maximum number of pages to crawl. The crawler will stop after reaching this limit.",
                    "zh_Hans": "指定要爬取的最大页面数。爬虫将在达到此限制后停止。"
                  },
                  "label": {
                    "en_US": "Maximum pages to crawl",
                    "zh_Hans": "最大爬取页面数"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": 1,
                  "name": "page_limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "",
                  "form": "form",
                  "human_description": {
                    "en_US": "Allows the crawler to follow links. By default, it follows all subdomains. You can specify a custom list of domains using comma-separated values, including wildcard patterns to match URLs. *.example.com",
                    "zh_Hans": "允许爬虫跟随链接。默认情况下，它会在所有子域名上跟随链接。您可以使用逗号分隔值，包括通配符模式来匹配URL。*.example.com"
                  },
                  "label": {
                    "en_US": "Allowed Domains",
                    "zh_Hans": "允许爬取的域名"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "allowed_domains",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Headers to send with the request. Can be used to send cookies, user-agent, etc. Example: {\"cookies\": \"testcookies\"}",
                    "zh_Hans": "随请求发送的头部。可以用来发送cookies、用户代理等。示例：{\"cookies\": \"testcookies\"}"
                  },
                  "label": {
                    "en_US": "Headers",
                    "zh_Hans": "请求头"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "headers",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Only include tags, classes and ids from the page in the final output. Use comma separated values. Example: script, .ad, #footer",
                    "zh_Hans": "仅在最终输出中包含HTML页面的这些标签，可以通过标签名、类或ID来设定，使用逗号分隔值。示例：script, .ad, #footer"
                  },
                  "label": {
                    "en_US": "Include Tags",
                    "zh_Hans": "仅抓取这些标签"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "include_tags",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Tags, classes and ids to remove from the page. Use comma separated values. Example: script, .ad, #footer",
                    "zh_Hans": "要在最终输出中移除HTML页面的这些标签，可以通过标签名、类或ID来设定，使用逗号分隔值。示例：script, .ad, #footer"
                  },
                  "label": {
                    "en_US": "Exclude Tags",
                    "zh_Hans": "要移除这些标签"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "exclude_tags",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "Only return the main content of the page excluding headers, navs, footers, etc.",
                    "zh_Hans": "只返回页面的主要内容，不包括头部、导航栏、尾部等。"
                  },
                  "label": {
                    "en_US": "only Main Content",
                    "zh_Hans": "仅抓取主要内容"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "only_main_content",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": 3000,
                  "form": "form",
                  "human_description": {
                    "en_US": "The timeout for the request, in milliseconds. Default is 3000ms."
                  },
                  "label": {
                    "en_US": "Timeout",
                    "zh_Hans": "超时时间"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": 1000,
                  "name": "timeout",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 1000,
                  "form": "form",
                  "human_description": {
                    "en_US": "Wait x amount of milliseconds for the page to load to fetch content.",
                    "zh_Hans": "等待x毫秒以使页面加载并获取内容。"
                  },
                  "label": {
                    "en_US": "Wait Time",
                    "zh_Hans": "等待时间"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": 0,
                  "name": "wait_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Include html in the output",
                    "zh_Hans": "包含html"
                  },
                  "label": {
                    "en_US": "Include HTML",
                    "zh_Hans": "包含html"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "include_html",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Include links in the output",
                    "zh_Hans": "包含链接"
                  },
                  "label": {
                    "en_US": "Include Links",
                    "zh_Hans": "包含链接"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "include_links",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Retrieve the scraping results based on the crawl request uuid, or cancel the scraping task.",
                  "zh_Hans": "根据爬取任务UUID获取爬取结果，或者取消爬取任务"
                },
                "llm": "Retrieve the scraping results based on the crawl request uuid, or cancel the scraping task."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "watercrawl",
                "label": {
                  "en_US": "Crawl Job",
                  "zh_Hans": "爬取任务处理"
                },
                "name": "crawl_job"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Enter the crawl request UUID.",
                    "zh_Hans": "输入爬取任务UUID"
                  },
                  "label": {
                    "en_US": "Crawl Request UUID",
                    "zh_Hans": "爬取任务UUID"
                  },
                  "llm_description": "Use the crawl request uuid to get the crawl results or cancel the",
                  "max": null,
                  "min": null,
                  "name": "crawl_request_uuid",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "choose the operation to perform. `get` is for getting the crawl status, `cancel` is for cancelling the crawl job, `get_results` is for getting the crawl results.",
                    "zh_Hans": "选择操作类型。`get` 是获取爬取状态，`cancel` 是取消爬取任务，`get_results` 是获取爬取结果。"
                  },
                  "label": {
                    "en_US": "operation",
                    "zh_Hans": "操作"
                  },
                  "llm_description": "choose the operation to perform. `get` is for getting the crawl status, `cancel` is for cancelling the crawl job, `get_results` is for getting the crawl results.",
                  "max": null,
                  "min": null,
                  "name": "operation",
                  "options": [
                    {
                      "label": {
                        "en_US": "get crawl status",
                        "zh_Hans": "获取爬取状态"
                      },
                      "value": "get"
                    },
                    {
                      "label": {
                        "en_US": "cancel crawl job",
                        "zh_Hans": "取消爬取任务"
                      },
                      "value": "cancel"
                    },
                    {
                      "label": {
                        "en_US": "get crawl results",
                        "zh_Hans": "获取爬取结果"
                      },
                      "value": "get_results"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-08T16:45:33Z",
        "version_updated_at": "2025-03-08T16:45:33Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Convert your Dify tools's API to MCP compatible API (Note: must dify 1.2.0+)",
          "zh_Hans": "将您的Dify工具的API转换为MCP兼容API（注：必须 dify 1.2.0+）"
        },
        "category": "extension",
        "created_at": "2025-04-13T16:30:58Z",
        "endpoint": {
          "endpoints": [
            {
              "hidden": false,
              "method": "GET",
              "path": "/sse"
            },
            {
              "hidden": false,
              "method": "POST",
              "path": "/messages/"
            },
            {
              "hidden": false,
              "method": "GET",
              "path": "/mcp"
            },
            {
              "hidden": false,
              "method": "POST",
              "path": "/mcp"
            }
          ],
          "settings": [
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Tool list",
                "zh_Hans": "工具列表"
              },
              "name": "tools",
              "options": null,
              "placeholder": null,
              "required": true,
              "scope": null,
              "type": "array[tools]",
              "url": null
            }
          ]
        },
        "icon": "junjiem/packages/mcp_compat_dify_tools/_assets/icon.svg",
        "index_id": "junjiem___mcp_compat_dify_tools",
        "install_count": 1477,
        "introduction": "## Dify 1.0 Plugin Convert your Dify tools's API to MCP compatible API\n\n**Author:** [Junjie.M](https://github.com/junjiem)   \n**Type:** extension   \n**Github Repo:** [https://github.com/junjiem/dify-plugin-mcp_compat_dify_tools](https://github.com/junjiem/dify-plugin-mcp_compat_dify_tools)   \n**Github Issues:** [issues](https://github.com/junjiem/dify-plugin-mcp_compat_dify_tools/issues)  \n\n\nReference to https://github.com/hjlarry/dify-plugin-mcp_server\n\n\n---\n\n\n### Description\n\n> **Note:** must be dify 1.2.0 and above.\n\n> **注:** 必须是 dify 1.2.0及以上版本。\n\nConvert your Dify tools's API to MCP compatible API (**Currently, two transports are supported: `HTTP with SSE` and `Streamable HTTP`**)\n\n将您的 Dify 工具的 API 转换为 MCP 兼容 API (**目前已支持 `HTTP with SSE` 和 `Streamable HTTP` 两种传输方式**)\n\n\n#### 1. Add a endpoint and add tool list. 添加API端点并添加工具列表。\n\n![add_endpoint](./_assets/add_endpoint.png)\n\n![add_tool_list](./_assets/add_tool_list.png)\n\n![edit_tool](./_assets/edit_tool.png)\n\n![save_endpoint](./_assets/save_endpoint.png)\n\n> **Note:**\n>\n> 1. The modification of the tool list for existing endpoint will take effect only after the endpoint are disabled and then enabled.\n> \n\n\n> **注：**\n>\n> 1. 对已有 API 端点进行工具列表的修改需要停用再启用 API 端点后才会生效。\n> \n\n\n#### 2. Copy the endpoint url to your MCP client, like `Cherry Studio`  复制端点url到您的MCP客户端，如 `Cherry Studio`\n\n![mcp_urls](./_assets/mcp_urls.png)\n\n\n##### **Option 1:** Use the newest `Streamable HTTP` transport (**Recommended**)  使用最新的`Streamable HTTP`传输方式（**推荐**）\n\n![mcp_streamable_http_url](./_assets/mcp_streamable_http_url.png)\n\n![cherry_studio_mcp_streamable_http](./_assets/cherry_studio_mcp_streamable_http.png)\n\n**OK!**\n\n\n##### **Option 2:** Use the legacy `HTTP with SSE` transport  使用过时的`HTTP with SSE`传输方式\n\n![mcp_sse_url](./_assets/mcp_sse_url.png)\n\n![cherry_studio_mcp_sse](./_assets/cherry_studio_mcp_sse.png)\n\n**OK!**\n\n\n\n---\n\n\n\n### Installing Plugins via GitHub  通过 GitHub 安装插件\n\nCan install the plugin using the GitHub repository address. Visit the Dify platform's plugin management page, choose to install via GitHub, enter the repository address, select version number and package file to complete installation.\n\n可以通过 GitHub 仓库地址安装该插件。访问 Dify 平台的插件管理页，选择通过 GitHub 安装插件，输入仓库地址后，选择版本号和包文件完成安装。\n\n![install_plugin_via_github](_assets/install_plugin_via_github.png)\n\n\n\n---\n\n\n\n### FAQ\n\n#### 1. How to Handle Errors When Installing Plugins? 安装插件时遇到异常应如何处理？\n\n**Issue**: If you encounter the error message: plugin verification has been enabled, and the plugin you want to install has a bad signature, how to handle the issue?\n\n**Solution**: Add the following line to the end of your .env configuration file: FORCE_VERIFYING_SIGNATURE=false\nOnce this field is added, the Dify platform will allow the installation of all plugins that are not listed (and thus not verified) in the Dify Marketplace.\n\n**问题描述**：安装插件时遇到异常信息：plugin verification has been enabled, and the plugin you want to install has a bad signature，应该如何处理？\n\n**解决办法**：在 .env 配置文件的末尾添加 FORCE_VERIFYING_SIGNATURE=false 字段即可解决该问题。\n添加该字段后，Dify 平台将允许安装所有未在 Dify Marketplace 上架（审核）的插件，可能存在安全隐患。\n\n\n#### 2. How to install the offline version 如何安装离线版本\n\nScripting tool for downloading Dify plugin package from Dify Marketplace and Github and repackaging [true] offline package (contains dependencies, no need to be connected to the Internet).\n\n从Dify市场和Github下载Dify插件包并重新打【真】离线包（包含依赖，不需要再联网）的脚本工具。\n\nGithub Repo: https://github.com/junjiem/dify-plugin-repackaging\n\n",
        "label": {
          "en_US": "MCP Compatible Dify Tools",
          "zh_Hans": "MCP Compatible Dify Tools"
        },
        "latest_package_identifier": "junjiem/mcp_compat_dify_tools:0.1.0@299595c980dfcdd0404c1c00bf04aaedb77da3756589bdf97c7b15c855fce714",
        "latest_version": "0.1.0",
        "model": {},
        "name": "mcp_compat_dify_tools",
        "org": "junjiem",
        "plugin_id": "junjiem/mcp_compat_dify_tools",
        "plugins": {
          "agent_strategies": null,
          "endpoints": [
            "group/mcp_compat_dify_tools.yaml"
          ],
          "models": null,
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "endpoint": {
              "enabled": true
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-21T20:53:06Z",
        "version_updated_at": "2025-04-21T20:53:06Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Models provided by 01.AI, such as yi-34b-chat and yi-vl-plus.",
          "zh_Hans": "零一万物提供的模型，例如 yi-34b-chat 和 yi-vl-plus。"
        },
        "category": "model",
        "created_at": "2024-12-05T12:18:37Z",
        "endpoint": {},
        "icon": "langgenius/packages/yi/_assets/icon_s_en.svg",
        "index_id": "langgenius___yi",
        "install_count": 1401,
        "introduction": "",
        "label": {
          "en_US": "01.AI",
          "zh_Hans": "零一万物"
        },
        "latest_package_identifier": "langgenius/yi:0.0.2@d3bf4dee24d07f9b27e47ffce29497b0bcad7cc01dd093b9f71f7b69b0f4f807",
        "latest_version": "0.0.2",
        "model": {
          "background": "#E9F1EC",
          "configurate_methods": [
            "predefined-model",
            "customizable-model"
          ],
          "description": {
            "en_US": "Models provided by 01.AI, such as yi-34b-chat and yi-vl-plus.",
            "zh_Hans": "零一万物提供的模型，例如 yi-34b-chat 和 yi-vl-plus。"
          },
          "help": {
            "title": {
              "en_US": "Get your API Key from 01.ai",
              "zh_Hans": "从零一万物获取 API Key"
            },
            "url": {
              "en_US": "https://platform.lingyiwanwu.com/apikeys"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.svg"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "01.AI",
            "zh_Hans": "零一万物"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              },
              {
                "default": "4096",
                "label": {
                  "en_US": "Model context size",
                  "zh_Hans": "模型上下文长度"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Model context size",
                  "zh_Hans": "在此输入您的模型上下文长度"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "context_size"
              },
              {
                "default": "4096",
                "label": {
                  "en_US": "Upper bound for max tokens",
                  "zh_Hans": "最大 token 上限"
                },
                "max_length": 0,
                "options": [],
                "placeholder": null,
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "text-input",
                "variable": "max_tokens"
              },
              {
                "default": "no_call",
                "label": {
                  "en_US": "Function calling"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Not Support",
                      "zh_Hans": "不支持"
                    },
                    "show_on": [],
                    "value": "no_call"
                  },
                  {
                    "label": {
                      "en_US": "Support",
                      "zh_Hans": "支持"
                    },
                    "show_on": [],
                    "value": "function_call"
                  }
                ],
                "placeholder": null,
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "select",
                "variable": "function_calling_type"
              }
            ],
            "model": {
              "label": {
                "en_US": "Model Name",
                "zh_Hans": "模型名称"
              },
              "placeholder": {
                "en_US": "Enter your model name",
                "zh_Hans": "输入模型名称"
              }
            }
          },
          "models": [
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "yi-34b-chat-0205",
                "zh_Hans": "yi-34b-chat-0205"
              },
              "model": "yi-34b-chat-0205",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Control the diversity and randomness of generated results. The smaller the value, the more rigorous it is; the larger the value, the more divergent it is.",
                    "zh_Hans": "控制生成结果的多样性和随机性。数值越小，越严谨；数值越大，越发散。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 4000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "Control the randomness of generated results. The smaller the value, the weaker the randomness; the larger the value, the stronger the randomness. Generally speaking, you can adjust one of the two parameters top_p and temperature.",
                    "zh_Hans": "控制生成结果的随机性。数值越小，随机性越弱；数值越大，随机性越强。一般而言，top_p 和 temperature 两个参数选择一个进行调整即可。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0.01,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "2.5",
                "output": "2.5",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "yi-34b-chat-200k",
                "zh_Hans": "yi-34b-chat-200k"
              },
              "model": "yi-34b-chat-200k",
              "model_properties": {
                "context_size": 200000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.6,
                  "help": {
                    "en_US": "Control the diversity and randomness of generated results. The smaller the value, the more rigorous it is; the larger the value, the more divergent it is.",
                    "zh_Hans": "控制生成结果的多样性和随机性。数值越小，越严谨；数值越大，越发散。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 199950,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.9,
                  "help": {
                    "en_US": "Control the randomness of generated results. The smaller the value, the weaker the randomness; the larger the value, the stronger the randomness. Generally speaking, you can adjust one of the two parameters top_p and temperature.",
                    "zh_Hans": "控制生成结果的随机性。数值越小，随机性越弱；数值越大，随机性越强。一般而言，top_p 和 temperature 两个参数选择一个进行调整即可。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0.01,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "12",
                "output": "12",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "yi-large-turbo",
                "zh_Hans": "yi-large-turbo"
              },
              "model": "yi-large-turbo",
              "model_properties": {
                "context_size": 16384,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Control the diversity and randomness of generated results. The smaller the value, the more rigorous it is; the larger the value, the more divergent it is.",
                    "zh_Hans": "控制生成结果的多样性和随机性。数值越小，越严谨；数值越大，越发散。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 16384,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.9,
                  "help": {
                    "en_US": "Control the randomness of generated results. The smaller the value, the weaker the randomness; the larger the value, the stronger the randomness. Generally speaking, you can adjust one of the two parameters top_p and temperature.",
                    "zh_Hans": "控制生成结果的随机性。数值越小，随机性越弱；数值越大，随机性越强。一般而言，top_p 和 temperature 两个参数选择一个进行调整即可。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0.01,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "12",
                "output": "12",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "yi-large",
                "zh_Hans": "yi-large"
              },
              "model": "yi-large",
              "model_properties": {
                "context_size": 16384,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Control the diversity and randomness of generated results. The smaller the value, the more rigorous it is; the larger the value, the more divergent it is.",
                    "zh_Hans": "控制生成结果的多样性和随机性。数值越小，越严谨；数值越大，越发散。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 16384,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.9,
                  "help": {
                    "en_US": "Control the randomness of generated results. The smaller the value, the weaker the randomness; the larger the value, the stronger the randomness. Generally speaking, you can adjust one of the two parameters top_p and temperature.",
                    "zh_Hans": "控制生成结果的随机性。数值越小，随机性越弱；数值越大，随机性越强。一般而言，top_p 和 temperature 两个参数选择一个进行调整即可。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0.01,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "20",
                "output": "20",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "yi-lightning",
                "zh_Hans": "yi-lightning"
              },
              "model": "yi-lightning",
              "model_properties": {
                "context_size": 16384,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Control the diversity and randomness of generated results. The smaller the value, the more rigorous it is; the larger the value, the more divergent it is.",
                    "zh_Hans": "控制生成结果的多样性和随机性。数值越小，越严谨；数值越大，越发散。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 4000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.9,
                  "help": {
                    "en_US": "Control the randomness of generated results. The smaller the value, the weaker the randomness; the larger the value, the stronger the randomness. Generally speaking, you can adjust one of the two parameters top_p and temperature.",
                    "zh_Hans": "控制生成结果的随机性。数值越小，随机性越弱；数值越大，随机性越强。一般而言，top_p 和 temperature 两个参数选择一个进行调整即可。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0.01,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0.99",
                "output": "0.99",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "yi-medium-200k",
                "zh_Hans": "yi-medium-200k"
              },
              "model": "yi-medium-200k",
              "model_properties": {
                "context_size": 204800,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Control the diversity and randomness of generated results. The smaller the value, the more rigorous it is; the larger the value, the more divergent it is.",
                    "zh_Hans": "控制生成结果的多样性和随机性。数值越小，越严谨；数值越大，越发散。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 204800,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.9,
                  "help": {
                    "en_US": "Control the randomness of generated results. The smaller the value, the weaker the randomness; the larger the value, the stronger the randomness. Generally speaking, you can adjust one of the two parameters top_p and temperature.",
                    "zh_Hans": "控制生成结果的随机性。数值越小，随机性越弱；数值越大，随机性越强。一般而言，top_p 和 temperature 两个参数选择一个进行调整即可。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0.01,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "12",
                "output": "12",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "yi-medium",
                "zh_Hans": "yi-medium"
              },
              "model": "yi-medium",
              "model_properties": {
                "context_size": 16384,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Control the diversity and randomness of generated results. The smaller the value, the more rigorous it is; the larger the value, the more divergent it is.",
                    "zh_Hans": "控制生成结果的多样性和随机性。数值越小，越严谨；数值越大，越发散。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 16384,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.9,
                  "help": {
                    "en_US": "Control the randomness of generated results. The smaller the value, the weaker the randomness; the larger the value, the stronger the randomness. Generally speaking, you can adjust one of the two parameters top_p and temperature.",
                    "zh_Hans": "控制生成结果的随机性。数值越小，随机性越弱；数值越大，随机性越强。一般而言，top_p 和 temperature 两个参数选择一个进行调整即可。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0.01,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "2.5",
                "output": "2.5",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "yi-spark",
                "zh_Hans": "yi-spark"
              },
              "model": "yi-spark",
              "model_properties": {
                "context_size": 16384,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Control the diversity and randomness of generated results. The smaller the value, the more rigorous it is; the larger the value, the more divergent it is.",
                    "zh_Hans": "控制生成结果的多样性和随机性。数值越小，越严谨；数值越大，越发散。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 16384,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.9,
                  "help": {
                    "en_US": "Control the randomness of generated results. The smaller the value, the weaker the randomness; the larger the value, the stronger the randomness. Generally speaking, you can adjust one of the two parameters top_p and temperature.",
                    "zh_Hans": "控制生成结果的随机性。数值越小，随机性越弱；数值越大，随机性越强。一般而言，top_p 和 temperature 两个参数选择一个进行调整即可。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0.01,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "1",
                "output": "1",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "yi-vision",
                "zh_Hans": "yi-vision"
              },
              "model": "yi-vision",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Control the diversity and randomness of generated results. The smaller the value, the more rigorous it is; the larger the value, the more divergent it is.",
                    "zh_Hans": "控制生成结果的多样性和随机性。数值越小，越严谨；数值越大，越发散。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.9,
                  "help": {
                    "en_US": "Control the randomness of generated results. The smaller the value, the weaker the randomness; the larger the value, the stronger the randomness. Generally speaking, you can adjust one of the two parameters top_p and temperature.",
                    "zh_Hans": "控制生成结果的随机性。数值越小，随机性越弱；数值越大，随机性越强。一般而言，top_p 和 temperature 两个参数选择一个进行调整即可。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0.01,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "6",
                "output": "6",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "yi-vl-plus",
                "zh_Hans": "yi-vl-plus"
              },
              "model": "yi-vl-plus",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Control the diversity and randomness of generated results. The smaller the value, the more rigorous it is; the larger the value, the more divergent it is.",
                    "zh_Hans": "控制生成结果的多样性和随机性。数值越小，越严谨；数值越大，越发散。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 4000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "Control the randomness of generated results. The smaller the value, the weaker the randomness; the larger the value, the stronger the randomness. Generally speaking, you can adjust one of the two parameters top_p and temperature.",
                    "zh_Hans": "控制生成结果的随机性。数值越小，随机性越弱；数值越大，随机性越强。一般而言，top_p 和 temperature 两个参数选择一个进行调整即可。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0.01,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "6",
                "output": "6",
                "unit": "0.000001"
              }
            }
          ],
          "position": {
            "llm": [
              "yi-34b-chat-0205",
              "yi-34b-chat-200k",
              "yi-vl-plus",
              "yi-large",
              "yi-medium",
              "yi-vision",
              "yi-medium-200k",
              "yi-spark",
              "yi-large-turbo",
              "yi-lightning"
            ]
          },
          "provider": "yi",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Custom API endpoint URL",
                  "zh_Hans": "自定义 API endpoint 地址"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Base URL, e.g. https://api.lingyiwanwu.com/v1",
                  "zh_Hans": "Base URL, e.g. https://api.lingyiwanwu.com/v1"
                },
                "required": false,
                "show_on": [],
                "type": "text-input",
                "variable": "endpoint_url"
              }
            ]
          },
          "supported_model_types": [
            "llm"
          ]
        },
        "name": "yi",
        "org": "langgenius",
        "plugin_id": "langgenius/yi",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/yi.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-02-17T06:58:37Z",
        "version_updated_at": "2025-02-17T06:58:37Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "A tool for generating QR code (quick-response code) image.",
          "pt_BR": "A tool for generating QR code (quick-response code) image.",
          "zh_Hans": "一个二维码工具"
        },
        "category": "tool",
        "created_at": "2024-12-04T08:34:06Z",
        "endpoint": {},
        "icon": "langgenius/packages/qrcode/_assets/icon.svg",
        "index_id": "langgenius___qrcode",
        "install_count": 1366,
        "introduction": "## Overview\n\n**QRCode** is a simple yet effective tool for generating QR code images.\n\nIn **Dify**, QRCode allows you to quickly create QR codes for various types of content, such as URLs, text, or other information. This tool is ideal for sharing data visually and efficiently.\n\n## Configuration\n\nOpen the Plugin Marketplace, search for the QRCode tool, and install it to integrate it with your application.\n\n![](./_assets/qrcode-01.png)\n\n## Tool Features\n\nThe **QRCode** plugin includes a single, highly customizable action:\n\n### Generate QR Code\n\nGenerate a QR code image based on your specified content and configuration.\n\n**Input Variables:**\n\n* **Content Text for QR Code (Required):** Enter the text or data to encode in the QR code.\n* **Error Correction (Required):** Choose the error correction level (e.g., Low, Medium, Quartile, High) to ensure QR code readability even with partial damage.\n* **Border Size (Required):** Define the size of the border around the QR code (default: 2).\n* **Output:** A generated QR code image that encodes the specified content and adheres to the selected error correction level and border size.\n\nThis action provides flexibility for generating QR codes tailored to your specific needs, ensuring reliable encoding and clear presentation.\n\n## Usage\n\nQRCode can seamlessly integrate Chatflow / Workflow Apps and Agent Apps.\n\n### Chatflow / Workflow Apps\n\n1. Add the QRCode node to your Chatflow or Workflow pipeline.\n2. Configure the \"Generate QR Code\" action by specifying the content text for the QR code.\n3. Run the pipeline to generate the QR code and deliver it as part of your workflow.\n\n![](./_assets/qrcode-02.png)\n\n### Agent Apps\n\n1. Add the QRCode tool to your Agent application.\n2. Send the text or data you want to encode via the chatbox.\n3. The tool processes your input and returns the generated QR code image.\n\n![](./_assets/qrcode-03.png)\n\n## Use Cases\n\n* **Link Sharing:** Create QR codes for URLs to simplify link sharing.\n* **Event Promotions:** Generate QR codes for event invitations or ticketing.\n* **Business Cards:** Add QR codes to business cards for quick contact sharing.\n* **Content Access:** Access digital content such as documents, images, or videos.\n\nWith **QRCode**, you can quickly create visually shareable data representations, making connecting and sharing information easy.\n",
        "label": {
          "en_US": "QRCode",
          "pt_BR": "QRCode",
          "zh_Hans": "二维码工具"
        },
        "latest_package_identifier": "langgenius/qrcode:0.0.3@aa4ebdaf3794b31d04e768699026a682c9113b8e6da5fca480c352b5c9f7173a",
        "latest_version": "0.0.3",
        "model": {},
        "name": "qrcode",
        "org": "langgenius",
        "plugin_id": "langgenius/qrcode",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/qrcode.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "utilities"
          }
        ],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "Bowen Liang",
            "description": {
              "en_US": "A tool for generating QR code (quick-response code) image.",
              "pt_BR": "A tool for generating QR code (quick-response code) image.",
              "zh_Hans": "一个二维码工具"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "QRCode",
              "pt_BR": "QRCode",
              "zh_Hans": "二维码工具"
            },
            "name": "qrcode",
            "tags": [
              "utilities"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool for generating QR code image",
                  "pt_BR": "A tool for generating QR code image",
                  "zh_Hans": "一个用于生成二维码的工具"
                },
                "llm": "A tool for generating QR code image"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Bowen Liang",
                "label": {
                  "en_US": "Generate QR Code",
                  "pt_BR": "Generate QR Code",
                  "zh_Hans": "生成二维码"
                },
                "name": "qrcode_generator"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "content text for QR code",
                    "pt_BR": "二维码文本内容",
                    "zh_Hans": "二维码文本内容"
                  },
                  "label": {
                    "en_US": "content text for QR code",
                    "pt_BR": "content text for QR code",
                    "zh_Hans": "二维码文本内容"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "M",
                  "form": "form",
                  "human_description": {
                    "en_US": "Error Correction in L, M, Q or H, from low to high, the bigger size of generated QR code with the better error correction effect",
                    "pt_BR": "Error Correction in L, M, Q or H, from low to high, the bigger size of generated QR code with the better error correction effect",
                    "zh_Hans": "容错等级，可设置为低、中、偏高或高，从低到高，生成的二维码越大且容错效果越好"
                  },
                  "label": {
                    "en_US": "Error Correction",
                    "pt_BR": "Error Correction",
                    "zh_Hans": "容错等级"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "error_correction",
                  "options": [
                    {
                      "label": {
                        "en_US": "Low",
                        "pt_BR": "Low",
                        "zh_Hans": "低"
                      },
                      "value": "L"
                    },
                    {
                      "label": {
                        "en_US": "Medium",
                        "pt_BR": "Medium",
                        "zh_Hans": "中"
                      },
                      "value": "M"
                    },
                    {
                      "label": {
                        "en_US": "Quartile",
                        "pt_BR": "Quartile",
                        "zh_Hans": "偏高"
                      },
                      "value": "Q"
                    },
                    {
                      "label": {
                        "en_US": "High",
                        "pt_BR": "High",
                        "zh_Hans": "高"
                      },
                      "value": "H"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 2,
                  "form": "form",
                  "human_description": {
                    "en_US": "border size（default to 2）",
                    "pt_BR": "border size（default to 2）",
                    "zh_Hans": "边框粗细的格数（默认为2）"
                  },
                  "label": {
                    "en_US": "border size",
                    "pt_BR": "border size",
                    "zh_Hans": "边框粗细"
                  },
                  "llm_description": "",
                  "max": 100,
                  "min": 0,
                  "name": "border",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:11:46Z",
        "version_updated_at": "2025-02-17T07:11:46Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Weather query toolkit based on Open Weather",
          "pt_BR": "Kit de consulta de clima baseado no Open Weather",
          "zh_Hans": "基于open weather的天气查询工具包"
        },
        "category": "tool",
        "created_at": "2024-12-04T04:47:43Z",
        "endpoint": {},
        "icon": "langgenius/packages/openweather/_assets/icon.svg",
        "index_id": "langgenius___openweather",
        "install_count": 1308,
        "introduction": "# Open Weather query\n\n## Overview\n\nOpenWeather provides an API service offering access to global weather data. It allows developers to retrieve current conditions, forecasts, historical data, and other weather-related information. It supports various data formats and query parameters for different use cases.\n\n## Configuration\n\n### 1. Apply for Open Weather API Key\nPlease apply for an API Key on [Open Weather](https://home.openweathermap.org/api_keys).\n\n![](./_assets/weather_1.PNG)\n\n### 2. Get Open Weather query tools from Plugin Marketplace\nThe Open Weather query tools could be found at the Plugin Marketplace, please install it.\n\n![](./_assets/weather_2.PNG)\n\n### 3. Use the tool\nYou can use the Open Weather query tool in the following application types.\n\n![](./_assets/weather_3.PNG)\n\n#### Chatflow / Workflow applications\nBoth Chatflow and Workflow applications support adding an `Open Weather query` tool node.\n\n![](./_assets/weather_4.PNG)\n\n#### Agent applications\nAdd the `Open Weather query` tool in the Agent application, then enter the city name to call this tool.\n",
        "label": {
          "en_US": "Open weather query",
          "pt_BR": "Consulta de clima open weather",
          "zh_Hans": "Open Weather"
        },
        "latest_package_identifier": "langgenius/openweather:0.0.3@0fceac83f9ebaf32a2ae5892bb0e0988fca7456e96d845a90def713baa9f01db",
        "latest_version": "0.0.3",
        "model": {},
        "name": "openweather",
        "org": "langgenius",
        "plugin_id": "langgenius/openweather",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/openweather.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "weather"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "API Key",
                "pt_BR": "Fogo a chave",
                "zh_Hans": "API Key"
              },
              "name": "api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please enter your open weather API Key",
                "pt_BR": "Insira sua chave de API open weather",
                "zh_Hans": "请输入你的open weather API Key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://openweathermap.org"
            }
          ],
          "identity": {
            "author": "Onelevenvy",
            "description": {
              "en_US": "Weather query toolkit based on Open Weather",
              "pt_BR": "Kit de consulta de clima baseado no Open Weather",
              "zh_Hans": "基于open weather的天气查询工具包"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Open weather query",
              "pt_BR": "Consulta de clima open weather",
              "zh_Hans": "Open Weather"
            },
            "name": "openweather",
            "tags": [
              "weather"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Weather forecast inquiry",
                  "pt_BR": "Inquérito sobre previsão meteorológica",
                  "zh_Hans": "天气查询"
                },
                "llm": "A tool when you want to ask about the weather or weather-related question"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Onelevenvy",
                "label": {
                  "en_US": "Open Weather Query",
                  "pt_BR": "Previsão do tempo",
                  "zh_Hans": "天气查询"
                },
                "name": "weather"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Target city for weather forecast query",
                    "pt_BR": "Cidade de destino para consulta de previsão do tempo",
                    "zh_Hans": "天气预报查询的目标城市"
                  },
                  "label": {
                    "en_US": "city",
                    "pt_BR": "cidade",
                    "zh_Hans": "城市"
                  },
                  "llm_description": "If you don't know you can extract the city name from the question or you can reply：Please tell me your city. You have to extract the Chinese city name from the question.If the input region is in Chinese characters for China, it should be replaced with the corresponding English name, such as '北京' for correct input is 'Beijing'",
                  "max": null,
                  "min": null,
                  "name": "city",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "zh_cn",
                  "form": "form",
                  "human_description": {
                    "en_US": "language",
                    "pt_BR": "language",
                    "zh_Hans": "语言"
                  },
                  "label": {
                    "en_US": "language",
                    "pt_BR": "language",
                    "zh_Hans": "语言"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "lang",
                  "options": [
                    {
                      "label": {
                        "en_US": "cn",
                        "pt_BR": "cn",
                        "zh_Hans": "中国"
                      },
                      "value": "zh_cn"
                    },
                    {
                      "label": {
                        "en_US": "usa",
                        "pt_BR": "usa",
                        "zh_Hans": "美国"
                      },
                      "value": "en_us"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "metric",
                  "form": "form",
                  "human_description": {
                    "en_US": "units for temperature",
                    "pt_BR": "units for temperature",
                    "zh_Hans": "温度单位"
                  },
                  "label": {
                    "en_US": "units",
                    "pt_BR": "units",
                    "zh_Hans": "单位"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "units",
                  "options": [
                    {
                      "label": {
                        "en_US": "metric",
                        "pt_BR": "metric",
                        "zh_Hans": "℃"
                      },
                      "value": "metric"
                    },
                    {
                      "label": {
                        "en_US": "imperial",
                        "pt_BR": "imperial",
                        "zh_Hans": "℉"
                      },
                      "value": "imperial"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:16:15Z",
        "version_updated_at": "2025-02-17T07:16:15Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Innovative AI for Image Generation",
          "pt_BR": "Innovative AI for Image Generation",
          "zh_Hans": "用于图像生成的创新人工智能。"
        },
        "category": "tool",
        "created_at": "2024-12-04T08:49:22Z",
        "endpoint": {},
        "icon": "langgenius/packages/novitaai/_assets/icon.ico",
        "index_id": "langgenius___novitaai",
        "install_count": 1284,
        "introduction": "## Overview\n\n**Novita AI** is an innovative tool for image generation and model exploration.\n\nIn **Dify**, Novita AI allows you to create stunning visuals, explore model details, and generate seamless tile patterns for various design needs. With advanced AI capabilities, Novita AI simplifies creative processes and enhances workflows.\n\n## Configuration\n\nTo start using **Novita AI**, follow these steps:\n\n1. **Install the Novita AI Tool** Browser the Plugin Marketplace, search for the Novita AI tool, and install it to integrate it with your application.\n\n2. **Get a Novita AI API Key** Go the Novita AI API page, create a new API Key, and ensure your account has the necessary permissions to access its features.\n\n3. **Authorize Novita AI** In Dify, go to **Plugins > Novita AI > Authorize**. Enter your API Key to activate the tool.\n\n![](./_assets/novitaai-01.png)\n\n## Tool Features\n\nThe **Novita AI** plugin provides three main actions to power your creative projects:\n\n### 1. Novita AI Text to Image\n\nGenerate high-quality images from text prompts using Stable Diffusion models.\n\n* **Input:** Provide a descriptive text prompt to create your desired image.\n* **Output:** A visually stunning image based on your input.\n\n### 2. Novita AI Model Query\n\nRetrieve detailed information about public and private models.\n\n* **Input:** Specify the model you want to query.\n* **Output:** Information such as model specifications, capabilities, and availability.\n\n### 3. Novita AI Create Tile\n\nCreate seamless tile patterns for design purposes.\n\n* **Input:** Define the specifications or pattern requirements.\n* **Output:** A tiled image suitable for fabrics, wallpapers, or backgrounds.\n\n## Usage\n\nNovita AI can seamlessly integrate Chatflow / Workflow Apps and Agent Apps.\n\n### Chatflow / Workflow Apps\n\n1. Add the Novita AI node to your Chatflow or Workflow pipeline.\n2. Select one of the actions (e.g., Text to Image, Model Query, or Create Tile) and configure the inputs.\n3. Run the pipeline to generate images, retrieve model details, or produce seamless tiles for your use case.\n\n![](./_assets/novitaai-02.png)\n\n### Agent Apps\n\n1. Add the Novita AI tool to your Agent application.\n2. Send a text prompt, model query, or tile specification via the chat interface.\n3. The tool processes your input and returns the desired output (e.g., image, model details, or pattern).\n\n![](./_assets/novitaai-03.png)\n\n## Use Cases\n\n* **Image Generation:** Quickly create visuals for marketing, storytelling, or social media content.\n* **Model Exploration:** Access detailed information about AI models for research or development purposes.\n* **Seamless Patterns:** Design tiled images for fabrics, wallpapers, or user interface backgrounds.\n* **Creative Automation:** Streamline repetitive design tasks with AI-powered image generation.\n\nWith **Novita AI**, you can unlock new possibilities for creative expression and create a more efficient AI app.\n",
        "label": {
          "en_US": "Novita AI",
          "pt_BR": "Novita AI",
          "zh_Hans": "Novita AI"
        },
        "latest_package_identifier": "langgenius/novitaai:0.0.3@8fe7b67b075077a7cfae3d72a14a2fc0f58f333c151a867718ce1283457a9a42",
        "latest_version": "0.0.3",
        "model": {},
        "name": "novitaai",
        "org": "langgenius",
        "plugin_id": "langgenius/novitaai",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/novitaai.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "image"
          },
          {
            "name": "productivity"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "API Key",
                "pt_BR": "Chave API",
                "zh_Hans": "API 密钥"
              },
              "name": "api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please enter your Novita AI API key",
                "pt_BR": "Por favor, insira sua chave de API do Novita AI",
                "zh_Hans": "请输入你的 Novita AI API 密钥"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://novita.ai"
            }
          ],
          "identity": {
            "author": "Xiao Ley",
            "description": {
              "en_US": "Innovative AI for Image Generation",
              "pt_BR": "Innovative AI for Image Generation",
              "zh_Hans": "用于图像生成的创新人工智能。"
            },
            "icon": "icon.ico",
            "label": {
              "en_US": "Novita AI",
              "pt_BR": "Novita AI",
              "zh_Hans": "Novita AI"
            },
            "name": "novitaai",
            "tags": [
              "image",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Generate images from text prompts using Stable Diffusion models",
                  "zh_Hans": "通过 Stable Diffusion 模型根据文字提示生成图像"
                },
                "llm": "A tool for generate images from English text prompts."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Xiao Ley",
                "label": {
                  "en_US": "Novita AI Text to Image",
                  "zh_Hans": "Novita AI 文字转图像"
                },
                "name": "novitaai_txt2img"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Specify the name of the model checkpoint. You can use the \"Novita AI Model Query\" tool to query the corresponding \"sd_name\" value (type select \"Checkpoint\").",
                    "zh_Hans": "指定 Model Checkpoint 名称。可通过“Novita AI 模型请求”工具查询对应的“sd_name”值（类型选择“Checkpoint”）。"
                  },
                  "label": {
                    "en_US": "model name",
                    "zh_Hans": "模块名字"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "model_name",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Text input required to guide the image generation, divided by `,`, Range [1, 1024]. Only English input is allowed.",
                    "zh_Hans": "生成图像的正向提示，用 `,` 分隔，范围 [1, 1024]。仅允许输入英文。"
                  },
                  "label": {
                    "en_US": "prompt",
                    "zh_Hans": "提示"
                  },
                  "llm_description": "Image prompt of Novita AI, you should describe the image you want to generate as a list of words as possible as detailed, divided by `,`, Range [1, 1024]. Only English input is allowed.",
                  "max": null,
                  "min": null,
                  "name": "prompt",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Text input that will not guide the image generation, divided by `,`, Range [1, 1024]. Only English input is allowed.",
                    "zh_Hans": "生成图像的负向提示，用 `,` 分隔，范围 [1, 1024]。仅允许输入英文。"
                  },
                  "label": {
                    "en_US": "negative prompt",
                    "zh_Hans": "负向提示"
                  },
                  "llm_description": "Image negative prompt of Novita AI, divided by `,`, Range [1, 1024]. Only English input is allowed.",
                  "max": null,
                  "min": null,
                  "name": "negative_prompt",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 512,
                  "form": "form",
                  "human_description": {
                    "en_US": "Image width, Range [128, 2048].",
                    "zh_Hans": "图像宽度，范围 [128, 2048]"
                  },
                  "label": {
                    "en_US": "width",
                    "zh_Hans": "宽"
                  },
                  "llm_description": "",
                  "max": 2048,
                  "min": 128,
                  "name": "width",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 512,
                  "form": "form",
                  "human_description": {
                    "en_US": "Image height, Range [128, 2048].",
                    "zh_Hans": "图像高度，范围 [128, 2048]"
                  },
                  "label": {
                    "en_US": "height",
                    "zh_Hans": "高"
                  },
                  "llm_description": "",
                  "max": 2048,
                  "min": 128,
                  "name": "height",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 1,
                  "form": "form",
                  "human_description": {
                    "en_US": "Image num, Range [1, 8].",
                    "zh_Hans": "图片数，范围 [1, 8]"
                  },
                  "label": {
                    "en_US": "image num",
                    "zh_Hans": "图片数"
                  },
                  "llm_description": "",
                  "max": 8,
                  "min": 1,
                  "name": "image_num",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 20,
                  "form": "form",
                  "human_description": {
                    "en_US": "The number of denoising steps. More steps usually can produce higher quality images, but take more time to generate, Range [1, 100].",
                    "zh_Hans": "生成步数。更多步数可能会产生更好的图像，但生成时间更长，范围 [1, 100]"
                  },
                  "label": {
                    "en_US": "steps",
                    "zh_Hans": "步数"
                  },
                  "llm_description": "",
                  "max": 100,
                  "min": 1,
                  "name": "steps",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": -1,
                  "form": "form",
                  "human_description": {
                    "en_US": "A seed is a number from which Stable Diffusion generates noise, which, makes generation deterministic. Using the same seed and set of parameters will produce identical image each time, minimum -1.",
                    "zh_Hans": "种子是 Stable Diffusion 生成噪声的数字，它使生成具有确定性。使用相同的种子和参数设置将生成每次生成相同的图像，最小值 -1。"
                  },
                  "label": {
                    "en_US": "seed",
                    "zh_Hans": "种子"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "This parameter indicates the number of layers to stop from the bottom during optimization, so clip_skip on 2 would mean, that in SD1.x model where the CLIP has 12 layers, you would stop at 10th layer, Range [1, 12], get reference at https://novita.ai/get-started/Misc.html#what-s-clip-skip.",
                    "zh_Hans": "此参数表示优化过程中从底部停止的层数，因此 clip_skip 的值为 2，表示在 SD1.x 模型中，CLIP 有 12 层，你将停止在 10 层，范围 [1, 12]，参考 https://novita.ai/get-started/Misc.html#what-s-clip-skip。"
                  },
                  "label": {
                    "en_US": "clip skip",
                    "zh_Hans": "层跳过数"
                  },
                  "llm_description": "",
                  "max": 12,
                  "min": 1,
                  "name": "clip_skip",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "7.5",
                  "form": "form",
                  "human_description": {
                    "en_US": "This setting says how close the Stable Diffusion will listen to your prompt, higer guidance forces the model to better follow the prompt, but result in lower quality output.Range [1, 30].",
                    "zh_Hans": "此设置表明 Stable Diffusion 如何听从您的提示，较高的 guidance_scale 会强制模型更好跟随提示，但结果会更低质量输出。范围 [1.0, 30.0]。"
                  },
                  "label": {
                    "en_US": "guidance scale",
                    "zh_Hans": "提示词遵守程度"
                  },
                  "llm_description": "",
                  "max": 30,
                  "min": 1,
                  "name": "guidance_scale",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "This parameter determines the denoising algorithm employed during the sampling phase of Stable Diffusion. Get reference at https://novita.ai/get-started/Misc.htmll#what-is-samplers.",
                    "zh_Hans": "此参数决定了在稳定扩散采样阶段使用的去噪算法。参考 https://novita.ai/get-started/Misc.htmll#what-is-samplers。"
                  },
                  "label": {
                    "en_US": "sampler name",
                    "zh_Hans": "采样器名称"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "sampler_name",
                  "options": [
                    {
                      "label": {
                        "en_US": "Euler a",
                        "zh_Hans": "Euler a"
                      },
                      "value": "Euler a"
                    },
                    {
                      "label": {
                        "en_US": "Euler",
                        "zh_Hans": "Euler"
                      },
                      "value": "Euler"
                    },
                    {
                      "label": {
                        "en_US": "LMS",
                        "zh_Hans": "LMS"
                      },
                      "value": "LMS"
                    },
                    {
                      "label": {
                        "en_US": "Heun",
                        "zh_Hans": "Heun"
                      },
                      "value": "Heun"
                    },
                    {
                      "label": {
                        "en_US": "DPM2",
                        "zh_Hans": "DPM2"
                      },
                      "value": "DPM2"
                    },
                    {
                      "label": {
                        "en_US": "DPM2 a",
                        "zh_Hans": "DPM2 a"
                      },
                      "value": "DPM2 a"
                    },
                    {
                      "label": {
                        "en_US": "DPM++ 2S a",
                        "zh_Hans": "DPM++ 2S a"
                      },
                      "value": "DPM++ 2S a"
                    },
                    {
                      "label": {
                        "en_US": "DPM++ 2M",
                        "zh_Hans": "DPM++ 2M"
                      },
                      "value": "DPM++ 2M"
                    },
                    {
                      "label": {
                        "en_US": "DPM++ SDE",
                        "zh_Hans": "DPM++ SDE"
                      },
                      "value": "DPM++ SDE"
                    },
                    {
                      "label": {
                        "en_US": "DPM fast",
                        "zh_Hans": "DPM fast"
                      },
                      "value": "DPM fast"
                    },
                    {
                      "label": {
                        "en_US": "DPM adaptive",
                        "zh_Hans": "DPM adaptive"
                      },
                      "value": "DPM adaptive"
                    },
                    {
                      "label": {
                        "en_US": "LMS Karras",
                        "zh_Hans": "LMS Karras"
                      },
                      "value": "LMS Karras"
                    },
                    {
                      "label": {
                        "en_US": "DPM2 Karras",
                        "zh_Hans": "DPM2 Karras"
                      },
                      "value": "DPM2 Karras"
                    },
                    {
                      "label": {
                        "en_US": "DPM2 a Karras",
                        "zh_Hans": "DPM2 a Karras"
                      },
                      "value": "DPM2 a Karras"
                    },
                    {
                      "label": {
                        "en_US": "DPM++ 2S a Karras",
                        "zh_Hans": "DPM++ 2S a Karras"
                      },
                      "value": "DPM++ 2S a Karras"
                    },
                    {
                      "label": {
                        "en_US": "DPM++ 2M Karras",
                        "zh_Hans": "DPM++ 2M Karras"
                      },
                      "value": "DPM++ 2M Karras"
                    },
                    {
                      "label": {
                        "en_US": "DPM++ SDE Karras",
                        "zh_Hans": "DPM++ SDE Karras"
                      },
                      "value": "DPM++ SDE Karras"
                    },
                    {
                      "label": {
                        "en_US": "DDIM",
                        "zh_Hans": "DDIM"
                      },
                      "value": "DDIM"
                    },
                    {
                      "label": {
                        "en_US": "PLMS",
                        "zh_Hans": "PLMS"
                      },
                      "value": "PLMS"
                    },
                    {
                      "label": {
                        "en_US": "UniPC",
                        "zh_Hans": "UniPC"
                      },
                      "value": "UniPC"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "VAE(Variational Autoencoder), get reference at https://novita.ai/get-started/Misc.html#what-s-variational-autoencoders-vae. You can use the \"Novita AI Model Query\" tool to query the corresponding \"sd_name\" value (type select \"VAE\").",
                    "zh_Hans": "VAE（变分自编码器），参考 https://novita.ai/get-started/Misc.html#what-s-variational-autoencoders-vae。可通过“Novita AI 模型请求”工具查询对应的“sd_name”值（类型选择“VAE”）。"
                  },
                  "label": {
                    "en_US": "sd vae",
                    "zh_Hans": "sd vae"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "sd_vae",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "LoRA models. Currenlty supports up to 5 LoRAs. You can use the \"Novita AI Model Query\" tool to query the corresponding \"sd_name\" value (type select \"LoRA\"). Input template is \"<sd_name>,<strength [0-1.0]>;<sd_name>,<strength [0-1.0]>;...\". Such as\"Film Grain style_331903,0.5;DoggystylePOV_9600,0.5\"",
                    "zh_Hans": "LoRA 模型。目前仅支持 5 个 LoRA。可通过“Novita AI 模型请求”工具查询对应的“sd_name”值（类型选择“LoRA”）。输入模板：“<sd_name>,<strength [0-1.0]>;<sd_name>,<strength [0-1.0]>;...”，例如：“Film Grain style_331903,0.5;DoggystylePOV_9600,0.5”"
                  },
                  "label": {
                    "en_US": "loRAs",
                    "zh_Hans": "loRAs"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "loras",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Textual Inversion is a training method for personalizing models by learning new text embeddings from a few example images, currenlty supports up to 5 embeddings. You can use the \"Novita AI Model Query\" tool to query the corresponding \"sd_name\" value (type select \"Text Inversion\"). Input template is \"<sd_name>;<sd_name>;...\". Such as \"EasyNegativeV2_75525;AS-YoungerV2\"",
                    "zh_Hans": "文本反转是一种通过从一些示例图像中学习新的文本嵌入来个性化模型的训练方法，目前仅支持 5 个嵌入。可通过“Novita AI 模型请求”工具查询对应的“sd_name”值（类型选择“Text Inversion”）。输入模板：“<sd_name>;<sd_name>;...”，例如：“EasyNegativeV2_75525;AS-YoungerV2”"
                  },
                  "label": {
                    "en_US": "text embeddings",
                    "zh_Hans": "文本嵌入"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "embeddings",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Use high resolution image fix. Input template is \"<target_width [128, 4096]>,<target_height [128, 4096]>,<strength [0, 1.0]>,<upscaler (optional, selec type, `RealESRGAN_x4plus_anime_6B`, `RealESRNet_x4plus` or `Latent`)>\". Such as \"1024,1024,0.8\", \"1024,1024,0.8,RealESRGAN_x4plus_anime_6B\"",
                    "zh_Hans": "使用高分辨率修复。输入模板 “<target_width [128, 4096]>,<target_height [128, 4096]>,<strength [0, 1.0]>,<upscaler (可选, 选项类型, `RealESRGAN_x4plus_anime_6B`, `RealESRNet_x4plus` 或 `Latent`)>”。例如 “1024,1024,0.8”、“1024,1024,0.8,RealESRGAN_x4plus_anime_6B”"
                  },
                  "label": {
                    "en_US": "hires fix",
                    "zh_Hans": "高分辨率修复"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "hires_fix",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "This parameter in the context of a refiner allows you to set the extent to which the refiner alters the output of a model. When set to 0, the refiner has no effect; at 1, it's fully active. Intermediate values like 0.5 provide a balanced effect, where the refiner is moderately engaged, enhancing or adjusting the output without dominating the original model's characteristics. This setting is particularly useful for fine-tuning the output to achieve a desired balance between refinement and the original generative features, Range [0, 1.0]. Is not all models support refiners!",
                    "zh_Hans": "此参数允许您设置重采样更改模型输出的程度。当设置为0时，重采样不起作用；1时，它处于完全活动状态。像0.5这样的中间值提供了一种平衡效果，其中重采样适度参与，增强或调整输出，而不会主导原始模型的特性。此设置对于微调输出特别有用，范围 [0, 1.0]。不是所有模型都支持重采样！"
                  },
                  "label": {
                    "en_US": "refiner switch at",
                    "zh_Hans": "重采样参与时刻"
                  },
                  "llm_description": "",
                  "max": 1,
                  "min": 0,
                  "name": "refiner_switch_at",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "jpeg",
                  "form": "form",
                  "human_description": {
                    "en_US": "Response image type, png or jpeg",
                    "zh_Hans": "响应图像类型，png 或 jpeg"
                  },
                  "label": {
                    "en_US": "response image type",
                    "zh_Hans": "响应图像类型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "response_image_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "jpeg",
                        "zh_Hans": "jpeg"
                      },
                      "value": "jpeg"
                    },
                    {
                      "label": {
                        "en_US": "png",
                        "zh_Hans": "png"
                      },
                      "value": "png"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Enable enterprise plan",
                    "zh_Hans": "启用企业版计划"
                  },
                  "label": {
                    "en_US": "enterprise plan enabled",
                    "zh_Hans": "企业版计划启用"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "enabled_enterprise_plan",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Enable nsfw detection",
                    "zh_Hans": "启用 NSFW 检测"
                  },
                  "label": {
                    "en_US": "enable nsfw detection",
                    "zh_Hans": "启用 NSFW 检测"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "enable_nsfw_detection",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": "2",
                  "form": "form",
                  "human_description": {
                    "en_US": "Nsfw detection level, from low to high",
                    "zh_Hans": "NSFW 检测级别，越高越严格"
                  },
                  "label": {
                    "en_US": "nsfw detection level",
                    "zh_Hans": "NSFW 检测级别"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "nsfw_detection_level",
                  "options": [
                    {
                      "label": {
                        "en_US": "low",
                        "zh_Hans": "低"
                      },
                      "value": "0"
                    },
                    {
                      "label": {
                        "en_US": "middle",
                        "zh_Hans": "中"
                      },
                      "value": "1"
                    },
                    {
                      "label": {
                        "en_US": "high",
                        "zh_Hans": "高"
                      },
                      "value": "2"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Retrieve information on both public and private models. It allows users to access details such as model specifications, status, and usage guidelines, ensuring comprehensive insight into the available modeling resources.",
                  "zh_Hans": "检索公开和私有模型信息。它允许用户访问模型规范、状态和使用指南等详细信息，确保了解可用的建模资源。"
                },
                "llm": "A tool for retrieve information on both public and private Novita AI models."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Xiao Ley",
                "label": {
                  "en_US": "Novita AI Model Query",
                  "zh_Hans": "Novita AI 模型查询"
                },
                "name": "novitaai_modelquery"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Seaching the content of sd_name, name, tags.",
                    "zh_Hans": "搜索 sd_name、name、tags 中的内容"
                  },
                  "label": {
                    "en_US": "query",
                    "zh_Hans": "查询"
                  },
                  "llm_description": "Enter the content to search",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "first sd_name",
                  "form": "form",
                  "human_description": {
                    "en_US": "The format of result",
                    "zh_Hans": "请求结果的格式"
                  },
                  "label": {
                    "en_US": "result format",
                    "zh_Hans": "结果格式"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "result_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "first sd_name",
                        "zh_Hans": "第一个 sd_name"
                      },
                      "value": "first sd_name"
                    },
                    {
                      "label": {
                        "en_US": "first name and sd_name pair: {name, sd_name}",
                        "zh_Hans": "第一个 name sd_name 组合：{name, sd_name}"
                      },
                      "value": "first name sd_name pair"
                    },
                    {
                      "label": {
                        "en_US": "sd_name array: [sd_name]",
                        "zh_Hans": "sd_name 数组：[sd_name]"
                      },
                      "value": "sd_name array"
                    },
                    {
                      "label": {
                        "en_US": "name array: [name]",
                        "zh_Hans": "name 数组：[name]"
                      },
                      "value": "name array"
                    },
                    {
                      "label": {
                        "en_US": "name and sd_name pair array: [{name, sd_name}]",
                        "zh_Hans": "name sd_name 组合数组：[{name, sd_name}]"
                      },
                      "value": "name sd_name pair array"
                    },
                    {
                      "label": {
                        "en_US": "whole info array",
                        "zh_Hans": "完整信息数组"
                      },
                      "value": "whole info array"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "unspecified",
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether the model is public or private",
                    "zh_Hans": "模型是否公开或私有"
                  },
                  "label": {
                    "en_US": "visibility",
                    "zh_Hans": "可见性"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "visibility",
                  "options": [
                    {
                      "label": {
                        "en_US": "Unspecified",
                        "zh_Hans": "未指定"
                      },
                      "value": "unspecified"
                    },
                    {
                      "label": {
                        "en_US": "Public",
                        "zh_Hans": "公开"
                      },
                      "value": "public"
                    },
                    {
                      "label": {
                        "en_US": "Private",
                        "zh_Hans": "私有"
                      },
                      "value": "private"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "unspecified",
                  "form": "form",
                  "human_description": {
                    "en_US": "Source of the model",
                    "zh_Hans": "模型来源"
                  },
                  "label": {
                    "en_US": "source",
                    "zh_Hans": "来源"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "source",
                  "options": [
                    {
                      "label": {
                        "en_US": "Unspecified",
                        "zh_Hans": "未指定"
                      },
                      "value": "unspecified"
                    },
                    {
                      "label": {
                        "en_US": "Civitai",
                        "zh_Hans": "Civitai"
                      },
                      "value": "civitai"
                    },
                    {
                      "label": {
                        "en_US": "Training",
                        "zh_Hans": "训练"
                      },
                      "value": "training"
                    },
                    {
                      "label": {
                        "en_US": "Uploading",
                        "zh_Hans": "上传"
                      },
                      "value": "uploading"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "unspecified",
                  "form": "form",
                  "human_description": {
                    "en_US": "Specifies the type of models to include in the query.",
                    "zh_Hans": "指定要查询的模型类型"
                  },
                  "label": {
                    "en_US": "type",
                    "zh_Hans": "类型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "type",
                  "options": [
                    {
                      "label": {
                        "en_US": "Unspecified",
                        "zh_Hans": "未指定"
                      },
                      "value": "unspecified"
                    },
                    {
                      "label": {
                        "en_US": "Checkpoint",
                        "zh_Hans": "Checkpoint"
                      },
                      "value": "checkpoint"
                    },
                    {
                      "label": {
                        "en_US": "LoRA",
                        "zh_Hans": "LoRA"
                      },
                      "value": "lora"
                    },
                    {
                      "label": {
                        "en_US": "VAE",
                        "zh_Hans": "VAE"
                      },
                      "value": "vae"
                    },
                    {
                      "label": {
                        "en_US": "ControlNet",
                        "zh_Hans": "ControlNet"
                      },
                      "value": "controlnet"
                    },
                    {
                      "label": {
                        "en_US": "Upscaler",
                        "zh_Hans": "Upscaler"
                      },
                      "value": "upscaler"
                    },
                    {
                      "label": {
                        "en_US": "Textual inversion",
                        "zh_Hans": "Textual Inversion"
                      },
                      "value": "textualinversion"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "unspecified",
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether sdxl model or not. Setting this parameter to `true` includes only sdxl models in the query results, which are typically large-scale, high-performance models designed for extensive data processing tasks. Conversely, setting it to `false` excludes these models from the results. If left unspecified, the filter will not discriminate based on the sdxl classification, including all model types in the search results.",
                    "zh_Hans": "是否是 SDXL 模型。设置此参数为 `是`，只查询 SDXL 模型，并包含大规模，高性能的模型。相反，设置为 `否`，将排除这些模型。如果未指定，将不会根据 SDXL 分类进行区分，包括查询结果中的所有模型类型。"
                  },
                  "label": {
                    "en_US": "is sdxl",
                    "zh_Hans": "是否是 SDXL"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "is_sdxl",
                  "options": [
                    {
                      "label": {
                        "en_US": "Unspecified",
                        "zh_Hans": "未指定"
                      },
                      "value": "unspecified"
                    },
                    {
                      "label": {
                        "en_US": "True",
                        "zh_Hans": "是"
                      },
                      "value": "true"
                    },
                    {
                      "label": {
                        "en_US": "False",
                        "zh_Hans": "否"
                      },
                      "value": "false"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "This feature produces images designed for seamless tiling, ideal for creating continuous patterns in fabrics, wallpapers, and various textures.",
                  "zh_Hans": "该功能生成设计用于无缝平铺的图像，非常适合用于制作连续图案的织物、壁纸和各种纹理。"
                },
                "llm": "A tool for create images designed for seamless tiling, ideal for creating continuous patterns in fabrics, wallpapers, and various textures."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Xiao Ley",
                "label": {
                  "en_US": "Novita AI Create Tile",
                  "zh_Hans": "Novita AI 创建平铺图案"
                },
                "name": "novitaai_createtile"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Positive prompt word of the created tile, divided by `,`, Range [1, 512]. Only English input is allowed.",
                    "zh_Hans": "生成平铺图案的正向提示，用 `,` 分隔，范围 [1, 512]。仅允许输入英文。"
                  },
                  "label": {
                    "en_US": "prompt",
                    "zh_Hans": "提示"
                  },
                  "llm_description": "Image prompt of Novita AI, you should describe the image you want to generate as a list of words as possible as detailed, divided by `,`, Range [1, 512]. Only English input is allowed.",
                  "max": null,
                  "min": null,
                  "name": "prompt",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Negtive prompt word of the created tile, divided by `,`, Range [1, 512]. Only English input is allowed.",
                    "zh_Hans": "生成平铺图案的负向提示，用 `,` 分隔，范围 [1, 512]。仅允许输入英文。"
                  },
                  "label": {
                    "en_US": "negative prompt",
                    "zh_Hans": "负向提示"
                  },
                  "llm_description": "Image negative prompt of Novita AI, divided by `,`, Range [1, 512]. Only English input is allowed.",
                  "max": null,
                  "min": null,
                  "name": "negative_prompt",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 256,
                  "form": "form",
                  "human_description": {
                    "en_US": "Image width, Range [128, 1024].",
                    "zh_Hans": "图像宽度，范围 [128, 1024]"
                  },
                  "label": {
                    "en_US": "width",
                    "zh_Hans": "宽"
                  },
                  "llm_description": "",
                  "max": 1024,
                  "min": 128,
                  "name": "width",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 256,
                  "form": "form",
                  "human_description": {
                    "en_US": "Image height, Range [128, 1024].",
                    "zh_Hans": "图像高度，范围 [128, 1024]"
                  },
                  "label": {
                    "en_US": "height",
                    "zh_Hans": "高"
                  },
                  "llm_description": "",
                  "max": 1024,
                  "min": 128,
                  "name": "height",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "jpeg",
                  "form": "form",
                  "human_description": {
                    "en_US": "Response image type, png or jpeg",
                    "zh_Hans": "响应图像类型，png 或 jpeg"
                  },
                  "label": {
                    "en_US": "response image type",
                    "zh_Hans": "响应图像类型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "response_image_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "jpeg",
                        "zh_Hans": "jpeg"
                      },
                      "value": "jpeg"
                    },
                    {
                      "label": {
                        "en_US": "png",
                        "zh_Hans": "png"
                      },
                      "value": "png"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:06:59Z",
        "version_updated_at": "2025-02-17T07:06:59Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "A tool for maths.",
          "pt_BR": "A tool for maths.",
          "zh_Hans": "一个用于数学计算的工具。"
        },
        "category": "tool",
        "created_at": "2024-11-29T06:41:16Z",
        "endpoint": {},
        "icon": "langgenius/packages/maths/_assets/icon.svg",
        "index_id": "langgenius___maths",
        "install_count": 1227,
        "introduction": "# Overview\nMath Expression Evaluator online is an online tool that allows you to enter a math expression and get its value. It could evaluate math expression, like a calculator on steroid (you can use function like sqrt, cos, sin, abs, ...).\n\nTo use this math expression evaluator, you only need to enter the math expression that you want to evaluate in the input field. Then it will show you the value of the expression.\n\n# Configure\n1. Install Maths from Dify Marketplace.\n![](_assets/maths_install.png)\n2. Add Maths to your workflow.\n3. Fill in the math expression. For example cos(60).\n![](_assets/maths_configure.png)\n![](_assets/maths_test.png)\n4. For further help, please refer to the readme of the tool.",
        "label": {
          "en_US": "Maths",
          "pt_BR": "Maths",
          "zh_Hans": "数学工具"
        },
        "latest_package_identifier": "langgenius/maths:0.0.3@672d22e7aca6f346bf6bf9c5d31e2ce4634d295f61b6aa1f5ee2632f4ed3fdb0",
        "latest_version": "0.0.3",
        "model": {},
        "name": "maths",
        "org": "langgenius",
        "plugin_id": "langgenius/maths",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/maths.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "utilities"
          }
        ],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "Bowen Liang",
            "description": {
              "en_US": "A tool for maths.",
              "pt_BR": "A tool for maths.",
              "zh_Hans": "一个用于数学计算的工具。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Maths",
              "pt_BR": "Maths",
              "zh_Hans": "数学工具"
            },
            "name": "maths",
            "tags": [
              "utilities",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool for evaluating an math expression, calculated locally with NumExpr.",
                  "pt_BR": "A tool for evaluating an math expression, calculated locally with NumExpr.",
                  "zh_Hans": "一个用于计算数学表达式的工具，表达式将通过NumExpr本地执行。"
                },
                "llm": "A tool for evaluating an math expression."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Bowen Liang",
                "label": {
                  "en_US": "Evaluate Math Expression",
                  "pt_BR": "Evaluate Math Expression",
                  "zh_Hans": "计算数学表达式"
                },
                "name": "eval_expression"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Math Expression",
                    "pt_BR": "Math Expression",
                    "zh_Hans": "数学计算表达式"
                  },
                  "label": {
                    "en_US": "Math Expression",
                    "pt_BR": "Math Expression",
                    "zh_Hans": "数学计算表达式"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "expression",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:13:26Z",
        "version_updated_at": "2025-02-17T07:13:26Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Models provided by MistralAI, such as open-mistral-7b and mistral-large-latest.",
          "zh_Hans": "MistralAI 提供的模型，例如 open-mistral-7b 和 mistral-large-latest。"
        },
        "category": "model",
        "created_at": "2024-12-05T06:26:52Z",
        "endpoint": {},
        "icon": "langgenius/packages/mistralai/_assets/icon_s_en.png",
        "index_id": "langgenius___mistralai",
        "install_count": 1212,
        "introduction": "# Overview\nMistral AI provides a cutting-edge platform for developing and deploying open-weight generative AI models. It supports developers and businesses by offering customizable AI solutions that can be fine-tuned to meet specific needs. Mistral AI's flagship models are Mistral 7B and Mixtral 8x7B.\n\n# Configure\nAfter installation, you need to get API keys from [MistralAI](https://console.mistral.ai/api-keys/) and setup in Settings -> Model Provider.\n\n![](_assets/mistralai.PNG)",
        "label": {
          "en_US": "MistralAI"
        },
        "latest_package_identifier": "langgenius/mistralai:0.0.2@7790fbca054b5b2a797634e187b06729b5efeed0e8fe2f610ccc87bfddb88721",
        "latest_version": "0.0.2",
        "model": {
          "background": "#FFFFFF",
          "configurate_methods": [
            "predefined-model"
          ],
          "description": {
            "en_US": "Models provided by MistralAI, such as open-mistral-7b and mistral-large-latest.",
            "zh_Hans": "MistralAI 提供的模型，例如 open-mistral-7b 和 mistral-large-latest。"
          },
          "help": {
            "title": {
              "en_US": "Get your API Key from MistralAI",
              "zh_Hans": "从 MistralAI 获取 API Key"
            },
            "url": {
              "en_US": "https://console.mistral.ai/api-keys/"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.png"
          },
          "icon_small": {
            "en_US": "icon_s_en.png"
          },
          "label": {
            "en_US": "MistralAI"
          },
          "model_credential_schema": null,
          "models": [
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "codestral-latest",
                "zh_Hans": "codestral-latest"
              },
              "model": "codestral-latest",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "Whether to inject a safety prompt before all conversations.",
                    "zh_Hans": "是否开启提示词审查"
                  },
                  "label": {
                    "en_US": "SafePrompt",
                    "zh_Hans": "提示词审查"
                  },
                  "max": null,
                  "min": null,
                  "name": "safe_prompt",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "The seed to use for random sampling. If set, different calls will generate deterministic results.",
                    "zh_Hans": "当开启随机数种子以后，你可以通过指定一个固定的种子来使得回答结果更加稳定"
                  },
                  "label": {
                    "en_US": "RandomSeed",
                    "zh_Hans": "随机数种子"
                  },
                  "max": 2147483647,
                  "min": 0,
                  "name": "random_seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.008",
                "output": "0.024",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "mistral-embed",
                "zh_Hans": "mistral-embed"
              },
              "model": "mistral-embed",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 1024,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "Whether to inject a safety prompt before all conversations.",
                    "zh_Hans": "是否开启提示词审查"
                  },
                  "label": {
                    "en_US": "SafePrompt",
                    "zh_Hans": "提示词审查"
                  },
                  "max": null,
                  "min": null,
                  "name": "safe_prompt",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "The seed to use for random sampling. If set, different calls will generate deterministic results.",
                    "zh_Hans": "当开启随机数种子以后，你可以通过指定一个固定的种子来使得回答结果更加稳定"
                  },
                  "label": {
                    "en_US": "RandomSeed",
                    "zh_Hans": "随机数种子"
                  },
                  "max": 2147483647,
                  "min": 0,
                  "name": "random_seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.008",
                "output": "0.024",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "mistral-large-latest",
                "zh_Hans": "mistral-large-latest"
              },
              "model": "mistral-large-latest",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 8000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "Whether to inject a safety prompt before all conversations.",
                    "zh_Hans": "是否开启提示词审查"
                  },
                  "label": {
                    "en_US": "SafePrompt",
                    "zh_Hans": "提示词审查"
                  },
                  "max": null,
                  "min": null,
                  "name": "safe_prompt",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "The seed to use for random sampling. If set, different calls will generate deterministic results.",
                    "zh_Hans": "当开启随机数种子以后，你可以通过指定一个固定的种子来使得回答结果更加稳定"
                  },
                  "label": {
                    "en_US": "RandomSeed",
                    "zh_Hans": "随机数种子"
                  },
                  "max": 2147483647,
                  "min": 0,
                  "name": "random_seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.008",
                "output": "0.024",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "mistral-medium-latest",
                "zh_Hans": "mistral-medium-latest"
              },
              "model": "mistral-medium-latest",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 8000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "Whether to inject a safety prompt before all conversations.",
                    "zh_Hans": "是否开启提示词审查"
                  },
                  "label": {
                    "en_US": "SafePrompt",
                    "zh_Hans": "提示词审查"
                  },
                  "max": null,
                  "min": null,
                  "name": "safe_prompt",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "The seed to use for random sampling. If set, different calls will generate deterministic results.",
                    "zh_Hans": "当开启随机数种子以后，你可以通过指定一个固定的种子来使得回答结果更加稳定"
                  },
                  "label": {
                    "en_US": "RandomSeed",
                    "zh_Hans": "随机数种子"
                  },
                  "max": 2147483647,
                  "min": 0,
                  "name": "random_seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0027",
                "output": "0.0081",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "mistral-small-latest",
                "zh_Hans": "mistral-small-latest"
              },
              "model": "mistral-small-latest",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 8000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "Whether to inject a safety prompt before all conversations.",
                    "zh_Hans": "是否开启提示词审查"
                  },
                  "label": {
                    "en_US": "SafePrompt",
                    "zh_Hans": "提示词审查"
                  },
                  "max": null,
                  "min": null,
                  "name": "safe_prompt",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "The seed to use for random sampling. If set, different calls will generate deterministic results.",
                    "zh_Hans": "当开启随机数种子以后，你可以通过指定一个固定的种子来使得回答结果更加稳定"
                  },
                  "label": {
                    "en_US": "RandomSeed",
                    "zh_Hans": "随机数种子"
                  },
                  "max": 2147483647,
                  "min": 0,
                  "name": "random_seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.002",
                "output": "0.006",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "open-codestral-mamba",
                "zh_Hans": "open-codestral-mamba"
              },
              "model": "open-codestral-mamba",
              "model_properties": {
                "context_size": 256000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 16384,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "Whether to inject a safety prompt before all conversations.",
                    "zh_Hans": "是否开启提示词审查"
                  },
                  "label": {
                    "en_US": "SafePrompt",
                    "zh_Hans": "提示词审查"
                  },
                  "max": null,
                  "min": null,
                  "name": "safe_prompt",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "The seed to use for random sampling. If set, different calls will generate deterministic results.",
                    "zh_Hans": "当开启随机数种子以后，你可以通过指定一个固定的种子来使得回答结果更加稳定"
                  },
                  "label": {
                    "en_US": "RandomSeed",
                    "zh_Hans": "随机数种子"
                  },
                  "max": 2147483647,
                  "min": 0,
                  "name": "random_seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.008",
                "output": "0.024",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "open-mistral-7b",
                "zh_Hans": "open-mistral-7b"
              },
              "model": "open-mistral-7b",
              "model_properties": {
                "context_size": 8000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "Whether to inject a safety prompt before all conversations.",
                    "zh_Hans": "是否开启提示词审查"
                  },
                  "label": {
                    "en_US": "SafePrompt",
                    "zh_Hans": "提示词审查"
                  },
                  "max": null,
                  "min": null,
                  "name": "safe_prompt",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "The seed to use for random sampling. If set, different calls will generate deterministic results.",
                    "zh_Hans": "当开启随机数种子以后，你可以通过指定一个固定的种子来使得回答结果更加稳定"
                  },
                  "label": {
                    "en_US": "RandomSeed",
                    "zh_Hans": "随机数种子"
                  },
                  "max": 2147483647,
                  "min": 0,
                  "name": "random_seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.00025",
                "output": "0.00025",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "open-mistral-nemo",
                "zh_Hans": "open-mistral-nemo"
              },
              "model": "open-mistral-nemo",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "Whether to inject a safety prompt before all conversations.",
                    "zh_Hans": "是否开启提示词审查"
                  },
                  "label": {
                    "en_US": "SafePrompt",
                    "zh_Hans": "提示词审查"
                  },
                  "max": null,
                  "min": null,
                  "name": "safe_prompt",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "The seed to use for random sampling. If set, different calls will generate deterministic results.",
                    "zh_Hans": "当开启随机数种子以后，你可以通过指定一个固定的种子来使得回答结果更加稳定"
                  },
                  "label": {
                    "en_US": "RandomSeed",
                    "zh_Hans": "随机数种子"
                  },
                  "max": 2147483647,
                  "min": 0,
                  "name": "random_seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.008",
                "output": "0.024",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "open-mixtral-8x22b",
                "zh_Hans": "open-mixtral-8x22b"
              },
              "model": "open-mixtral-8x22b",
              "model_properties": {
                "context_size": 64000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 8000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "Whether to inject a safety prompt before all conversations.",
                    "zh_Hans": "是否开启提示词审查"
                  },
                  "label": {
                    "en_US": "SafePrompt",
                    "zh_Hans": "提示词审查"
                  },
                  "max": null,
                  "min": null,
                  "name": "safe_prompt",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "The seed to use for random sampling. If set, different calls will generate deterministic results.",
                    "zh_Hans": "当开启随机数种子以后，你可以通过指定一个固定的种子来使得回答结果更加稳定"
                  },
                  "label": {
                    "en_US": "RandomSeed",
                    "zh_Hans": "随机数种子"
                  },
                  "max": 2147483647,
                  "min": 0,
                  "name": "random_seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.002",
                "output": "0.006",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "open-mixtral-8x7b",
                "zh_Hans": "open-mixtral-8x7b"
              },
              "model": "open-mixtral-8x7b",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 8000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "Whether to inject a safety prompt before all conversations.",
                    "zh_Hans": "是否开启提示词审查"
                  },
                  "label": {
                    "en_US": "SafePrompt",
                    "zh_Hans": "提示词审查"
                  },
                  "max": null,
                  "min": null,
                  "name": "safe_prompt",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "The seed to use for random sampling. If set, different calls will generate deterministic results.",
                    "zh_Hans": "当开启随机数种子以后，你可以通过指定一个固定的种子来使得回答结果更加稳定"
                  },
                  "label": {
                    "en_US": "RandomSeed",
                    "zh_Hans": "随机数种子"
                  },
                  "max": 2147483647,
                  "min": 0,
                  "name": "random_seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0007",
                "output": "0.0007",
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "pixtral-12b-2409",
                "zh_Hans": "pixtral-12b-2409"
              },
              "model": "pixtral-12b-2409",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": false,
                  "help": {
                    "en_US": "Whether to inject a safety prompt before all conversations.",
                    "zh_Hans": "是否开启提示词审查"
                  },
                  "label": {
                    "en_US": "SafePrompt",
                    "zh_Hans": "提示词审查"
                  },
                  "max": null,
                  "min": null,
                  "name": "safe_prompt",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "The seed to use for random sampling. If set, different calls will generate deterministic results.",
                    "zh_Hans": "当开启随机数种子以后，你可以通过指定一个固定的种子来使得回答结果更加稳定"
                  },
                  "label": {
                    "en_US": "RandomSeed",
                    "zh_Hans": "随机数种子"
                  },
                  "max": 2147483647,
                  "min": 0,
                  "name": "random_seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.008",
                "output": "0.024",
                "unit": "0.001"
              }
            }
          ],
          "position": {
            "llm": [
              "pixtral-12b-2409",
              "codestral-latest",
              "mistral-embed",
              "open-mistral-nemo",
              "open-codestral-mamba",
              "open-mistral-7b",
              "open-mixtral-8x7b",
              "open-mixtral-8x22b",
              "mistral-small-latest",
              "mistral-medium-latest",
              "mistral-large-latest"
            ]
          },
          "provider": "mistralai",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              }
            ]
          },
          "supported_model_types": [
            "llm"
          ]
        },
        "name": "mistralai",
        "org": "langgenius",
        "plugin_id": "langgenius/mistralai",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/mistralai.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-02-17T06:54:49Z",
        "version_updated_at": "2025-02-17T06:54:49Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "API Catalog",
          "zh_Hans": "API Catalog"
        },
        "category": "model",
        "created_at": "2024-12-04T04:41:46Z",
        "endpoint": {},
        "icon": "langgenius/packages/nvidia/_assets/icon_s_en.svg",
        "index_id": "langgenius___nvidia",
        "install_count": 1204,
        "introduction": "# Nvidia\n",
        "label": {
          "en_US": "API Catalog"
        },
        "latest_package_identifier": "langgenius/nvidia:0.0.2@349abb2dddec8d1dd26ed945137d1865e9e62dd710535638bf15b54bd0ec71c6",
        "latest_version": "0.0.2",
        "model": {
          "background": "#FFFFFF",
          "configurate_methods": [
            "predefined-model"
          ],
          "description": {
            "en_US": "API Catalog",
            "zh_Hans": "API Catalog"
          },
          "help": {
            "title": {
              "en_US": "Get your API Key from NVIDIA",
              "zh_Hans": "从 NVIDIA 获取 API Key"
            },
            "url": {
              "en_US": "https://build.nvidia.com/explore/discover"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.png"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "API Catalog"
          },
          "model_credential_schema": null,
          "models": [
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "snowflake/arctic",
                "zh_Hans": "snowflake/arctic"
              },
              "model": "snowflake/arctic",
              "model_properties": {
                "context_size": 4000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 1024,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "google/codegemma-7b",
                "zh_Hans": "google/codegemma-7b"
              },
              "model": "google/codegemma-7b",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 1024,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "deepseek-ai/deepseek-r1"
              },
              "model": "deepseek-ai/deepseek-r1",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 1024,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "fuyu-8b",
                "zh_Hans": "fuyu-8b"
              },
              "model": "fuyu-8b",
              "model_properties": {
                "context_size": 16000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.2,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0.1,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 1024,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "google/gemma-7b",
                "zh_Hans": "google/gemma-7b"
              },
              "model": "google/gemma-7b",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 1024,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "meta/llama-3.1-405b-instruct",
                "zh_Hans": "meta/llama-3.1-405b-instruct"
              },
              "model": "meta/llama-3.1-405b-instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalt",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "meta/llama-3.1-70b-instruct",
                "zh_Hans": "meta/llama-3.1-70b-instruct"
              },
              "model": "meta/llama-3.1-70b-instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "meta/llama-3.1-8b-instruct",
                "zh_Hans": "meta/llama-3.1-8b-instruct"
              },
              "model": "meta/llama-3.1-8b-instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "meta/llama2-70b",
                "zh_Hans": "meta/llama2-70b"
              },
              "model": "meta/llama2-70b",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 1024,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "meta/llama3-70b-instruct",
                "zh_Hans": "meta/llama3-70b-instruct"
              },
              "model": "meta/llama3-70b-instruct",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 1024,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "meta/llama3-8b-instruct",
                "zh_Hans": "meta/llama3-8b-instruct"
              },
              "model": "meta/llama3-8b-instruct",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 1024,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "mistralai/mistral-large",
                "zh_Hans": "mistralai/mistral-large"
              },
              "model": "mistralai/mistral-large",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 1024,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "mistralai/mixtral-8x7b-instruct-v0.1",
                "zh_Hans": "mistralai/mixtral-8x7b-instruct-v0.1"
              },
              "model": "mistralai/mixtral-8x7b-instruct-v0.1",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 1024,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "mistralai/mixtral-8x22b-instruct-v0.1",
                "zh_Hans": "mistralai/mixtral-8x22b-instruct-v0.1"
              },
              "model": "mistralai/mixtral-8x22b-instruct-v0.1",
              "model_properties": {
                "context_size": 64000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 1024,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "nvidia/nemotron-4-340b-instruct",
                "zh_Hans": "nvidia/nemotron-4-340b-instruct"
              },
              "model": "nvidia/nemotron-4-340b-instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "microsoft/phi-3-medium-128k-instruct",
                "zh_Hans": "microsoft/phi-3-medium-128k-instruct"
              },
              "model": "microsoft/phi-3-medium-128k-instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "microsoft/phi-3-mini-128k-instruct",
                "zh_Hans": "microsoft/phi-3-mini-128k-instruct"
              },
              "model": "microsoft/phi-3-mini-128k-instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "google/recurrentgemma-2b",
                "zh_Hans": "google/recurrentgemma-2b"
              },
              "model": "google/recurrentgemma-2b",
              "model_properties": {
                "context_size": 2048,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.2,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 1024,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "The seed to use for random sampling. If set, different calls will generate deterministic results.",
                    "zh_Hans": "当开启随机数种子以后，你可以通过指定一个固定的种子来使得回答结果更加稳定"
                  },
                  "label": {
                    "en_US": "Seed",
                    "zh_Hans": "种子"
                  },
                  "max": 2147483647,
                  "min": 0,
                  "name": "random_seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "nv-rerank-qa-mistral-4b:1"
              },
              "model": "nv-rerank-qa-mistral-4b:1",
              "model_properties": {
                "context_size": 512
              },
              "model_type": "rerank",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "NV-Embed-QA"
              },
              "model": "NV-Embed-QA",
              "model_properties": {
                "context_size": 512,
                "max_chunks": 1
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": null
            }
          ],
          "position": {
            "llm": [
              "deepseek-ai/deepseek-r1",
              "google/gemma-7b",
              "google/codegemma-7b",
              "google/recurrentgemma-2b",
              "meta/llama2-70b",
              "meta/llama-3.1-8b-instruct",
              "meta/llama-3.1-70b-instruct",
              "meta/llama-3.1-405b-instruct",
              "meta/llama3-8b-instruct",
              "meta/llama3-70b-instruct",
              "mistralai/mistral-large",
              "mistralai/mixtral-8x7b-instruct-v0.1",
              "mistralai/mixtral-8x22b-instruct-v0.1",
              "nvidia/nemotron-4-340b-instruct",
              "microsoft/phi-3-medium-128k-instruct",
              "microsoft/phi-3-mini-128k-instruct",
              "fuyu-8b",
              "snowflake/arctic"
            ],
            "rerank": null,
            "text_embedding": null
          },
          "provider": "nvidia",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              }
            ]
          },
          "supported_model_types": [
            "llm",
            "text-embedding",
            "rerank"
          ]
        },
        "name": "nvidia",
        "org": "langgenius",
        "plugin_id": "langgenius/nvidia",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/nvidia.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-02-17T06:59:05Z",
        "version_updated_at": "2025-02-17T06:59:05Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "A tool can be used to automate the browser with playwright script.",
          "zh_Hans": "一个可以使用 playwright 脚本自动化浏览器的工具"
        },
        "category": "tool",
        "created_at": "2025-04-03T08:28:05Z",
        "endpoint": {},
        "icon": "hjlarry/packages/playwright/_assets/icon.svg",
        "index_id": "hjlarry___playwright",
        "install_count": 1196,
        "introduction": "# playwright\n\n**Author:** hjlarry  \n**Version:** 0.0.1  \n**Type:** tool  \n**Repo&Issue:** [https://github.com/hjlarry/dify-plugin-playwright](https://github.com/hjlarry/dify-plugin-playwright)  \n\nA tool can be used to automate the browser with playwright script.\n\n## Get Started\n\n### 1. run your playwright server\n\nThe default port `3000` is already used by dify, you should change to another port.\n\n**Option 1 (Use Docker)**\n```\ndocker run -p 3003:3000 --rm --init -it --workdir /home/pwuser --user pwuser mcr.microsoft.com/playwright:v1.51.0-noble /bin/sh -c \"npx -y playwright@1.51.0 run-server --port 3000 --host 0.0.0.0\"\n```\n\n**Option 2 (Use npx)**\n```\nnpx -y playwright@1.51.0 run-server --port 3003 --host 0.0.0.0\n```\n\n### 2. Authroize\n\nUse `ws://<IP>:3003` to authorize.\n\n### 3. Execute script\nThe script should like this:\n```\npage = browser.new_page(); page.goto('http://playwright.dev'); result = page.screenshot();\n```\nusing `;` to separate commands. Assign the final output to the variable `result`(only support string and bytes). Utilize the `browser` variable to access the browser object. \n\n### 4. The agent can use this tool well\n![agent](./_assets/agent.png)",
        "label": {
          "en_US": "playwright",
          "ja_JP": "playwright",
          "pt_BR": "playwright",
          "zh_Hans": "playwright"
        },
        "latest_package_identifier": "hjlarry/playwright:0.0.1@ce1b837ae1a102b7edf1097dcff1edaee3b00baee837f6667b24915e43c5f85c",
        "latest_version": "0.0.1",
        "model": {},
        "name": "playwright",
        "org": "hjlarry",
        "plugin_id": "hjlarry/playwright",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/playwright.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {}
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "For example `ws://host.docker.internal:3003`",
                "zh_Hans": "例如 `ws://host.docker.internal:3003`"
              },
              "label": {
                "en_US": "Playwright URI"
              },
              "name": "playwright_uri",
              "options": null,
              "placeholder": {
                "en_US": "Please enter the Playwright URI",
                "zh_Hans": "请输入Playwright URI"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            }
          ],
          "identity": {
            "author": "hjlarry",
            "description": {
              "en_US": "A tool can be used to automate the browser with playwright script.",
              "zh_Hans": "一个可以使用 playwright 脚本自动化浏览器的工具"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "playwright",
              "pt_BR": "playwright",
              "zh_Hans": "playwright"
            },
            "name": "playwright",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool can be used to automate the browser with playwright script.",
                  "zh_Hans": "一个可以使用 playwright 脚本自动化浏览器的工具"
                },
                "llm": "A tool can be used to automate the browser with playwright script."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "hjlarry",
                "label": {
                  "en_US": "playwright",
                  "zh_Hans": "playwright"
                },
                "name": "playwright"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "script send to playwright to execute",
                    "zh_Hans": "发送给 playwright 执行的脚本"
                  },
                  "label": {
                    "en_US": "playwright script",
                    "zh_Hans": "playwright 脚本"
                  },
                  "llm_description": "Send the python script to Playwright for execution, using `;` to separate commands. Assign the final output to the variable `result`(only support string and bytes). Utilize the `browser` variable to access the browser object. Example: page = browser.new_page(); page.goto(\"http://www.baidu.com\"); result = page.screenshot(full_page=True);\n",
                  "max": null,
                  "min": null,
                  "name": "script",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-03T08:28:13Z",
        "version_updated_at": "2025-04-03T08:28:13Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Baichuan"
        },
        "category": "model",
        "created_at": "2024-12-05T06:58:13Z",
        "endpoint": {},
        "icon": "langgenius/packages/baichuan/_assets/icon_s_en.svg",
        "index_id": "langgenius___baichuan",
        "install_count": 1176,
        "introduction": "## Overview\n\nBaichun is an open-source, large-scale pre-trained language model which supports both Chinese and English languages with the benchmarks such as C-Eval, MMLU, etc. With those models, Baichuan provides a rich set of AI tools, including language models, chat models, and embedding models.\n\n## Configure\n\nAfter installing the plugin, configure the API key and API base within the Model Provider settings. Obtain your API key from [here](https://www.baichuan-ai.com/home). Once saved, you can begin using Baichuan to build your AI agents and agentic workflows.\n\n![](./_assets/baichuan_config.PNG)",
        "label": {
          "en_US": "Baichuan",
          "zh_Hans": "百川智能"
        },
        "latest_package_identifier": "langgenius/baichuan:0.0.3@ea78e38252ea150c872d6f5fddf7855fcb04a4e12dfb986749559fc4d7bfc08c",
        "latest_version": "0.0.3",
        "model": {
          "background": "#FFF6F2",
          "configurate_methods": [
            "predefined-model"
          ],
          "description": {
            "en_US": "Baichuan"
          },
          "help": {
            "title": {
              "en_US": "Get your API Key from BAICHUAN AI",
              "zh_Hans": "从百川智能获取您的 API Key"
            },
            "url": {
              "en_US": "https://www.baichuan-ai.com"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.svg"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "Baichuan"
          },
          "model_credential_schema": null,
          "models": [
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Baichuan2-53B"
              },
              "model": "baichuan2-53b",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1000,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": 1,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Allow the model to perform external search to enhance the generation results.",
                    "zh_Hans": "允许模型自行进行外部搜索，以增强生成结果。"
                  },
                  "label": {
                    "en_US": "Search Enhance",
                    "zh_Hans": "搜索增强"
                  },
                  "max": null,
                  "min": null,
                  "name": "with_search_enhance",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Baichuan2-Turbo-192K"
              },
              "model": "baichuan2-turbo-192k",
              "model_properties": {
                "context_size": 192000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 8000,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 192000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": 1,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Allow the model to perform external search to enhance the generation results.",
                    "zh_Hans": "允许模型自行进行外部搜索，以增强生成结果。"
                  },
                  "label": {
                    "en_US": "Search Enhance",
                    "zh_Hans": "搜索增强"
                  },
                  "max": null,
                  "min": null,
                  "name": "with_search_enhance",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "multi-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Baichuan2-Turbo"
              },
              "model": "baichuan2-turbo",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.85,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 5,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 20,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Allow the model to perform external search to enhance the generation results.",
                    "zh_Hans": "允许模型自行进行外部搜索，以增强生成结果。"
                  },
                  "label": {
                    "en_US": "Search Enhance",
                    "zh_Hans": "搜索增强"
                  },
                  "max": null,
                  "min": null,
                  "name": "with_search_enhance",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "multi-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Baichuan3-Turbo-128k"
              },
              "model": "baichuan3-turbo-128k",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.85,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 5,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 20,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "res_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Allow the model to perform external search to enhance the generation results.",
                    "zh_Hans": "允许模型自行进行外部搜索，以增强生成结果。"
                  },
                  "label": {
                    "en_US": "Search Enhance",
                    "zh_Hans": "搜索增强"
                  },
                  "max": null,
                  "min": null,
                  "name": "with_search_enhance",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "multi-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Baichuan3-Turbo"
              },
              "model": "baichuan3-turbo",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.85,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 5,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 20,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "res_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Allow the model to perform external search to enhance the generation results.",
                    "zh_Hans": "允许模型自行进行外部搜索，以增强生成结果。"
                  },
                  "label": {
                    "en_US": "Search Enhance",
                    "zh_Hans": "搜索增强"
                  },
                  "max": null,
                  "min": null,
                  "name": "with_search_enhance",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "multi-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Baichuan4-Air"
              },
              "model": "baichuan4-air",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.85,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 5,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 20,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "res_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Allow the model to perform external search to enhance the generation results.",
                    "zh_Hans": "允许模型自行进行外部搜索，以增强生成结果。"
                  },
                  "label": {
                    "en_US": "Search Enhance",
                    "zh_Hans": "搜索增强"
                  },
                  "max": null,
                  "min": null,
                  "name": "with_search_enhance",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "multi-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Baichuan4-Turbo"
              },
              "model": "baichuan4-turbo",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.85,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 5,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 20,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "res_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Allow the model to perform external search to enhance the generation results.",
                    "zh_Hans": "允许模型自行进行外部搜索，以增强生成结果。"
                  },
                  "label": {
                    "en_US": "Search Enhance",
                    "zh_Hans": "搜索增强"
                  },
                  "max": null,
                  "min": null,
                  "name": "with_search_enhance",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "multi-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Baichuan4"
              },
              "model": "baichuan4",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.85,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 5,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 20,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "specifying the format that the model must output",
                    "zh_Hans": "指定模型必须输出的格式"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "res_format",
                  "options": [
                    "text",
                    "json_object"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Allow the model to perform external search to enhance the generation results.",
                    "zh_Hans": "允许模型自行进行外部搜索，以增强生成结果。"
                  },
                  "label": {
                    "en_US": "Search Enhance",
                    "zh_Hans": "搜索增强"
                  },
                  "max": null,
                  "min": null,
                  "name": "with_search_enhance",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "boolean",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "baichuan-text-embedding"
              },
              "model": "baichuan-text-embedding",
              "model_properties": {
                "context_size": 512,
                "max_chunks": 16
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": null
            }
          ],
          "position": {},
          "provider": "baichuan",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              }
            ]
          },
          "supported_model_types": [
            "llm",
            "text-embedding"
          ]
        },
        "name": "baichuan",
        "org": "langgenius",
        "plugin_id": "langgenius/baichuan",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/baichuan.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {}
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-11T06:42:49Z",
        "version_updated_at": "2025-04-11T06:42:49Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Access Crawl4AI capabilities to extract content from web pages, etc, return markdown or html format",
          "zh_Hans": "通过API接口访问Crawl4AI的网页内容提取、数据解析和结构化处理等功能，实现高效的网络信息采集，返回markdown或者html格式"
        },
        "category": "tool",
        "created_at": "2025-03-31T17:23:15Z",
        "endpoint": {},
        "icon": "agimaster/packages/crawl4ai/_assets/icon.svg",
        "index_id": "agimaster___crawl4ai",
        "install_count": 1152,
        "introduction": "# Crawl4AI Plugin for Dify\n\n## Overview\n\n[Crawl4AI](https://github.com/unclecode/crawl4ai/tree/main) is an open-source web crawler that allows for efficient extraction of content from web pages, This plugin connects Dify to a Docker-deployed Crawl4AI service via HTTP.\n\n## Configuration\n\n### 1. Deploy Crawl4AI Docker Service\n\nFirst, deploy the Crawl4AI service using Docker on your server. Follow the instructions on the [Crawl4AI documentation](https://docs.crawl4ai.com/).\n\n### 2. Get Crawl4AI Plugin from Plugin Marketplace\n\nThe Crawl4AI plugin can be found in the Plugin Marketplace. Install it first.\n\n### 3. Fill in the configuration in Dify\n\nOn the Dify navigation page, click `Tools > Crawl4AI > To Authorize` and fill in the following information:\n\n- **Server URL**: Your Crawl4AI service URL, e.g., `http://localhost:11235`\n- **API Token**: The authentication token for your Crawl4AI service\n\n![](./_assets/crawl4ai_1.jpg)\n\n\n### 4. Use the tool\n\nYou can use the Crawl4AI tool in the following application types:\n\n![](./_assets/crawl4ai_2.jpg)\n\n#### Chatflow / Workflow applications\n\nBoth Chatflow and Workflow applications support adding `Crawl4AI` tool nodes for web content extraction.\n\n#### Agent applications\n\nAdd the Crawl4AI tool in the Agent application, then use web extraction commands to call this tool.\n\n## Features\n\n- Web Content Extraction\n    - **Web Content Extraction**: Extract content from web pages using Crawl4AI's API\n    - **Selector Support**: Target specific content using CSS selectors\n    - **Formatted Output**: Support for Markdown and HTML output formats\n    - **Tag Exclusion**: Ability to exclude specific HTML tags from extraction\n    - Python code reference: unclecode/crawl4ai/docs/examples/docker_example.py\n\n\n## Development\n\nFor development information, please refer to the [Dify Plugin Development Documentation](https://docs.dify.ai/plugins/develop-plugins). \n\nSource code is available at: https://github.com/AGIMaster/dify-plugin-my-development/tree/master/tools/crawl4ai\n",
        "label": {
          "en_US": "Crawl4AI",
          "zh_Hans": "Crawl4AI"
        },
        "latest_package_identifier": "agimaster/crawl4ai:0.0.1@075b230ee256f36bb93823b5d4e0e3408fc5c6dd09771e7d0505139ae063d52b",
        "latest_version": "0.0.1",
        "model": {},
        "name": "crawl4ai",
        "org": "agimaster",
        "plugin_id": "agimaster/crawl4ai",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/crawl4ai.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "privacy.md",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "app": {
              "enabled": false
            },
            "endpoint": {
              "enabled": true
            },
            "model": {
              "enabled": false,
              "llm": false,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "storage": {
              "enabled": false,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "search"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Get your Crawl4AI API token from your Crawl4AI installation",
                "zh_Hans": "从您的Crawl4AI安装获取API令牌"
              },
              "label": {
                "en_US": "API Token",
                "zh_Hans": "API令牌"
              },
              "name": "api_token",
              "options": null,
              "placeholder": {
                "en_US": "Please enter your Crawl4AI API token",
                "zh_Hans": "请输入您的Crawl4AI API令牌"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://docs.crawl4ai.com/core/docker-deployment/"
            },
            {
              "default": null,
              "help": {
                "en_US": "Your Crawl4AI server URL (e.g. http://localhost:11235)",
                "zh_Hans": "您的Crawl4AI服务器URL (例如 http://localhost:11235)"
              },
              "label": {
                "en_US": "Server URL",
                "zh_Hans": "服务器URL"
              },
              "name": "server_url",
              "options": null,
              "placeholder": {
                "en_US": "Please enter your Crawl4AI server URL",
                "zh_Hans": "请输入您的Crawl4AI服务器URL"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": "https://docs.crawl4ai.com/core/docker-deployment/"
            }
          ],
          "identity": {
            "author": "AGIMaster",
            "description": {
              "en_US": "Access Crawl4AI capabilities to extract content from web pages",
              "zh_Hans": "访问Crawl4AI功能，从网页中提取内容"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Crawl4AI",
              "zh_Hans": "Crawl4AI"
            },
            "name": "crawl4ai",
            "tags": [
              "search",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Extract content from web pages using Crawl4AI's crawl_direct API. Supports CSS selectors for precise content extraction.",
                  "zh_Hans": "使用Crawl4AI的 crawl_direct API从网页提取内容。支持使用CSS选择器进行精确的内容提取。"
                },
                "llm": "A tool for extracting content from web pages. Input should be a URL. You can use CSS selectors to extract specific parts of the page. Content will be returned in markdown or html format."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "AGIMaster",
                "label": {
                  "en_US": "Web Content Extraction",
                  "zh_Hans": "网页内容提取"
                },
                "name": "crawl_direct"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The URL of the webpage to extract content from",
                    "zh_Hans": "要提取内容的网页URL"
                  },
                  "label": {
                    "en_US": "URL",
                    "zh_Hans": "网址"
                  },
                  "llm_description": "The URL of the webpage to crawl",
                  "max": null,
                  "min": null,
                  "name": "url",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "CSS selector to target specific elements on the page (e.g. #article, .content)",
                    "zh_Hans": "CSS选择器，用于定位页面上的特定元素（如 #article, .content）"
                  },
                  "label": {
                    "en_US": "CSS Selector",
                    "zh_Hans": "CSS选择器"
                  },
                  "llm_description": "CSS selector to target specific elements on the page",
                  "max": null,
                  "min": null,
                  "name": "css_selector",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "script,style,noscript",
                  "form": "form",
                  "human_description": {
                    "en_US": "HTML tags to exclude from extraction (comma-separated)",
                    "zh_Hans": "从提取中排除的HTML标签（逗号分隔）"
                  },
                  "label": {
                    "en_US": "Excluded Tags",
                    "zh_Hans": "排除的标签"
                  },
                  "llm_description": "HTML tags to exclude from extraction",
                  "max": null,
                  "min": null,
                  "name": "excluded_tags",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "markdown",
                  "form": "form",
                  "human_description": {
                    "en_US": "Output format (markdown or text)",
                    "zh_Hans": "输出格式（markdown或text）"
                  },
                  "label": {
                    "en_US": "Output Format",
                    "zh_Hans": "输出格式"
                  },
                  "llm_description": "Format for the extracted content",
                  "max": null,
                  "min": null,
                  "name": "output_format",
                  "options": [
                    {
                      "label": {
                        "en_US": "Markdown",
                        "zh_Hans": "Markdown"
                      },
                      "value": "markdown"
                    },
                    {
                      "label": {
                        "en_US": "HTML",
                        "zh_Hans": "HTML"
                      },
                      "value": "html"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-31T17:23:24Z",
        "version_updated_at": "2025-03-31T17:23:24Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Discord Webhook",
          "pt_BR": "Discord Webhook",
          "zh_Hans": "Discord Webhook"
        },
        "category": "tool",
        "created_at": "2024-12-04T04:53:34Z",
        "endpoint": {},
        "icon": "langgenius/packages/discord/_assets/icon.svg",
        "index_id": "langgenius___discord",
        "install_count": 1150,
        "introduction": "# Discord Tool\n\n## Overview\n\nDiscord is a communication platform designed for communities. It offers features like text and voice channels, direct messaging, and server-based organization. In Dify, Discord tools allow users to create a random bot with random username and avatar to send messages.\n\n## Configuration\n\n### 1. Get Discord webhook url\nPlease follow [this site](https://support.discord.com/hc/en-us/articles/228383668-Intro-to-Webhooks) to create a webhook and get its url.\n\n### 2. Get Discord tools from Plugin Marketplace\nThe Discord tools could be found at the Plugin Marketplace, please install it first.\n\n![](./_assets/discord_1.PNG)\n\n### 3. Use the tool\nYou can use the Discord tool in the following application types.\n\n![](./_assets/discord_2.PNG)\n\n#### Chatflow / Workflow applications\n\nBoth Chatflow and Workflow applications support adding a `Discord` tool node.\n\n#### Agent applications\nAdd the Discord tool in the Agent application, then fill in the `discord incoming webhook url` to call this tool.",
        "label": {
          "en_US": "Discord",
          "pt_BR": "Discord",
          "zh_Hans": "Discord"
        },
        "latest_package_identifier": "langgenius/discord:0.0.2@e68d83d283c2fbab6372b9141fe7e7ce59de716095d6dd763aac9aa0fbfbf417",
        "latest_version": "0.0.2",
        "model": {},
        "name": "discord",
        "org": "langgenius",
        "plugin_id": "langgenius/discord",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/discord.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "social"
          }
        ],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "Ice Yao",
            "description": {
              "en_US": "Discord Webhook",
              "pt_BR": "Discord Webhook",
              "zh_Hans": "Discord Webhook"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Discord",
              "pt_BR": "Discord",
              "zh_Hans": "Discord"
            },
            "name": "discord",
            "tags": [
              "social",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Sending a message on Discord via the Incoming Webhook",
                  "pt_BR": "Sending a message on Discord via the Incoming Webhook",
                  "zh_Hans": "通过入站Webhook在Discord上发送消息"
                },
                "llm": "A tool for sending messages to a chat on Discord."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Ice Yao",
                "label": {
                  "en_US": "Incoming Webhook to send message",
                  "pt_BR": "Incoming Webhook to send message",
                  "zh_Hans": "通过入站Webhook发送消息"
                },
                "name": "discord_webhook"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Discord Incoming Webhook url",
                    "pt_BR": "Discord Incoming Webhook url",
                    "zh_Hans": "Discord入站Webhook的url"
                  },
                  "label": {
                    "en_US": "Discord Incoming Webhook url",
                    "pt_BR": "Discord Incoming Webhook url",
                    "zh_Hans": "Discord入站Webhook的url"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "webhook_url",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Content to sent to the channel or person.",
                    "pt_BR": "Content to sent to the channel or person.",
                    "zh_Hans": "消息内容文本"
                  },
                  "label": {
                    "en_US": "content",
                    "pt_BR": "content",
                    "zh_Hans": "消息内容"
                  },
                  "llm_description": "Content of the message",
                  "max": null,
                  "min": null,
                  "name": "content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Discord Webhook Username",
                    "pt_BR": "Discord Webhook Username",
                    "zh_Hans": "Discord Webhook用户名"
                  },
                  "label": {
                    "en_US": "Discord Webhook Username",
                    "pt_BR": "Discord Webhook Username",
                    "zh_Hans": "Discord Webhook用户名"
                  },
                  "llm_description": "Discord Webhook Username",
                  "max": null,
                  "min": null,
                  "name": "username",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Discord Webhook Avatar URL",
                    "pt_BR": "Discord Webhook Avatar URL",
                    "zh_Hans": "Discord Webhook头像地址"
                  },
                  "label": {
                    "en_US": "Discord Webhook Avatar",
                    "pt_BR": "Discord Webhook Avatar",
                    "zh_Hans": "Discord Webhook头像"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "avatar_url",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:04:16Z",
        "version_updated_at": "2025-02-17T07:04:16Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "A plugin for sending notifications to Lark group chats. It supports sending text messages and card messages, allowing you to communicate with your team in a more flexible and visually appealing way.",
          "ja_JP": "Larkグループチャットに通知を送信するためのプラグイン。テキストメッセージやカードメッセージの送信をサポートし、より柔軟で視覚的に魅力的な方法でチームとコミュニケーションを取ることができます。",
          "pt_BR": "Um plugin para enviar notificações para chats em grupo do Lark. Suporta o envio de mensagens de texto e cartões, permitindo que você se comunique com sua equipe de forma mais flexível e visualmente atraente.",
          "zh_Hans": "LarkNotify 是一个用于向飞书群聊发送通知消息的插件。它支持发送文本消息和卡片消息，让你能够以更灵活和美观的方式向团队传递信息。"
        },
        "category": "tool",
        "created_at": "2025-02-27T09:25:53Z",
        "endpoint": {},
        "icon": "opsworld30/packages/lark_notify/_assets/icon.svg",
        "index_id": "opsworld30___lark_notify",
        "install_count": 1145,
        "introduction": "# lark_notify\n\n**Author:** opsworld30\n**Version:** 0.0.1\n**Type:** tool\n\n### Description\n\nLarkNotify is a plugin for sending notification messages to Lark (Feishu) group chats. It supports sending text messages and card messages, allowing you to communicate with your team in a more flexible and visually appealing way.\n\n### Features\n\n- Support for plain text messages\n- Support for card messages, including:\n  - 4 message types: info, warning, success, error\n  - Markdown formatting support:\n    - Bold text: **text**\n    - Italic text: *text*\n    - Links: [text](url)\n    - Bullet points with -\n    - @everyone with <at id=all></at>\n  - Optional timestamp display\n- Support for automatic long text segmentation\n- Multi-language interface (English, Chinese, Japanese, Portuguese)\n\n### Prerequisites\n\n- Lark Bot Webhook URL\n  1. Add a custom bot to your Lark group chat\n  2. Get the bot's Webhook URL\n  3. Use either the complete webhook URL or just the webhook key (the part after /hook/)\n\n### Configuration\n\nIn the plugin configuration, you need to set the following credentials:\n\n- `webhook_key`: You can input either:\n  - The complete webhook URL: `https://open.feishu.cn/open-apis/bot/v2/hook/xxx`\n  - Just the webhook key: `xxx`\n\n### Usage Examples\n\n1. Send a text message:\n```json\n{\n  \"webhook\": \"xxx\",\n  \"message\": \"System backup completed\"\n}\n```\n\n2. Send a card message with markdown:\n```json\n{\n  \"webhook\": \"xxx\",\n  \"card_content\": \"**Deployment Status**: *Success*\\n- Service: API Gateway\\n- Version: 1.2.3\\n- Time: 2024-02-25\\n\\nFor details, see [Deployment Log](https://example.com/logs)\",\n  \"title\": \"Deployment Notice\",\n  \"card_type\": \"success\",\n  \"show_time\": true\n}\n```\n\n### Privacy Policy\n\nThis plugin only collects the following necessary information for message delivery:\n\n1. Lark bot webhook URL/key\n2. User-provided message content\n\nThis information is used solely for sending messages to the specified Lark group chat and will not be used for other purposes or shared with third parties.\n\nMessage sending uses Lark's official API. For related privacy policies, please refer to: [Lark Open Platform Service Agreement](https://www.larksuite.com/en_us/agreement)\n\n### Support\n\nIf you encounter any issues or have questions, please:\n1. Check the documentation in the GUIDE.md file\n2. Raise an issue on the GitHub repository\n3. Contact the plugin author\n",
        "label": {
          "en_US": "Lark Group Bot",
          "ja_JP": "Lark グループボット",
          "pt_BR": "Bot de Grupo do Lark",
          "zh_Hans": "飞书群机器人"
        },
        "latest_package_identifier": "opsworld30/lark_notify:0.0.1@68ec1271d23bea71441d4782284658144ff180fc9c3c051a97ed4a2a4e1bdbe8",
        "latest_version": "0.0.1",
        "model": {},
        "name": "lark_notify",
        "org": "opsworld30",
        "plugin_id": "opsworld30/lark_notify",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/lark_notify.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "opsworld30",
            "description": {
              "en_US": "Send notifications to Lark group chats, supporting both text and card messages.",
              "ja_JP": "Larkグループチャットに通知を送信し、テキストメッセージとカードメッセージの両方をサポートします。",
              "pt_BR": "Envie notificações para chats em grupo do Lark, suportando mensagens de texto e cartão.",
              "zh_Hans": "向飞书群聊发送通知，支持文本消息和卡片消息。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Lark Notification",
              "ja_JP": "Lark 通知",
              "pt_BR": "Notificação do Lark",
              "zh_Hans": "飞书通知"
            },
            "name": "lark_notify",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Send interactive card messages to Lark group chats with customizable styles.",
                  "ja_JP": "カスタマイズ可能なスタイルで、Larkグループチャットにインタラクティブなカードメッセージを送信します。",
                  "pt_BR": "Envie mensagens de cartão interativas para chats em grupo do Lark com estilos personalizáveis.",
                  "zh_Hans": "发送交互式卡片消息到飞书群聊，支持自定义样式。"
                },
                "llm": "A tool for sending interactive card messages to Lark group chats, featuring customizable styles."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "opsworld30",
                "label": {
                  "en_US": "Lark Card Message",
                  "ja_JP": "Lark カードメッセージ",
                  "pt_BR": "Mensagem de Cartão do Lark",
                  "zh_Hans": "飞书卡片消息"
                },
                "name": "lark_card"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The webhook URL or key for the Lark bot. You can input either a complete webhook URL or just the webhook key.",
                    "ja_JP": "Larkボットのwebhook URLまたはキー。完全なwebhook URLまたはwebhookキーのみを入力できます。",
                    "pt_BR": "URL ou chave do webhook para o bot do Lark. Você pode inserir a URL completa do webhook ou apenas a chave do webhook.",
                    "zh_Hans": "飞书机器人的webhook地址或key。您可以输入完整webhook地址或仅webhook的key。"
                  },
                  "label": {
                    "en_US": "Webhook URL/Key",
                    "ja_JP": "Webhook URL/キー",
                    "pt_BR": "URL/Chave do Webhook",
                    "zh_Hans": "Webhook地址/Key"
                  },
                  "llm_description": "The webhook URL or key for the Lark bot.",
                  "max": null,
                  "min": null,
                  "name": "webhook",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The text content to be displayed in the card message. Supports basic markdown: **bold**, *italic*, [link](url), bullet points with -, and @everyone with <at id=all></at>.",
                    "ja_JP": "カードメッセージに表示するテキスト内容。基本的なmarkdown形式をサポート：**太字**、*斜体*、[リンク](url)、- による箇条書き、<at id=all></at> による全員メンション。",
                    "pt_BR": "O conteúdo de texto a ser exibido na mensagem do cartão. Suporta markdown básico: **negrito**, *itálico*, [link](url), marcadores com -, e mencionar todos com <at id=all></at>.",
                    "zh_Hans": "要在卡片消息中显示的文本内容。支持基本的 markdown 格式：**粗体**、*斜体*、[链接](url)、以 - 开头的列表，以及使用 <at id=all></at> 来@所有人。"
                  },
                  "label": {
                    "en_US": "Card Content",
                    "ja_JP": "カード内容",
                    "pt_BR": "Conteúdo do Cartão",
                    "zh_Hans": "卡片内容"
                  },
                  "llm_description": "The text content that will be displayed in the card message, supports basic markdown formatting including @everyone.",
                  "max": null,
                  "min": null,
                  "name": "card_content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "",
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional title for the card message.",
                    "ja_JP": "カードメッセージのオプションタイトル。",
                    "pt_BR": "Título opcional para a mensagem do cartão.",
                    "zh_Hans": "卡片消息的可选标题。"
                  },
                  "label": {
                    "en_US": "Card Title",
                    "ja_JP": "カードタイトル",
                    "pt_BR": "Título do Cartão",
                    "zh_Hans": "卡片标题"
                  },
                  "llm_description": "Optional title to be displayed at the top of the card.",
                  "max": null,
                  "min": null,
                  "name": "title",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "info",
                  "form": "form",
                  "human_description": {
                    "en_US": "Card message type (info/warning/success/error)",
                    "ja_JP": "カードメッセージタイプ（情報/警告/成功/エラー）",
                    "pt_BR": "Tipo de mensagem de cartão (informação/aviso/sucesso/erro)",
                    "zh_Hans": "卡片消息类型（信息/警告/成功/错误）"
                  },
                  "label": {
                    "en_US": "Card Type",
                    "ja_JP": "カードタイプ",
                    "pt_BR": "Tipo do Cartão",
                    "zh_Hans": "卡片类型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "card_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "Information",
                        "ja_JP": "情報",
                        "pt_BR": "Informação",
                        "zh_Hans": "信息"
                      },
                      "value": "info"
                    },
                    {
                      "label": {
                        "en_US": "Warning",
                        "ja_JP": "警告",
                        "pt_BR": "Aviso",
                        "zh_Hans": "警告"
                      },
                      "value": "warning"
                    },
                    {
                      "label": {
                        "en_US": "Success",
                        "ja_JP": "成功",
                        "pt_BR": "Sucesso",
                        "zh_Hans": "成功"
                      },
                      "value": "success"
                    },
                    {
                      "label": {
                        "en_US": "Error",
                        "ja_JP": "エラー",
                        "pt_BR": "Erro",
                        "zh_Hans": "错误"
                      },
                      "value": "error"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "Show message timestamp (optional)",
                    "ja_JP": "メッセージのタイムスタンプを表示（オプション）",
                    "pt_BR": "Mostrar timestamp da mensagem (opcional)",
                    "zh_Hans": "显示消息时间戳（可选）"
                  },
                  "label": {
                    "en_US": "Show Time",
                    "ja_JP": "時間を表示",
                    "pt_BR": "Mostrar Tempo",
                    "zh_Hans": "显示时间"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "show_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Send text messages to Lark group chats. Supports automatic message splitting for long content.",
                  "ja_JP": "Larkグループチャットにテキストメッセージを送信します。長文の自動分割に対応。",
                  "pt_BR": "Envie mensagens de texto para chats em grupo do Lark. Suporta divisão automática de mensagens longas.",
                  "zh_Hans": "发送文本消息到飞书群聊。支持长文本自动分段发送。"
                },
                "llm": "A tool for sending text messages to Lark group chats, with support for automatic message splitting for long content."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "opsworld30",
                "label": {
                  "en_US": "Lark Text Message",
                  "ja_JP": "Lark テキストメッセージ",
                  "pt_BR": "Mensagem de Texto do Lark",
                  "zh_Hans": "飞书文本消息"
                },
                "name": "lark_text"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The webhook URL or key for the Lark bot. You can input either a complete webhook URL or just the webhook key.",
                    "ja_JP": "Larkボットのwebhook URLまたはキー。完全なwebhook URLまたはwebhookキーのみを入力できます。",
                    "pt_BR": "URL ou chave do webhook para o bot do Lark. Você pode inserir uma URL completa do webhook ou apenas a chave do webhook.",
                    "zh_Hans": "飞书机器人的webhook地址或key。您可以输入完整webhook地址或仅webhook的key。"
                  },
                  "label": {
                    "en_US": "Webhook URL/Key",
                    "ja_JP": "Webhook URL/キー",
                    "pt_BR": "URL/Chave do Webhook",
                    "zh_Hans": "Webhook地址/Key"
                  },
                  "llm_description": "The webhook URL or key for the Lark bot. Can be either a complete URL or just the key part.",
                  "max": null,
                  "min": null,
                  "name": "webhook",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The text message to send (max 500 characters). Messages longer than this will be automatically split into multiple messages.",
                    "ja_JP": "送信するテキストメッセージ（最大500文字）。これより長いメッセージは自動的に複数のメッセージに分割されます。",
                    "pt_BR": "A mensagem de texto a ser enviada (máximo de 500 caracteres). Mensagens mais longas serão automaticamente divididas em várias mensagens.",
                    "zh_Hans": "要发送的文本消息（最多500字符）。超过长度限制的消息会被自动分段发送。"
                  },
                  "label": {
                    "en_US": "Message Content",
                    "ja_JP": "メッセージ内容",
                    "pt_BR": "Conteúdo da Mensagem",
                    "zh_Hans": "消息内容"
                  },
                  "llm_description": "The text message to send. Messages longer than 500 characters will be automatically split into multiple messages.",
                  "max": null,
                  "min": null,
                  "name": "message",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-27T09:25:59Z",
        "version_updated_at": "2025-02-27T09:25:59Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "快速体验大模型，领先探索 AI 开源世界",
          "zh_Hans": "快速体验大模型，领先探索 AI 开源世界"
        },
        "category": "model",
        "created_at": "2024-12-02T14:50:16Z",
        "endpoint": {},
        "icon": "langgenius/packages/gitee_ai/_assets/Gitee-AI-Logo.svg",
        "index_id": "langgenius___gitee_ai",
        "install_count": 1143,
        "introduction": "## Overview\n\nGitee AI is a suite of AI-powered tools integrated within the Gitee platform, designed to boost developer productivity. It encompasses features like code completion and static analysis, and utilizes advanced models such as the text-generation model `Qwen2.5-14B-Instruct`, the vision model `Qwen2-VL-72B-Instruct`, and the speech synthesis model fish-speech-1.5. Gitee AI enhances various development tasks, from writing code to creating visual content and audio. It aims to streamline workflows and offer intelligent assistance across coding, collaboration, and content generation within the Gitee environment.\n\n## Configuration\n\nAfter installing the plugin, configure the API key and API base within the Model Provider settings. Obtain your API key from [here](https://ai.gitee.com/dashboard/settings/tokens). Once saved, you can begin using Gitee AI to build your AI agents and agentic workflows.\n\n![](./_assets/giteeai_config.PNG)",
        "label": {
          "en_US": "Gitee AI",
          "zh_Hans": "Gitee AI"
        },
        "latest_package_identifier": "langgenius/gitee_ai:0.0.8@e0b6858fa5180c3fb07e2b143cc74c7fc780ec4bf939f296b8db75c0c1dc252c",
        "latest_version": "0.0.8",
        "model": {
          "background": null,
          "configurate_methods": [
            "predefined-model"
          ],
          "description": {
            "en_US": "快速体验大模型，领先探索 AI 开源世界",
            "zh_Hans": "快速体验大模型，领先探索 AI 开源世界"
          },
          "help": {
            "title": {
              "en_US": "Get your token from Gitee AI",
              "zh_Hans": "从 Gitee AI 获取 token"
            },
            "url": {
              "en_US": "https://ai.gitee.com/dashboard/settings/tokens"
            }
          },
          "icon_large": {
            "en_US": "Gitee-AI-Logo-full.svg"
          },
          "icon_small": {
            "en_US": "Gitee-AI-Logo.svg"
          },
          "label": {
            "en_US": "Gitee AI",
            "zh_Hans": "Gitee AI"
          },
          "model_credential_schema": null,
          "models": [
            {
              "deprecated": false,
              "features": [
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Align-DS-V",
                "zh_Hans": "Align-DS-V"
              },
              "model": "Align-DS-V",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 512,
                  "help": {
                    "en_US": "The maximum number of tokens that can be generated by the model varies depending on the model.",
                    "zh_Hans": "模型可生成的最大 token 个数，不同模型上限不同。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "zh_Hans": "最大Token数"
                  },
                  "max": 32768,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "zh_Hans": "采样温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 50,
                  "help": {
                    "en_US": "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be.",
                    "zh_Hans": "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
                  },
                  "label": {
                    "en_US": "Top K",
                    "zh_Hans": "Top K"
                  },
                  "max": 100,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation.",
                    "zh_Hans": "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": -1,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 1,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Used to track and differentiate conversation requests from different users.",
                    "zh_Hans": "用于追踪和区分不同用户的对话请求。"
                  },
                  "label": {
                    "en_US": "User",
                    "zh_Hans": "用户"
                  },
                  "max": null,
                  "min": null,
                  "name": "user",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "DeepSeek-R1-Distill-Qwen-1.5B",
                "zh_Hans": "DeepSeek-R1-Distill-Qwen-1.5B"
              },
              "model": "DeepSeek-R1-Distill-Qwen-1.5B",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": true,
                  "help": {
                    "en_US": "Whether to return the results in batches through streaming. If set to true, the generated text will be pushed to the user in real time during the generation process.",
                    "zh_Hans": "是否通过流式分批返回结果。如果设置为 true，生成过程中实时地向用户推送每一部分生成的文本。"
                  },
                  "label": {
                    "en_US": "Stream",
                    "zh_Hans": "流式"
                  },
                  "max": null,
                  "min": null,
                  "name": "stream",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "The maximum number of tokens that can be generated by the model varies depending on the model.",
                    "zh_Hans": "模型可生成的最大 token 个数，不同模型上限不同。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "zh_Hans": "最大Token数"
                  },
                  "max": 32768,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "zh_Hans": "采样温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 50,
                  "help": {
                    "en_US": "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be.",
                    "zh_Hans": "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
                  },
                  "label": {
                    "en_US": "Top K",
                    "zh_Hans": "Top K"
                  },
                  "max": 100,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation.",
                    "zh_Hans": "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": -1,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 1,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Used to track and differentiate conversation requests from different users.",
                    "zh_Hans": "用于追踪和区分不同用户的对话请求。"
                  },
                  "label": {
                    "en_US": "User",
                    "zh_Hans": "用户"
                  },
                  "max": null,
                  "min": null,
                  "name": "user",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "DeepSeek-R1-Distill-Qwen-14B",
                "zh_Hans": "DeepSeek-R1-Distill-Qwen-14B"
              },
              "model": "DeepSeek-R1-Distill-Qwen-14B",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": true,
                  "help": {
                    "en_US": "Whether to return the results in batches through streaming. If set to true, the generated text will be pushed to the user in real time during the generation process.",
                    "zh_Hans": "是否通过流式分批返回结果。如果设置为 true，生成过程中实时地向用户推送每一部分生成的文本。"
                  },
                  "label": {
                    "en_US": "Stream",
                    "zh_Hans": "流式"
                  },
                  "max": null,
                  "min": null,
                  "name": "stream",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "The maximum number of tokens that can be generated by the model varies depending on the model.",
                    "zh_Hans": "模型可生成的最大 token 个数，不同模型上限不同。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "zh_Hans": "最大Token数"
                  },
                  "max": 32768,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "zh_Hans": "采样温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 50,
                  "help": {
                    "en_US": "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be.",
                    "zh_Hans": "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
                  },
                  "label": {
                    "en_US": "Top K",
                    "zh_Hans": "Top K"
                  },
                  "max": 100,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation.",
                    "zh_Hans": "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": -1,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 1,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Used to track and differentiate conversation requests from different users.",
                    "zh_Hans": "用于追踪和区分不同用户的对话请求。"
                  },
                  "label": {
                    "en_US": "User",
                    "zh_Hans": "用户"
                  },
                  "max": null,
                  "min": null,
                  "name": "user",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "DeepSeek-R1-Distill-Qwen-32B",
                "zh_Hans": "DeepSeek-R1-Distill-Qwen-32B"
              },
              "model": "DeepSeek-R1-Distill-Qwen-32B",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": true,
                  "help": {
                    "en_US": "Whether to return the results in batches through streaming. If set to true, the generated text will be pushed to the user in real time during the generation process.",
                    "zh_Hans": "是否通过流式分批返回结果。如果设置为 true，生成过程中实时地向用户推送每一部分生成的文本。"
                  },
                  "label": {
                    "en_US": "Stream",
                    "zh_Hans": "流式"
                  },
                  "max": null,
                  "min": null,
                  "name": "stream",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "The maximum number of tokens that can be generated by the model varies depending on the model.",
                    "zh_Hans": "模型可生成的最大 token 个数，不同模型上限不同。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "zh_Hans": "最大Token数"
                  },
                  "max": 32768,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "zh_Hans": "采样温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 50,
                  "help": {
                    "en_US": "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be.",
                    "zh_Hans": "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
                  },
                  "label": {
                    "en_US": "Top K",
                    "zh_Hans": "Top K"
                  },
                  "max": 100,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation.",
                    "zh_Hans": "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": -1,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 1,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Used to track and differentiate conversation requests from different users.",
                    "zh_Hans": "用于追踪和区分不同用户的对话请求。"
                  },
                  "label": {
                    "en_US": "User",
                    "zh_Hans": "用户"
                  },
                  "max": null,
                  "min": null,
                  "name": "user",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "DeepSeek-R1-Distill-Qwen-7B",
                "zh_Hans": "DeepSeek-R1-Distill-Qwen-7B"
              },
              "model": "DeepSeek-R1-Distill-Qwen-7B",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": true,
                  "help": {
                    "en_US": "Whether to return the results in batches through streaming. If set to true, the generated text will be pushed to the user in real time during the generation process.",
                    "zh_Hans": "是否通过流式分批返回结果。如果设置为 true，生成过程中实时地向用户推送每一部分生成的文本。"
                  },
                  "label": {
                    "en_US": "Stream",
                    "zh_Hans": "流式"
                  },
                  "max": null,
                  "min": null,
                  "name": "stream",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "The maximum number of tokens that can be generated by the model varies depending on the model.",
                    "zh_Hans": "模型可生成的最大 token 个数，不同模型上限不同。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "zh_Hans": "最大Token数"
                  },
                  "max": 32768,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "zh_Hans": "采样温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 50,
                  "help": {
                    "en_US": "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be.",
                    "zh_Hans": "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
                  },
                  "label": {
                    "en_US": "Top K",
                    "zh_Hans": "Top K"
                  },
                  "max": 100,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation.",
                    "zh_Hans": "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": -1,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 1,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Used to track and differentiate conversation requests from different users.",
                    "zh_Hans": "用于追踪和区分不同用户的对话请求。"
                  },
                  "label": {
                    "en_US": "User",
                    "zh_Hans": "用户"
                  },
                  "max": null,
                  "min": null,
                  "name": "user",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "DeepSeek-R1",
                "zh_Hans": "DeepSeek-R1"
              },
              "model": "DeepSeek-R1",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": true,
                  "help": {
                    "en_US": "Whether to return the results in batches through streaming. If set to true, the generated text will be pushed to the user in real time during the generation process.",
                    "zh_Hans": "是否通过流式分批返回结果。如果设置为 true，生成过程中实时地向用户推送每一部分生成的文本。"
                  },
                  "label": {
                    "en_US": "Stream",
                    "zh_Hans": "流式"
                  },
                  "max": null,
                  "min": null,
                  "name": "stream",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "The maximum number of tokens that can be generated by the model varies depending on the model.",
                    "zh_Hans": "模型可生成的最大 token 个数，不同模型上限不同。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "zh_Hans": "最大Token数"
                  },
                  "max": 32768,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "zh_Hans": "采样温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 50,
                  "help": {
                    "en_US": "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be.",
                    "zh_Hans": "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
                  },
                  "label": {
                    "en_US": "Top K",
                    "zh_Hans": "Top K"
                  },
                  "max": 100,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation.",
                    "zh_Hans": "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": -1,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 1,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Used to track and differentiate conversation requests from different users.",
                    "zh_Hans": "用于追踪和区分不同用户的对话请求。"
                  },
                  "label": {
                    "en_US": "User",
                    "zh_Hans": "用户"
                  },
                  "max": null,
                  "min": null,
                  "name": "user",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "DeepSeek-V3",
                "zh_Hans": "DeepSeek-V3"
              },
              "model": "DeepSeek-V3",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": true,
                  "help": {
                    "en_US": "Whether to return the results in batches through streaming. If set to true, the generated text will be pushed to the user in real time during the generation process.",
                    "zh_Hans": "是否通过流式分批返回结果。如果设置为 true，生成过程中实时地向用户推送每一部分生成的文本。"
                  },
                  "label": {
                    "en_US": "Stream",
                    "zh_Hans": "流式"
                  },
                  "max": null,
                  "min": null,
                  "name": "stream",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "The maximum number of tokens that can be generated by the model varies depending on the model.",
                    "zh_Hans": "模型可生成的最大 token 个数，不同模型上限不同。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "zh_Hans": "最大Token数"
                  },
                  "max": 32768,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "zh_Hans": "采样温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 50,
                  "help": {
                    "en_US": "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be.",
                    "zh_Hans": "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
                  },
                  "label": {
                    "en_US": "Top K",
                    "zh_Hans": "Top K"
                  },
                  "max": 100,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation.",
                    "zh_Hans": "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": -1,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 1,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Used to track and differentiate conversation requests from different users.",
                    "zh_Hans": "用于追踪和区分不同用户的对话请求。"
                  },
                  "label": {
                    "en_US": "User",
                    "zh_Hans": "用户"
                  },
                  "max": null,
                  "min": null,
                  "name": "user",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "InternVL2-8B",
                "zh_Hans": "InternVL2-8B"
              },
              "model": "InternVL2-8B",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 512,
                  "help": {
                    "en_US": "The maximum number of tokens that can be generated by the model varies depending on the model.",
                    "zh_Hans": "模型可生成的最大 token 个数，不同模型上限不同。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "zh_Hans": "最大Token数"
                  },
                  "max": 32768,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "zh_Hans": "采样温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 50,
                  "help": {
                    "en_US": "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be.",
                    "zh_Hans": "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
                  },
                  "label": {
                    "en_US": "Top K",
                    "zh_Hans": "Top K"
                  },
                  "max": 100,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation.",
                    "zh_Hans": "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": -1,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 1,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Used to track and differentiate conversation requests from different users.",
                    "zh_Hans": "用于追踪和区分不同用户的对话请求。"
                  },
                  "label": {
                    "en_US": "User",
                    "zh_Hans": "用户"
                  },
                  "max": null,
                  "min": null,
                  "name": "user",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "InternVL2.5-26B",
                "zh_Hans": "InternVL2.5-26B"
              },
              "model": "InternVL2.5-26B",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 512,
                  "help": {
                    "en_US": "The maximum number of tokens that can be generated by the model varies depending on the model.",
                    "zh_Hans": "模型可生成的最大 token 个数，不同模型上限不同。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "zh_Hans": "最大Token数"
                  },
                  "max": 32768,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "zh_Hans": "采样温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 50,
                  "help": {
                    "en_US": "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be.",
                    "zh_Hans": "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
                  },
                  "label": {
                    "en_US": "Top K",
                    "zh_Hans": "Top K"
                  },
                  "max": 100,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation.",
                    "zh_Hans": "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": -1,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 1,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Used to track and differentiate conversation requests from different users.",
                    "zh_Hans": "用于追踪和区分不同用户的对话请求。"
                  },
                  "label": {
                    "en_US": "User",
                    "zh_Hans": "用户"
                  },
                  "max": null,
                  "min": null,
                  "name": "user",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "InternVL2.5-78B",
                "zh_Hans": "InternVL2.5-78B"
              },
              "model": "InternVL2.5-78B",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 512,
                  "help": {
                    "en_US": "The maximum number of tokens that can be generated by the model varies depending on the model.",
                    "zh_Hans": "模型可生成的最大 token 个数，不同模型上限不同。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "zh_Hans": "最大Token数"
                  },
                  "max": 32768,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "zh_Hans": "采样温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 50,
                  "help": {
                    "en_US": "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be.",
                    "zh_Hans": "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
                  },
                  "label": {
                    "en_US": "Top K",
                    "zh_Hans": "Top K"
                  },
                  "max": 100,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation.",
                    "zh_Hans": "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": -1,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 1,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Used to track and differentiate conversation requests from different users.",
                    "zh_Hans": "用于追踪和区分不同用户的对话请求。"
                  },
                  "label": {
                    "en_US": "User",
                    "zh_Hans": "用户"
                  },
                  "max": null,
                  "min": null,
                  "name": "user",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "QwQ-32B",
                "zh_Hans": "QwQ-32B"
              },
              "model": "QwQ-32B",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 512,
                  "help": {
                    "en_US": "The maximum number of tokens that can be generated by the model varies depending on the model.",
                    "zh_Hans": "模型可生成的最大 token 个数，不同模型上限不同。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "zh_Hans": "最大Token数"
                  },
                  "max": 32768,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "zh_Hans": "采样温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 50,
                  "help": {
                    "en_US": "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be.",
                    "zh_Hans": "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
                  },
                  "label": {
                    "en_US": "Top K",
                    "zh_Hans": "Top K"
                  },
                  "max": 100,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation.",
                    "zh_Hans": "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": -1,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 1,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Used to track and differentiate conversation requests from different users.",
                    "zh_Hans": "用于追踪和区分不同用户的对话请求。"
                  },
                  "label": {
                    "en_US": "User",
                    "zh_Hans": "用户"
                  },
                  "max": null,
                  "min": null,
                  "name": "user",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen2-72B-Instruct",
                "zh_Hans": "Qwen2-72B-Instruct"
              },
              "model": "Qwen2-72B-Instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": true,
                  "help": {
                    "en_US": "Whether to return the results in batches through streaming. If set to true, the generated text will be pushed to the user in real time during the generation process.",
                    "zh_Hans": "是否通过流式分批返回结果。如果设置为 true，生成过程中实时地向用户推送每一部分生成的文本。"
                  },
                  "label": {
                    "en_US": "Stream",
                    "zh_Hans": "流式"
                  },
                  "max": null,
                  "min": null,
                  "name": "stream",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "The maximum number of tokens that can be generated by the model varies depending on the model.",
                    "zh_Hans": "模型可生成的最大 token 个数，不同模型上限不同。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "zh_Hans": "最大Token数"
                  },
                  "max": 32768,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "zh_Hans": "采样温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 50,
                  "help": {
                    "en_US": "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be.",
                    "zh_Hans": "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
                  },
                  "label": {
                    "en_US": "Top K",
                    "zh_Hans": "Top K"
                  },
                  "max": 100,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation.",
                    "zh_Hans": "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": -1,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 1,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Used to track and differentiate conversation requests from different users.",
                    "zh_Hans": "用于追踪和区分不同用户的对话请求。"
                  },
                  "label": {
                    "en_US": "User",
                    "zh_Hans": "用户"
                  },
                  "max": null,
                  "min": null,
                  "name": "user",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen2-7B-Instruct",
                "zh_Hans": "Qwen2-7B-Instruct"
              },
              "model": "Qwen2-7B-Instruct",
              "model_properties": {
                "context_size": 24576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": true,
                  "help": {
                    "en_US": "Whether to return the results in batches through streaming. If set to true, the generated text will be pushed to the user in real time during the generation process.",
                    "zh_Hans": "是否通过流式分批返回结果。如果设置为 true，生成过程中实时地向用户推送每一部分生成的文本。"
                  },
                  "label": {
                    "en_US": "Stream",
                    "zh_Hans": "流式"
                  },
                  "max": null,
                  "min": null,
                  "name": "stream",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "The maximum number of tokens that can be generated by the model varies depending on the model.",
                    "zh_Hans": "模型可生成的最大 token 个数，不同模型上限不同。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "zh_Hans": "最大Token数"
                  },
                  "max": 24576,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "zh_Hans": "采样温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 50,
                  "help": {
                    "en_US": "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be.",
                    "zh_Hans": "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
                  },
                  "label": {
                    "en_US": "Top K",
                    "zh_Hans": "Top K"
                  },
                  "max": 100,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation.",
                    "zh_Hans": "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": -1,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 1,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Used to track and differentiate conversation requests from different users.",
                    "zh_Hans": "用于追踪和区分不同用户的对话请求。"
                  },
                  "label": {
                    "en_US": "User",
                    "zh_Hans": "用户"
                  },
                  "max": null,
                  "min": null,
                  "name": "user",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen2-VL-72B",
                "zh_Hans": "Qwen2-VL-72B"
              },
              "model": "Qwen2-VL-72B",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 512,
                  "help": {
                    "en_US": "The maximum number of tokens that can be generated by the model varies depending on the model.",
                    "zh_Hans": "模型可生成的最大 token 个数，不同模型上限不同。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "zh_Hans": "最大Token数"
                  },
                  "max": 32768,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "zh_Hans": "采样温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 50,
                  "help": {
                    "en_US": "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be.",
                    "zh_Hans": "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
                  },
                  "label": {
                    "en_US": "Top K",
                    "zh_Hans": "Top K"
                  },
                  "max": 100,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation.",
                    "zh_Hans": "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": -1,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 1,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Used to track and differentiate conversation requests from different users.",
                    "zh_Hans": "用于追踪和区分不同用户的对话请求。"
                  },
                  "label": {
                    "en_US": "User",
                    "zh_Hans": "用户"
                  },
                  "max": null,
                  "min": null,
                  "name": "user",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen2.5-14B-Instruct",
                "zh_Hans": "Qwen2.5-14B-Instruct"
              },
              "model": "Qwen2.5-14B-Instruct",
              "model_properties": {
                "context_size": 24576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 512,
                  "help": {
                    "en_US": "The maximum number of tokens that can be generated by the model varies depending on the model.",
                    "zh_Hans": "模型可生成的最大 token 个数，不同模型上限不同。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "zh_Hans": "最大Token数"
                  },
                  "max": 24576,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "zh_Hans": "采样温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 50,
                  "help": {
                    "en_US": "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be.",
                    "zh_Hans": "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
                  },
                  "label": {
                    "en_US": "Top K",
                    "zh_Hans": "Top K"
                  },
                  "max": 100,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation.",
                    "zh_Hans": "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": -1,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 1,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Used to track and differentiate conversation requests from different users.",
                    "zh_Hans": "用于追踪和区分不同用户的对话请求。"
                  },
                  "label": {
                    "en_US": "User",
                    "zh_Hans": "用户"
                  },
                  "max": null,
                  "min": null,
                  "name": "user",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen2.5-32B-Instruct",
                "zh_Hans": "Qwen2.5-32B-Instruct"
              },
              "model": "Qwen2.5-32B-Instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 512,
                  "help": {
                    "en_US": "The maximum number of tokens that can be generated by the model varies depending on the model.",
                    "zh_Hans": "模型可生成的最大 token 个数，不同模型上限不同。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "zh_Hans": "最大Token数"
                  },
                  "max": 32768,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "zh_Hans": "采样温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 50,
                  "help": {
                    "en_US": "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be.",
                    "zh_Hans": "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
                  },
                  "label": {
                    "en_US": "Top K",
                    "zh_Hans": "Top K"
                  },
                  "max": 100,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation.",
                    "zh_Hans": "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": -1,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 1,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Used to track and differentiate conversation requests from different users.",
                    "zh_Hans": "用于追踪和区分不同用户的对话请求。"
                  },
                  "label": {
                    "en_US": "User",
                    "zh_Hans": "用户"
                  },
                  "max": null,
                  "min": null,
                  "name": "user",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen2.5-72B-Instruct",
                "zh_Hans": "Qwen2.5-72B-Instruct"
              },
              "model": "Qwen2.5-72B-Instruct",
              "model_properties": {
                "context_size": 16384,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 512,
                  "help": {
                    "en_US": "The maximum number of tokens that can be generated by the model varies depending on the model.",
                    "zh_Hans": "模型可生成的最大 token 个数，不同模型上限不同。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "zh_Hans": "最大Token数"
                  },
                  "max": 16384,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "zh_Hans": "采样温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 50,
                  "help": {
                    "en_US": "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be.",
                    "zh_Hans": "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
                  },
                  "label": {
                    "en_US": "Top K",
                    "zh_Hans": "Top K"
                  },
                  "max": 100,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation.",
                    "zh_Hans": "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": -1,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 1,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Used to track and differentiate conversation requests from different users.",
                    "zh_Hans": "用于追踪和区分不同用户的对话请求。"
                  },
                  "label": {
                    "en_US": "User",
                    "zh_Hans": "用户"
                  },
                  "max": null,
                  "min": null,
                  "name": "user",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen2.5-VL-32B-Instruct",
                "zh_Hans": "Qwen2.5-VL-32B-Instruct"
              },
              "model": "Qwen2.5-VL-32B-Instruct",
              "model_properties": {
                "context_size": 24576,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 512,
                  "help": {
                    "en_US": "The maximum number of tokens that can be generated by the model varies depending on the model.",
                    "zh_Hans": "模型可生成的最大 token 个数，不同模型上限不同。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "zh_Hans": "最大Token数"
                  },
                  "max": 32768,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "zh_Hans": "采样温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 50,
                  "help": {
                    "en_US": "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be.",
                    "zh_Hans": "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
                  },
                  "label": {
                    "en_US": "Top K",
                    "zh_Hans": "Top K"
                  },
                  "max": 100,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation.",
                    "zh_Hans": "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": -1,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 1,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Used to track and differentiate conversation requests from different users.",
                    "zh_Hans": "用于追踪和区分不同用户的对话请求。"
                  },
                  "label": {
                    "en_US": "User",
                    "zh_Hans": "用户"
                  },
                  "max": null,
                  "min": null,
                  "name": "user",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Yi-34B-Chat",
                "zh_Hans": "Yi-34B-Chat"
              },
              "model": "Yi-34B-Chat",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": true,
                  "help": {
                    "en_US": "Whether to return the results in batches through streaming. If set to true, the generated text will be pushed to the user in real time during the generation process.",
                    "zh_Hans": "是否通过流式分批返回结果。如果设置为 true，生成过程中实时地向用户推送每一部分生成的文本。"
                  },
                  "label": {
                    "en_US": "Stream",
                    "zh_Hans": "流式"
                  },
                  "max": null,
                  "min": null,
                  "name": "stream",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "The maximum number of tokens that can be generated by the model varies depending on the model.",
                    "zh_Hans": "模型可生成的最大 token 个数，不同模型上限不同。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "zh_Hans": "最大Token数"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "zh_Hans": "采样温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 50,
                  "help": {
                    "en_US": "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be.",
                    "zh_Hans": "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
                  },
                  "label": {
                    "en_US": "Top K",
                    "zh_Hans": "Top K"
                  },
                  "max": 100,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation.",
                    "zh_Hans": "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": -1,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 1,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Used to track and differentiate conversation requests from different users.",
                    "zh_Hans": "用于追踪和区分不同用户的对话请求。"
                  },
                  "label": {
                    "en_US": "User",
                    "zh_Hans": "用户"
                  },
                  "max": null,
                  "min": null,
                  "name": "user",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "codegeex4-all-9b",
                "zh_Hans": "codegeex4-all-9b"
              },
              "model": "codegeex4-all-9b",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": true,
                  "help": {
                    "en_US": "Whether to return the results in batches through streaming. If set to true, the generated text will be pushed to the user in real time during the generation process.",
                    "zh_Hans": "是否通过流式分批返回结果。如果设置为 true，生成过程中实时地向用户推送每一部分生成的文本。"
                  },
                  "label": {
                    "en_US": "Stream",
                    "zh_Hans": "流式"
                  },
                  "max": null,
                  "min": null,
                  "name": "stream",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "The maximum number of tokens that can be generated by the model varies depending on the model.",
                    "zh_Hans": "模型可生成的最大 token 个数，不同模型上限不同。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "zh_Hans": "最大Token数"
                  },
                  "max": 32768,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "zh_Hans": "采样温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 50,
                  "help": {
                    "en_US": "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be.",
                    "zh_Hans": "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
                  },
                  "label": {
                    "en_US": "Top K",
                    "zh_Hans": "Top K"
                  },
                  "max": 100,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation.",
                    "zh_Hans": "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": -1,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 1,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Used to track and differentiate conversation requests from different users.",
                    "zh_Hans": "用于追踪和区分不同用户的对话请求。"
                  },
                  "label": {
                    "en_US": "User",
                    "zh_Hans": "用户"
                  },
                  "max": null,
                  "min": null,
                  "name": "user",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "deepseek-coder-33B-instruct",
                "zh_Hans": "deepseek-coder-33B-instruct"
              },
              "model": "deepseek-coder-33B-instruct",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": true,
                  "help": {
                    "en_US": "Whether to return the results in batches through streaming. If set to true, the generated text will be pushed to the user in real time during the generation process.",
                    "zh_Hans": "是否通过流式分批返回结果。如果设置为 true，生成过程中实时地向用户推送每一部分生成的文本。"
                  },
                  "label": {
                    "en_US": "Stream",
                    "zh_Hans": "流式"
                  },
                  "max": null,
                  "min": null,
                  "name": "stream",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "The maximum number of tokens that can be generated by the model varies depending on the model.",
                    "zh_Hans": "模型可生成的最大 token 个数，不同模型上限不同。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "zh_Hans": "最大Token数"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "zh_Hans": "采样温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 50,
                  "help": {
                    "en_US": "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be.",
                    "zh_Hans": "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
                  },
                  "label": {
                    "en_US": "Top K",
                    "zh_Hans": "Top K"
                  },
                  "max": 100,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation.",
                    "zh_Hans": "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": -1,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 1,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Used to track and differentiate conversation requests from different users.",
                    "zh_Hans": "用于追踪和区分不同用户的对话请求。"
                  },
                  "label": {
                    "en_US": "User",
                    "zh_Hans": "用户"
                  },
                  "max": null,
                  "min": null,
                  "name": "user",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "tool-call",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gemma-3-27b-it",
                "zh_Hans": "gemma-3-27b-it"
              },
              "model": "gemma-3-27b-it",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": true,
                  "help": {
                    "en_US": "Whether to return the results in batches through streaming. If set to true, the generated text will be pushed to the user in real time during the generation process.",
                    "zh_Hans": "是否通过流式分批返回结果。如果设置为 true，生成过程中实时地向用户推送每一部分生成的文本。"
                  },
                  "label": {
                    "en_US": "Stream",
                    "zh_Hans": "流式"
                  },
                  "max": null,
                  "min": null,
                  "name": "stream",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "The maximum number of tokens that can be generated by the model varies depending on the model.",
                    "zh_Hans": "模型可生成的最大 token 个数，不同模型上限不同。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "zh_Hans": "最大Token数"
                  },
                  "max": 32768,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "zh_Hans": "采样温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 50,
                  "help": {
                    "en_US": "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be.",
                    "zh_Hans": "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
                  },
                  "label": {
                    "en_US": "Top K",
                    "zh_Hans": "Top K"
                  },
                  "max": 100,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation.",
                    "zh_Hans": "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": -1,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 1,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Used to track and differentiate conversation requests from different users.",
                    "zh_Hans": "用于追踪和区分不同用户的对话请求。"
                  },
                  "label": {
                    "en_US": "User",
                    "zh_Hans": "用户"
                  },
                  "max": null,
                  "min": null,
                  "name": "user",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "glm-4-9b-chat",
                "zh_Hans": "glm-4-9b-chat"
              },
              "model": "glm-4-9b-chat",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": true,
                  "help": {
                    "en_US": "Whether to return the results in batches through streaming. If set to true, the generated text will be pushed to the user in real time during the generation process.",
                    "zh_Hans": "是否通过流式分批返回结果。如果设置为 true，生成过程中实时地向用户推送每一部分生成的文本。"
                  },
                  "label": {
                    "en_US": "Stream",
                    "zh_Hans": "流式"
                  },
                  "max": null,
                  "min": null,
                  "name": "stream",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "boolean",
                  "use_template": null
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "The maximum number of tokens that can be generated by the model varies depending on the model.",
                    "zh_Hans": "模型可生成的最大 token 个数，不同模型上限不同。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "zh_Hans": "最大Token数"
                  },
                  "max": 32768,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": true,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "zh_Hans": "采样温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time.",
                    "zh_Hans": "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 1,
                  "required": true,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 50,
                  "help": {
                    "en_US": "The value range is [0,100], which limits the model to only select from the top k words with the highest probability when choosing the next word at each step. The larger the value, the more diverse text generation will be.",
                    "zh_Hans": "取值范围为 [0,100]，限制模型在每一步选择下一个词时，只从概率最高的前 k 个词中选取。数值越大，文本生成越多样。"
                  },
                  "label": {
                    "en_US": "Top K",
                    "zh_Hans": "Top K"
                  },
                  "max": 100,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": true,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Used to adjust the frequency of repeated content in automatically generated text. Positive numbers reduce repetition, while negative numbers increase repetition. After setting this parameter, if a word has already appeared in the text, the model will decrease the probability of choosing that word for subsequent generation.",
                    "zh_Hans": "用于调整自动生成文本中重复内容的频率。正数减少重复，负数增加重复。设置此参数后，如果一个词在文本中已经出现过，模型在后续生成中选择该词的概率会降低。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": -1,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 1,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Used to track and differentiate conversation requests from different users.",
                    "zh_Hans": "用于追踪和区分不同用户的对话请求。"
                  },
                  "label": {
                    "en_US": "User",
                    "zh_Hans": "用户"
                  },
                  "max": null,
                  "min": null,
                  "name": "user",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "bce-reranker-base_v1"
              },
              "model": "bce-reranker-base_v1",
              "model_properties": {
                "context_size": 512
              },
              "model_type": "rerank",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "bge-reranker-v2-m3"
              },
              "model": "bge-reranker-v2-m3",
              "model_properties": {
                "context_size": 8192
              },
              "model_type": "rerank",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "jina-reranker-m0"
              },
              "model": "jina-reranker-m0",
              "model_properties": {
                "context_size": 10240
              },
              "model_type": "rerank",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "SenseVoiceSmall"
              },
              "model": "SenseVoiceSmall",
              "model_properties": {
                "file_upload_limit": 1,
                "supported_file_extensions": "flac,mp3,mp4,mpeg,mpga,m4a,ogg,wav,webm"
              },
              "model_type": "speech2text",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "whisper-base"
              },
              "model": "whisper-base",
              "model_properties": {
                "file_upload_limit": 1,
                "supported_file_extensions": "flac,mp3,mp4,mpeg,mpga,m4a,ogg,wav,webm"
              },
              "model_type": "speech2text",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "whisper-large-v3-turbo"
              },
              "model": "whisper-large-v3-turbo",
              "model_properties": {
                "file_upload_limit": 1,
                "supported_file_extensions": "flac,mp3,mp4,mpeg,mpga,m4a,ogg,wav,webm"
              },
              "model_type": "speech2text",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "whisper-large"
              },
              "model": "whisper-large",
              "model_properties": {
                "file_upload_limit": 1,
                "supported_file_extensions": "flac,mp3,mp4,mpeg,mpga,m4a,ogg,wav,webm"
              },
              "model_type": "speech2text",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "bce-embedding-base_v1",
                "zh_Hans": "bce-embedding-base_v1"
              },
              "model": "bce-embedding-base_v1",
              "model_properties": {
                "context_size": 512,
                "max_chunks": 20
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "bge-large-zh-v1.5",
                "zh_Hans": "bge-large-zh-v1.5"
              },
              "model": "bge-large-zh-v1.5",
              "model_properties": {
                "context_size": 512,
                "max_chunks": 20
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "bge-m3",
                "zh_Hans": "bge-m3"
              },
              "model": "bge-m3",
              "model_properties": {
                "context_size": 8192,
                "max_chunks": 20
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "bge-small-zh-v1.5",
                "zh_Hans": "bge-small-zh-v1.5"
              },
              "model": "bge-small-zh-v1.5",
              "model_properties": {
                "context_size": 512,
                "max_chunks": 20
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "ChatTTS"
              },
              "model": "ChatTTS",
              "model_properties": {
                "audio_type": "mp3",
                "default_voice": "default",
                "max_workers": 5,
                "voices": [
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "default",
                    "name": "Default"
                  }
                ],
                "word_limit": 3500
              },
              "model_type": "tts",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "CosyVoice2"
              },
              "model": "CosyVoice2",
              "model_properties": {
                "audio_type": "mp3",
                "default_voice": "default",
                "max_workers": 5,
                "voices": [
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "default",
                    "name": "Default"
                  }
                ],
                "word_limit": 3500
              },
              "model_type": "tts",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "FunAudioLLM-CosyVoice-300M"
              },
              "model": "FunAudioLLM-CosyVoice-300M",
              "model_properties": {
                "audio_type": "mp3",
                "default_voice": "default",
                "max_workers": 5,
                "voices": [
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "default",
                    "name": "Default"
                  }
                ],
                "word_limit": 3500
              },
              "model_type": "tts",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "fish-speech-1.2-sft"
              },
              "model": "fish-speech-1.2-sft",
              "model_properties": {
                "audio_type": "mp3",
                "default_voice": "default",
                "max_workers": 5,
                "voices": [
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "default",
                    "name": "Default"
                  }
                ],
                "word_limit": 3500
              },
              "model_type": "tts",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "speecht5_tts"
              },
              "model": "speecht5_tts",
              "model_properties": {
                "audio_type": "mp3",
                "default_voice": "default",
                "max_workers": 5,
                "voices": [
                  {
                    "language": [
                      "zh-Hans",
                      "en-US",
                      "de-DE",
                      "fr-FR",
                      "es-ES",
                      "it-IT",
                      "th-TH",
                      "id-ID"
                    ],
                    "mode": "default",
                    "name": "Default"
                  }
                ],
                "word_limit": 3500
              },
              "model_type": "tts",
              "parameter_rules": [],
              "pricing": null
            }
          ],
          "position": {
            "llm": [
              "Qwen2.5-72B-Instruct",
              "Qwen2.5-14B-Instruct",
              "Qwen2-7B-Instruct",
              "Qwen2.5-32B-Instruct",
              "Qwen2-72B-Instruct",
              "Qwen2-VL-72B",
              "Qwen2.5-VL-32B-Instruct",
              "QwQ-32B",
              "Align-DS-V",
              "Yi-34B-Chat",
              "glm-4-9b-chat",
              "deepseek-coder-33B-instruct",
              "codegeex4-all-9b",
              "InternVL2-8B",
              "InternVL2.5-26B",
              "InternVL2.5-78B",
              "DeepSeek-R1-Distill-Qwen-32B",
              "DeepSeek-R1-Distill-Qwen-1.5B",
              "DeepSeek-R1-Distill-Qwen-14B",
              "DeepSeek-R1-Distill-Qwen-7B",
              "DeepSeek-V3",
              "DeepSeek-R1",
              "gemma-3-27b-it"
            ],
            "rerank": [
              "jina-reranker-m0",
              "bge-reranker-v2-m3",
              "bce-reranker-base_v1"
            ],
            "speech2text": [
              "whisper-base",
              "whisper-large",
              "whisper-large-v3-turbo",
              "SenseVoiceSmall"
            ],
            "text_embedding": [
              "bge-large-zh-v1.5",
              "bge-small-zh-v1.5",
              "bge-m3",
              "bce-embedding-base_v1"
            ],
            "tts": [
              "speecht5_tts",
              "ChatTTS",
              "fish-speech-1.2-sft",
              "CosyVoice2",
              "FunAudioLLM-CosyVoice-300M"
            ]
          },
          "provider": "gitee_ai",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              }
            ]
          },
          "supported_model_types": [
            "llm",
            "text-embedding",
            "rerank",
            "speech2text",
            "tts"
          ]
        },
        "name": "gitee_ai",
        "org": "langgenius",
        "plugin_id": "langgenius/gitee_ai",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/gitee_ai.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "image"
          }
        ],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-14T11:15:13Z",
        "version_updated_at": "2025-04-14T11:15:13Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Elasticsearch ",
          "ja_JP": "Elasticsearch ",
          "pt_BR": "Elasticsearch ",
          "zh_Hans": "Elasticsearch "
        },
        "category": "tool",
        "created_at": "2025-03-14T11:43:16Z",
        "endpoint": {},
        "icon": "quicksandzn/packages/elasticsearch/_assets/icon.svg",
        "index_id": "quicksandzn___elasticsearch",
        "install_count": 1102,
        "introduction": "## Elasticsearch\n\n- **Author:** [quicksandzn](https://github.com/quicksandznzn)\n- **Github:** https://github.com/quicksandznzn/dify-plugin-elasticsearch\n- **Version:** 0.0.5\n- **Type:** tool\n\n### Description\n\nThis plugin is used to search for data in Elasticsearch.\n\n### Usage\n\n- Set Up Authorization\n\n![img.png](_assets/img-5.png)\n\n- Query Example\n\n![img.png](_assets/img-2.png)\n\n- Create Example:\n\n![img.png](_assets/img-3.png)",
        "label": {
          "en_US": "Elasticsearch",
          "ja_JP": "Elasticsearch",
          "pt_BR": "Elasticsearch",
          "zh_Hans": "Elasticsearch"
        },
        "latest_package_identifier": "quicksandzn/elasticsearch:0.0.5@5c97748cc033bb83b856fd5b53e145f5ab3da184aad37b8f8f6ba76ded0bfd2a",
        "latest_version": "0.0.5",
        "model": {},
        "name": "elasticsearch",
        "org": "quicksandzn",
        "plugin_id": "quicksandzn/elasticsearch",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/es.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Get your endpoint from elasticsearch",
                "zh_Hans": "从 elasticsearch 获取您的 endpoint"
              },
              "label": {
                "en_US": "Endpoint",
                "zh_Hans": "Endpoint"
              },
              "name": "endpoint",
              "options": null,
              "placeholder": {
                "en_US": "Please input your endpoint",
                "zh_Hans": "请输入你的 endpoint"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": "https://www.elastic.co/guide/en/elasticsearch/client/python-api/current/getting-started-python.html"
            },
            {
              "default": false,
              "help": null,
              "label": {
                "en_US": "Verify Certs",
                "zh_Hans": "是否验证证书"
              },
              "name": "verify_certs",
              "options": null,
              "placeholder": null,
              "required": false,
              "scope": null,
              "type": "boolean",
              "url": null
            },
            {
              "default": "no_auth",
              "help": null,
              "label": {
                "en_US": "Authentication Method",
                "zh_Hans": "鉴权方式"
              },
              "name": "auth_method",
              "options": [
                {
                  "label": {
                    "en_US": "No Auth",
                    "zh_Hans": "无鉴权"
                  },
                  "value": "no_auth"
                },
                {
                  "label": {
                    "en_US": "API Key",
                    "zh_Hans": "API Key"
                  },
                  "value": "api_key"
                },
                {
                  "label": {
                    "en_US": "Basic Auth",
                    "zh_Hans": "基础认证"
                  },
                  "value": "basic"
                }
              ],
              "placeholder": null,
              "required": true,
              "scope": null,
              "type": "select",
              "url": null
            },
            {
              "default": null,
              "help": {
                "en_US": "Get your API key from Elasticsearch",
                "zh_Hans": "从 Elasticsearch 获取您的 API key"
              },
              "label": {
                "en_US": "API Key",
                "zh_Hans": "API Key"
              },
              "name": "api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your API key",
                "zh_Hans": "请输入你的 API key"
              },
              "required": false,
              "scope": null,
              "type": "secret-input",
              "url": "https://www.elastic.co/guide/en/elasticsearch/client/python-api/8.17/connecting.html#auth-apikey"
            },
            {
              "default": null,
              "help": {
                "en_US": "Username for Basic Authentication",
                "zh_Hans": "基础认证的用户名"
              },
              "label": {
                "en_US": "Username",
                "zh_Hans": "用户名"
              },
              "name": "username",
              "options": null,
              "placeholder": {
                "en_US": "Please input your username",
                "zh_Hans": "请输入你的用户名"
              },
              "required": false,
              "scope": null,
              "type": "text-input",
              "url": "https://www.elastic.co/guide/en/elasticsearch/client/python-api/8.17/connecting.html#auth-basic"
            },
            {
              "default": null,
              "help": {
                "en_US": "Password for Basic Authentication",
                "zh_Hans": "基础认证的密码"
              },
              "label": {
                "en_US": "Password",
                "zh_Hans": "密码"
              },
              "name": "password",
              "options": null,
              "placeholder": {
                "en_US": "Please input your password",
                "zh_Hans": "请输入你的密码"
              },
              "required": false,
              "scope": null,
              "type": "secret-input",
              "url": "https://www.elastic.co/guide/en/elasticsearch/client/python-api/8.17/connecting.html#auth-basic"
            }
          ],
          "identity": {
            "author": "quicksandzn",
            "description": {
              "en_US": "Elasticsearch",
              "pt_BR": "Elasticsearch",
              "zh_Hans": "Elasticsearch"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Elasticsearch",
              "pt_BR": "Elasticsearch",
              "zh_Hans": "Elasticsearch"
            },
            "name": "elasticsearch",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Elasticsearch Query",
                  "zh_Hans": "Elasticsearch Query"
                },
                "llm": "Elasticsearch Query"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "quicksandzn",
                "label": {
                  "en_US": "Elasticsearch Query",
                  "zh_Hans": "Elasticsearch Query"
                },
                "name": "search"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "index name",
                    "pt_BR": "index name",
                    "zh_Hans": "index name"
                  },
                  "label": {
                    "en_US": "Index name",
                    "pt_BR": "Index name",
                    "zh_Hans": "索引名称"
                  },
                  "llm_description": "index name",
                  "max": null,
                  "min": null,
                  "name": "index",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "DSL Query",
                    "zh_Hans": "DSL 查询语句"
                  },
                  "label": {
                    "en_US": "DSL Query",
                    "zh_Hans": "DSL 查询语句"
                  },
                  "llm_description": "Elasticsearch DSL Query",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Source Fields (default: *, multiple fields separated by commas)",
                    "zh_Hans": "返回字段 (默认: 全部，多个字段以逗号分隔)"
                  },
                  "label": {
                    "en_US": "Source Fields",
                    "zh_Hans": "返回字段"
                  },
                  "llm_description": "Elasticsearch Source",
                  "max": null,
                  "min": null,
                  "name": "source_includes",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 0,
                  "form": "llm",
                  "human_description": {
                    "en_US": "From",
                    "zh_Hans": "查询的起始位置"
                  },
                  "label": {
                    "en_US": "From",
                    "zh_Hans": "查询的起始位置"
                  },
                  "llm_description": "Elasticsearch Query from",
                  "max": null,
                  "min": null,
                  "name": "from",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 10,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Size",
                    "zh_Hans": "文档数量"
                  },
                  "label": {
                    "en_US": "Size",
                    "zh_Hans": "文档数量"
                  },
                  "llm_description": "Elasticsearch Query Size",
                  "max": null,
                  "min": null,
                  "name": "size",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Elasticsearch Create",
                  "zh_Hans": "Elasticsearch Create"
                },
                "llm": "Elasticsearch Create"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "quicksandzn",
                "label": {
                  "en_US": "Elasticsearch Create",
                  "zh_Hans": "Elasticsearch Create"
                },
                "name": "create"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "index name",
                    "pt_BR": "index name",
                    "zh_Hans": "index name"
                  },
                  "label": {
                    "en_US": "Index name",
                    "pt_BR": "Index name",
                    "zh_Hans": "索引名称"
                  },
                  "llm_description": "index name",
                  "max": null,
                  "min": null,
                  "name": "index",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Document ID",
                    "zh_Hans": "文档唯一ID"
                  },
                  "label": {
                    "en_US": "Document ID",
                    "zh_Hans": "文档唯一ID"
                  },
                  "llm_description": "Elasticsearch Create Document",
                  "max": null,
                  "min": null,
                  "name": "document_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Document",
                    "zh_Hans": "文档"
                  },
                  "label": {
                    "en_US": "Document",
                    "zh_Hans": "文档"
                  },
                  "llm_description": "Elasticsearch Document Content",
                  "max": null,
                  "min": null,
                  "name": "document",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-08T14:44:43Z",
        "version_updated_at": "2025-04-08T14:44:43Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Your waifu is here.",
          "zh_Hans": "你的老婆在这里。"
        },
        "category": "extension",
        "created_at": "2025-03-07T13:34:22Z",
        "endpoint": {
          "endpoints": [
            {
              "hidden": false,
              "method": "GET",
              "path": "/"
            },
            {
              "hidden": false,
              "method": "POST",
              "path": "/api/chat"
            },
            {
              "hidden": false,
              "method": "GET",
              "path": "/asset/<path:path>"
            },
            {
              "hidden": false,
              "method": "POST",
              "path": "/api/file/<name>"
            },
            {
              "hidden": false,
              "method": "GET",
              "path": "/api/file/<name>"
            }
          ],
          "settings": [
            {
              "default": "Candy",
              "help": null,
              "label": {
                "en_US": "Bot name",
                "pt_BR": "Nome do bot",
                "zh_Hans": "机器人名称"
              },
              "name": "bot_name",
              "options": null,
              "placeholder": {
                "en_US": "Please input your bot name",
                "pt_BR": "Por favor, insira o nome do seu bot",
                "zh_Hans": "请输入你的机器人名称"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "App",
                "pt_BR": "App",
                "zh_Hans": "App"
              },
              "name": "app",
              "options": null,
              "placeholder": null,
              "required": true,
              "scope": "chat",
              "type": "app-selector",
              "url": null
            }
          ]
        },
        "icon": "yeuoly/packages/waifu/_assets/waifu.gif",
        "index_id": "yeuoly___waifu",
        "install_count": 1099,
        "introduction": "# Waifu\n\nAuthor: [@Yeuoly](https://github.com/Yeuoly)\n\nWaifu is a Dify plugin that allows you to chat with a kawaii style webapp.\n\n## Overview\n\n![Overview](./_assets/chat.png)\n\nYou can setup your own waifu by uploading a custom avatar and background also.\n\n![Setup](./_assets/upload.png)\n\n## Usage\n\nInstall the plugin \n\n![Install](./_assets/install.png)\n\nThen setup this plugin in the `Plugin` page.\n\n![Setup](./_assets/setup1.png)\n\nFinally, click here to start chatting with your waifu.\n\n![Chat](./_assets/setup.png)\n",
        "label": {
          "en_US": "Waifu"
        },
        "latest_package_identifier": "yeuoly/waifu:0.0.1@29f712ac2be29d57371108b4de2b3e6f7480df5af6e8a77f170016bd591c648a",
        "latest_version": "0.0.1",
        "model": {},
        "name": "waifu",
        "org": "yeuoly",
        "plugin_id": "yeuoly/waifu",
        "plugins": {
          "agent_strategies": null,
          "endpoints": [
            "provider/waifu.yaml"
          ],
          "models": null,
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": true
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-03-07T13:34:40Z",
        "version_updated_at": "2025-03-07T13:34:40Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Generate random number, string, UUID, prime number and etc.",
          "zh_Hans": "生成随机数、字符串、UUID、质数等。"
        },
        "category": "tool",
        "created_at": "2025-03-18T03:05:05Z",
        "endpoint": {},
        "icon": "bowenliang123/packages/random/_assets/icon.png",
        "index_id": "bowenliang123___random",
        "install_count": 1007,
        "introduction": "# Random - Generator for random number and string\n\n**Author:** [bowenliang123](https://github.com/bowenliang123)\n\n**Github Repository:** https://github.com/bowenliang123/random\n\n**Dify Marketplace:** https://marketplace.dify.ai/plugins/bowenliang123/random\n\n## Description\n\nA Dify plugin to generate random number, string, UUID, prime number etc.\n\n## Tools\n\n### Random String:\n\n- Generate a random string with given length from alphabets and numbers.\n- Input parameters:\n    - `include_alphabets`: Include alphabets from both, either or none of [uppercase](https://docs.python.org/3/library/string.html#string.ascii_uppercase) or [lowercase](https://docs.python.org/3/library/string.html#string.ascii_lowercase) alphabets.\n    - `include_numbers`: Whether to include [numbers](https://docs.python.org/3/library/string.html#string.digits)\n    - `include_punctuation`: Whether to include punctuation characters from `!\"#$%&'()*+,-./:;<=>?@[\\]^_``{|}~`\n    - `string_count`: Number of random strings to generate\n- Output: \n    - eg. `TSUWUBoOIu4bZja7mdjTkKteaKVrhz` for requested length of 30.\n\n### Random Number:\n\n- Generate a random number in the given range of [ lower_bound, upper bound ] .\n- Input:\n    - `lower_bound` and `upper_bound`: The range of random number to generate. Either integer or float is accepted.\n    - `num_count`: Number of random numbers to generate\n- Output: \n    - If the digits is set to 0, an integer will be generated.\n\n    ![](_assets/img1.png)\n\n    ![](_assets/img2.png)\n\n### Random Prime Number:\n\n- Generate a random prime number in the given range of [ lower_bound, upper bound ] .\n- Input:\n    - `lower_bound` and `upper_bound`: The range of random prime number to generate. Either integer or float is\n      accepted.\n- Output: A prime number, or `NaN` if no prime number is found.\n\n### Random UUID:\n\n- Generate a random string of [UUID v4](https://docs.python.org/3/library/uuid.html#uuid.uuid4).\n\n    ![](_assets/img3.png)\n\n## Changelog\n\n- 0.1.0\n  - change the random generation from `random` to `secrets` for better randomness and security\n  - fix decimal generation with digits guaranteed incase of digits greater than 17\n- 0.0.3\n  - support generating multiple random numbers\n- 0.0.1\n  - introducing tools for random number, prime number and UUID v4 generation\n\n## License\n- Apache License 2.0\n\n## Privacy\n\nThis plugin collects no data.\n\nAll the random object generation are completed locally. NO data is transmitted to third-party services.\n",
        "label": {
          "en_US": "Random Generator",
          "zh_Hans": "随机生成器"
        },
        "latest_package_identifier": "bowenliang123/random:0.1.0@04bedbcdb1affdf38ffd2a09d912e8fd1425724bc8775c1fe18774858ce63d08",
        "latest_version": "0.1.0",
        "model": {},
        "name": "random",
        "org": "bowenliang123",
        "plugin_id": "bowenliang123/random",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/random.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "bowenliang123",
            "description": {
              "en_US": "Generate random number, string, UUID, prime number and etc.",
              "zh_Hans": "生成随机数、字符串、UUID、质数等。"
            },
            "icon": "icon.png",
            "label": {
              "en_US": "Random Generator",
              "zh_Hans": "随机生成器"
            },
            "name": "random",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Generate random number(s).",
                  "zh_Hans": "生成随机数"
                },
                "llm": "Generate random number(s)."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "bowenliang123",
                "label": {
                  "en_US": "Random number(s)",
                  "zh_Hans": "生成随机数"
                },
                "name": "random_num"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": 0,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Included lower bound of the random number, accepting integer or float.",
                    "zh_Hans": "包含的数值下限，可填写整数或小数"
                  },
                  "label": {
                    "en_US": "Lower bound",
                    "zh_Hans": "范围下限"
                  },
                  "llm_description": "Lower bound of the random number.",
                  "max": null,
                  "min": null,
                  "name": "lower_bound",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 1024,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Included upper bound of the random number, accepting integer or float.",
                    "zh_Hans": "包含的数值上限，可填写整数或小数"
                  },
                  "label": {
                    "en_US": "Upper bound",
                    "zh_Hans": "范围上限"
                  },
                  "llm_description": "Upper bound of the random number.",
                  "max": null,
                  "min": null,
                  "name": "upper_bound",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 0,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Digits of the random number, default to 0. When 0, it generates an integer.",
                    "zh_Hans": "小数位数，默认为0。如果位数为0，则生成整数。"
                  },
                  "label": {
                    "en_US": "digits",
                    "zh_Hans": "小数位数"
                  },
                  "llm_description": "Digits of the random number, default to 0. When 0, it generates an integer.",
                  "max": null,
                  "min": null,
                  "name": "digits",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 1,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Default to 1. All generated numbers will be separated by \",\" delimiter.",
                    "zh_Hans": "默认为1。所有生成的随机数会以\",\"分隔符分隔。"
                  },
                  "label": {
                    "en_US": "Number of random numbers",
                    "zh_Hans": "生成的随机数个数"
                  },
                  "llm_description": "Number of random numbers to generate, default to 1. All generated numbers will be separated by \",\" delimiter.",
                  "max": null,
                  "min": null,
                  "name": "num_count",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Generate a random UUID."
                },
                "llm": "Generate a random UUID."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "bowenliang123",
                "label": {
                  "en_US": "Random UUID",
                  "zh_Hans": "生成随机UUID"
                },
                "name": "random_uuid"
              },
              "output_schema": null,
              "parameters": null
            },
            {
              "description": {
                "human": {
                  "en_US": "Generate a random string with given length from alphabets and numbers."
                },
                "llm": "Generate a random string with given length from alphabets and numbers."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "bowenliang123",
                "label": {
                  "en_US": "Random String",
                  "zh_Hans": "生成随机字符串"
                },
                "name": "random_string"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": 0,
                  "form": "llm",
                  "human_description": {
                    "en_US": "String length",
                    "zh_Hans": "字符串长度"
                  },
                  "label": {
                    "en_US": "String length",
                    "zh_Hans": "字符串长度"
                  },
                  "llm_description": "String length",
                  "max": null,
                  "min": null,
                  "name": "length",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "upper_and_lower",
                  "form": "form",
                  "human_description": {
                    "en_US": "Include uppercase or lowercase alphabets, default to include both",
                    "zh_Hans": "包含大写或小写字母, 默认为包含全部"
                  },
                  "label": {
                    "en_US": "Included alphabets",
                    "zh_Hans": "包含的英文字母"
                  },
                  "llm_description": "Include uppercase or lowercase alphabets",
                  "max": null,
                  "min": null,
                  "name": "include_alphabets",
                  "options": [
                    {
                      "label": {
                        "en_US": "Upper and lower case (a-zA-Z)",
                        "zh_Hans": "大写和小写英文字母 (a-zA-Z)"
                      },
                      "value": "upper_and_lower"
                    },
                    {
                      "label": {
                        "en_US": "Uppercase only (A-Z)",
                        "zh_Hans": "仅大写英文字母 (A-Z)"
                      },
                      "value": "uppercase_only"
                    },
                    {
                      "label": {
                        "en_US": "Lowercase only (a-z)",
                        "zh_Hans": "仅小写英文字母 (a-z)"
                      },
                      "value": "lowercase_only"
                    },
                    {
                      "label": {
                        "en_US": "Not included",
                        "zh_Hans": "不包含"
                      },
                      "value": "not_included"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "true",
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether include numbers (0-9), default to Yes",
                    "zh_Hans": "是否包含数字（0-9）, 默认为是"
                  },
                  "label": {
                    "en_US": "Whether include numbers",
                    "zh_Hans": "是否包含数字"
                  },
                  "llm_description": "Whether include numbers",
                  "max": null,
                  "min": null,
                  "name": "include_numbers",
                  "options": [
                    {
                      "label": {
                        "en_US": "Yes",
                        "zh_Hans": "是"
                      },
                      "value": "true"
                    },
                    {
                      "label": {
                        "en_US": "No",
                        "zh_Hans": "否"
                      },
                      "value": "false"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "false",
                  "form": "form",
                  "human_description": {
                    "en_US": "Default to false. Punctuation chars are !\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~",
                    "zh_Hans": "默认为否。特殊字符为 !\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~"
                  },
                  "label": {
                    "en_US": "Include punctuation",
                    "zh_Hans": "是否包含特殊字符"
                  },
                  "llm_description": "Whether include punctuation symbol characters",
                  "max": null,
                  "min": null,
                  "name": "include_punctuation",
                  "options": [
                    {
                      "label": {
                        "en_US": "Yes",
                        "zh_Hans": "是"
                      },
                      "value": "true"
                    },
                    {
                      "label": {
                        "en_US": "No",
                        "zh_Hans": "否"
                      },
                      "value": "false"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "1",
                  "form": "llm",
                  "human_description": {
                    "en_US": "Default to 1",
                    "zh_Hans": "默认为1"
                  },
                  "label": {
                    "en_US": "Number of random strings",
                    "zh_Hans": "生成的字符串个数"
                  },
                  "llm_description": "Number of random strings to generate, default to 1",
                  "max": null,
                  "min": null,
                  "name": "string_count",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": ",",
                  "form": "form",
                  "human_description": {
                    "en_US": "Default to \",\" comma",
                    "zh_Hans": "默认为 \",\" 小逗号"
                  },
                  "label": {
                    "en_US": "Separator for multiple generated strings",
                    "zh_Hans": "生成的多个字符串的分隔符"
                  },
                  "llm_description": "Separator for multiple generated strings, default to \",\"",
                  "max": null,
                  "min": null,
                  "name": "separator",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Generate a random prime number."
                },
                "llm": "Generate a random prime number."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "bowenliang123",
                "label": {
                  "en_US": "Random prime number",
                  "zh_Hans": "生成随机质数"
                },
                "name": "random_prime"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": 0,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Included lower bound of the random number, accepting integer or float.",
                    "zh_Hans": "包括的数值下限，可填写整数或小数"
                  },
                  "label": {
                    "en_US": "Lower bound",
                    "zh_Hans": "数值下限"
                  },
                  "llm_description": "Lower bound of the random number.",
                  "max": null,
                  "min": null,
                  "name": "lower_bound",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 1024,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Included upper bound of the random number, accepting integer or float.",
                    "zh_Hans": "包括的数值上限，可填写整数或小数"
                  },
                  "label": {
                    "en_US": "Upper bound",
                    "zh_Hans": "范围上限"
                  },
                  "llm_description": "Upper bound of the random number.",
                  "max": null,
                  "min": null,
                  "name": "upper_bound",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-02T01:34:30Z",
        "version_updated_at": "2025-04-02T01:34:30Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Translate text using Google",
          "zh_Hans": "使用 Google 进行翻译"
        },
        "category": "tool",
        "created_at": "2024-11-29T06:14:44Z",
        "endpoint": {},
        "icon": "langgenius/packages/google_translate/_assets/icon.svg",
        "index_id": "langgenius___google_translate",
        "install_count": 989,
        "introduction": "# Overview\nThe Google Translate Tool allows users to translate text from one language to another seamlessly. It leverages Google's robust translation capabilities to provide accurate and efficient translations. This tool is designed for developers and teams who need to integrate translation functionality into their workflows or applications.\n\n# Configure\n1. Install Google Translate from Dify Marketplace.\n![](_assets/google_translate_install.PNG)\n2. Add Google Translate to your workflow.\n3. Fill in variables.\n![](_assets/google_translate_configure.png)\n  - **Text Content** (Required): This is the string input that needs to be translated. You can type or insert the variable directly into the provided field.\n  - **Destination Language**: This is a required field where you specify the target language for translation (e.g., \"English,\" \"Spanish,\" \"French\"). Ensure the name of the language matches Google's supported languages.\n![](_assets/google_translate_test.PNG)",
        "label": {
          "en_US": "Google Translate",
          "zh_Hans": "谷歌翻译"
        },
        "latest_package_identifier": "langgenius/google_translate:0.0.2@1ebb3d28ec6eced92ec93ab085afc77ac34d9468ab9f64c98e2f8ed5021c93fe",
        "latest_version": "0.0.2",
        "model": {},
        "name": "google_translate",
        "org": "langgenius",
        "plugin_id": "langgenius/google_translate",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/google_translate.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "utilities"
          }
        ],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "Ron_Liu",
            "description": {
              "en_US": "Translate text using Google",
              "zh_Hans": "使用 Google 进行翻译"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Google Translate",
              "zh_Hans": "谷歌翻译"
            },
            "name": "google_translate",
            "tags": [
              "utilities"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool for Google Translate",
                  "zh_Hans": "Google 翻译"
                },
                "llm": "A tool for Google Translate"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Ron_Liu",
                "label": {
                  "en_US": "Translate",
                  "zh_Hans": "翻译"
                },
                "name": "translate"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Text content",
                    "zh_Hans": "需要翻译的文本内容"
                  },
                  "label": {
                    "en_US": "Text content",
                    "zh_Hans": "文本内容"
                  },
                  "llm_description": "Text content",
                  "max": null,
                  "min": null,
                  "name": "content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "en",
                  "form": "form",
                  "human_description": {
                    "en_US": "The destination language you want to translate.",
                    "zh_Hans": "你想翻译的目标语言"
                  },
                  "label": {
                    "en_US": "destination language",
                    "zh_Hans": "目标语言"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "dest",
                  "options": [
                    {
                      "label": {
                        "en_US": "Arabic",
                        "zh_Hans": "阿拉伯语"
                      },
                      "value": "ar"
                    },
                    {
                      "label": {
                        "en_US": "Bulgarian",
                        "zh_Hans": "保加利亚语"
                      },
                      "value": "bg"
                    },
                    {
                      "label": {
                        "en_US": "Catalan",
                        "zh_Hans": "加泰罗尼亚语"
                      },
                      "value": "ca"
                    },
                    {
                      "label": {
                        "en_US": "Chinese (Simplified)",
                        "zh_Hans": "中文（简体）"
                      },
                      "value": "zh-cn"
                    },
                    {
                      "label": {
                        "en_US": "Chinese (Traditional)",
                        "zh_Hans": "中文（繁体）"
                      },
                      "value": "zh-tw"
                    },
                    {
                      "label": {
                        "en_US": "Czech",
                        "zh_Hans": "捷克语"
                      },
                      "value": "cs"
                    },
                    {
                      "label": {
                        "en_US": "Danish",
                        "zh_Hans": "丹麦语"
                      },
                      "value": "da"
                    },
                    {
                      "label": {
                        "en_US": "Dutch",
                        "zh_Hans": "荷兰语"
                      },
                      "value": "nl"
                    },
                    {
                      "label": {
                        "en_US": "English",
                        "zh_Hans": "英语"
                      },
                      "value": "en"
                    },
                    {
                      "label": {
                        "en_US": "Estonian",
                        "zh_Hans": "爱沙尼亚语"
                      },
                      "value": "et"
                    },
                    {
                      "label": {
                        "en_US": "Finnish",
                        "zh_Hans": "芬兰语"
                      },
                      "value": "fi"
                    },
                    {
                      "label": {
                        "en_US": "French",
                        "zh_Hans": "法语"
                      },
                      "value": "fr"
                    },
                    {
                      "label": {
                        "en_US": "German",
                        "zh_Hans": "德语"
                      },
                      "value": "de"
                    },
                    {
                      "label": {
                        "en_US": "Greek",
                        "zh_Hans": "希腊语"
                      },
                      "value": "el"
                    },
                    {
                      "label": {
                        "en_US": "Hebrew",
                        "zh_Hans": "希伯来语"
                      },
                      "value": "iw"
                    },
                    {
                      "label": {
                        "en_US": "Hindi",
                        "zh_Hans": "印地语"
                      },
                      "value": "hi"
                    },
                    {
                      "label": {
                        "en_US": "Hungarian",
                        "zh_Hans": "匈牙利语"
                      },
                      "value": "hu"
                    },
                    {
                      "label": {
                        "en_US": "Indonesian",
                        "zh_Hans": "印尼语"
                      },
                      "value": "id"
                    },
                    {
                      "label": {
                        "en_US": "Italian",
                        "zh_Hans": "意大利语"
                      },
                      "value": "it"
                    },
                    {
                      "label": {
                        "en_US": "Japanese",
                        "zh_Hans": "日语"
                      },
                      "value": "ja"
                    },
                    {
                      "label": {
                        "en_US": "Kannada",
                        "zh_Hans": "卡纳达语"
                      },
                      "value": "kn"
                    },
                    {
                      "label": {
                        "en_US": "Korean",
                        "zh_Hans": "韩语"
                      },
                      "value": "ko"
                    },
                    {
                      "label": {
                        "en_US": "Latvian",
                        "zh_Hans": "拉脱维亚语"
                      },
                      "value": "lv"
                    },
                    {
                      "label": {
                        "en_US": "Lithuanian",
                        "zh_Hans": "立陶宛语"
                      },
                      "value": "lt"
                    },
                    {
                      "label": {
                        "en_US": "Malay",
                        "zh_Hans": "马来语"
                      },
                      "value": "my"
                    },
                    {
                      "label": {
                        "en_US": "Malayalam",
                        "zh_Hans": "马拉雅拉姆语"
                      },
                      "value": "ml"
                    },
                    {
                      "label": {
                        "en_US": "Marathi",
                        "zh_Hans": "马拉地语"
                      },
                      "value": "mr"
                    },
                    {
                      "label": {
                        "en_US": "Norwegian",
                        "zh_Hans": "挪威语"
                      },
                      "value": "no"
                    },
                    {
                      "label": {
                        "en_US": "Polish",
                        "zh_Hans": "波兰语"
                      },
                      "value": "pl"
                    },
                    {
                      "label": {
                        "en_US": "Portuguese (Brazil)",
                        "zh_Hans": "葡萄牙语（巴西）"
                      },
                      "value": "pt-br"
                    },
                    {
                      "label": {
                        "en_US": "Portuguese (Portugal)",
                        "zh_Hans": "葡萄牙语（葡萄牙）"
                      },
                      "value": "pt-pt"
                    },
                    {
                      "label": {
                        "en_US": "Punjabi",
                        "zh_Hans": "旁遮普语"
                      },
                      "value": "pa"
                    },
                    {
                      "label": {
                        "en_US": "Romanian",
                        "zh_Hans": "罗马尼亚语"
                      },
                      "value": "ro"
                    },
                    {
                      "label": {
                        "en_US": "Russian",
                        "zh_Hans": "俄语"
                      },
                      "value": "ru"
                    },
                    {
                      "label": {
                        "en_US": "Serbian",
                        "zh_Hans": "塞尔维亚语"
                      },
                      "value": "sr"
                    },
                    {
                      "label": {
                        "en_US": "Slovak",
                        "zh_Hans": "斯洛伐克语"
                      },
                      "value": "sk"
                    },
                    {
                      "label": {
                        "en_US": "Slovenian",
                        "zh_Hans": "斯洛文尼亚语"
                      },
                      "value": "sl"
                    },
                    {
                      "label": {
                        "en_US": "Spanish",
                        "zh_Hans": "西班牙语"
                      },
                      "value": "es"
                    },
                    {
                      "label": {
                        "en_US": "Swedish",
                        "zh_Hans": "瑞典语"
                      },
                      "value": "sv"
                    },
                    {
                      "label": {
                        "en_US": "Tamil",
                        "zh_Hans": "泰米尔语"
                      },
                      "value": "ta"
                    },
                    {
                      "label": {
                        "en_US": "Telugu",
                        "zh_Hans": "泰卢固语"
                      },
                      "value": "te"
                    },
                    {
                      "label": {
                        "en_US": "Thai",
                        "zh_Hans": "泰语"
                      },
                      "value": "th"
                    },
                    {
                      "label": {
                        "en_US": "Turkish",
                        "zh_Hans": "土耳其语"
                      },
                      "value": "tr"
                    },
                    {
                      "label": {
                        "en_US": "Ukrainian",
                        "zh_Hans": "乌克兰语"
                      },
                      "value": "uk"
                    },
                    {
                      "label": {
                        "en_US": "Vietnamese",
                        "zh_Hans": "越南语"
                      },
                      "value": "vi"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:16:54Z",
        "version_updated_at": "2025-02-17T07:16:54Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "NVIDIA NIM, a set of easy-to-use inference microservices.",
          "zh_Hans": "NVIDIA NIM，一组易于使用的模型推理微服务。"
        },
        "category": "model",
        "created_at": "2024-12-05T10:49:21Z",
        "endpoint": {},
        "icon": "langgenius/packages/nvidia_nim/_assets/icon_s_en.svg",
        "index_id": "langgenius___nvidia_nim",
        "install_count": 975,
        "introduction": "",
        "label": {
          "en_US": "NVIDIA NIM"
        },
        "latest_package_identifier": "langgenius/nvidia_nim:0.0.2@928d27aea242719bdc427ca15247f66fa2f68d6b0806e56c9920e618f8de9cc7",
        "latest_version": "0.0.2",
        "model": {
          "background": "#EFFDFD",
          "configurate_methods": [
            "customizable-model"
          ],
          "description": {
            "en_US": "NVIDIA NIM, a set of easy-to-use inference microservices.",
            "zh_Hans": "NVIDIA NIM，一组易于使用的模型推理微服务。"
          },
          "help": {
            "title": {
              "en_US": "Learn more about NVIDIA NIM",
              "zh_Hans": "了解 NVIDIA NIM 更多信息"
            },
            "url": {
              "en_US": "https://www.nvidia.com/en-us/ai/"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.png"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "NVIDIA NIM"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API endpoint URL",
                  "zh_Hans": "API endpoint URL"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Base URL, e.g. http://192.168.1.100:8000/v1",
                  "zh_Hans": "Base URL, e.g. http://192.168.1.100:8000/v1"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "endpoint_url"
              },
              {
                "default": "chat",
                "label": {
                  "en_US": "Completion mode"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Completion",
                      "zh_Hans": "补全"
                    },
                    "show_on": [],
                    "value": "completion"
                  },
                  {
                    "label": {
                      "en_US": "Chat",
                      "zh_Hans": "对话"
                    },
                    "show_on": [],
                    "value": "chat"
                  }
                ],
                "placeholder": {
                  "en_US": "Select completion mode",
                  "zh_Hans": "选择对话类型"
                },
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "select",
                "variable": "mode"
              },
              {
                "default": "4096",
                "label": {
                  "en_US": "Model context size",
                  "zh_Hans": "模型上下文长度"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Model context size",
                  "zh_Hans": "在此输入您的模型上下文长度"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "context_size"
              },
              {
                "default": "4096",
                "label": {
                  "en_US": "Upper bound for max tokens",
                  "zh_Hans": "最大 token 上限"
                },
                "max_length": 0,
                "options": [],
                "placeholder": null,
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "text-input",
                "variable": "max_tokens_to_sample"
              }
            ],
            "model": {
              "label": {
                "en_US": "Model Name",
                "zh_Hans": "模型名称"
              },
              "placeholder": {
                "en_US": "Enter full model name",
                "zh_Hans": "输入模型全称"
              }
            }
          },
          "models": [],
          "position": {
            "llm": null
          },
          "provider": "nvidia_nim",
          "provider_credential_schema": null,
          "supported_model_types": [
            "llm"
          ]
        },
        "name": "nvidia_nim",
        "org": "langgenius",
        "plugin_id": "langgenius/nvidia_nim",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/nvidia_nim.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-02-17T06:59:25Z",
        "version_updated_at": "2025-02-17T06:59:25Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Feishu Wiki, requires the following permissions: wiki:wiki:readonly.\n",
          "zh_Hans": "飞书知识库，需要开通以下权限: wiki:wiki:readonly。\n"
        },
        "category": "tool",
        "created_at": "2025-02-26T10:43:48Z",
        "endpoint": {},
        "icon": "langgenius/packages/feishu_wiki/_assets/icon.png",
        "index_id": "langgenius___feishu_wiki",
        "install_count": 952,
        "introduction": "",
        "label": {
          "en_US": "Feishu Wiki",
          "zh_Hans": "飞书知识库"
        },
        "latest_package_identifier": "langgenius/feishu_wiki:0.0.1@6f2dcbaf4ed67a2e60a4fbf00d0d8a3d6d661ce37edb5d5f257d81d8a772c0d2",
        "latest_version": "0.0.1",
        "model": {},
        "name": "feishu_wiki",
        "org": "langgenius",
        "plugin_id": "langgenius/feishu_wiki",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/feishu_wiki.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "social"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "APP ID"
              },
              "name": "app_id",
              "options": null,
              "placeholder": {
                "en_US": "Please input your feishu app id",
                "zh_Hans": "请输入你的飞书 app id"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": "https://open.larkoffice.com/app"
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "APP Secret"
              },
              "name": "app_secret",
              "options": null,
              "placeholder": {
                "en_US": "Please input your app secret",
                "zh_Hans": "请输入你的飞书 app secret"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            }
          ],
          "identity": {
            "author": "Doug Lea",
            "description": {
              "en_US": "Feishu Wiki, requires the following permissions: wiki:wiki:readonly.\n",
              "zh_Hans": "飞书知识库，需要开通以下权限: wiki:wiki:readonly。\n"
            },
            "icon": "icon.png",
            "label": {
              "en_US": "Feishu Wiki",
              "zh_Hans": "飞书知识库"
            },
            "name": "feishu_wiki",
            "tags": [
              "social",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Get the list of child nodes in Wiki, make sure the app/bot is a member of the wiki space. See How to add an app as a wiki base administrator (member). https://open.feishu.cn/document/server-docs/docs/wiki-v2/wiki-qa\n",
                  "zh_Hans": "获取知识库全部子节点列表，请确保应用/机器人为知识空间成员。参阅如何将应用添加为知识库管理员（成员）。https://open.feishu.cn/document/server-docs/docs/wiki-v2/wiki-qa\n"
                },
                "llm": "A tool for getting all sub-nodes of a knowledge base.(获取知识空间子节点列表)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Get Wiki Nodes",
                  "zh_Hans": "获取知识空间子节点列表"
                },
                "name": "get_wiki_nodes"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the knowledge space. Supports space link URL, for example: https://svi136aogf123.feishu.cn/wiki/settings/7166950623940706332\n",
                    "zh_Hans": "知识空间 ID，支持空间链接 URL，例如：https://svi136aogf123.feishu.cn/wiki/settings/7166950623940706332"
                  },
                  "label": {
                    "en_US": "Space Id",
                    "zh_Hans": "知识空间 ID"
                  },
                  "llm_description": "知识空间 ID，支持空间链接 URL，例如：https://svi136aogf123.feishu.cn/wiki/settings/7166950623940706332",
                  "max": null,
                  "min": null,
                  "name": "space_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 10,
                  "form": "form",
                  "human_description": {
                    "en_US": "The size of each page, with a maximum value of 50.",
                    "zh_Hans": "分页大小，最大值 50。"
                  },
                  "label": {
                    "en_US": "Page Size",
                    "zh_Hans": "分页大小"
                  },
                  "llm_description": "分页大小，最大值 50。",
                  "max": null,
                  "min": null,
                  "name": "page_size",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The pagination token. Leave empty for the first request to start from the beginning; if the paginated query result has more items, a new page_token will be returned, which can be used to get the next set of results.",
                    "zh_Hans": "分页标记，第一次请求不填，表示从头开始遍历；分页查询结果还有更多项时会同时返回新的 page_token，下次遍历可采用该 page_token 获取查询结果。"
                  },
                  "label": {
                    "en_US": "Page Token",
                    "zh_Hans": "分页标记"
                  },
                  "llm_description": "分页标记，第一次请求不填，表示从头开始遍历；分页查询结果还有更多项时会同时返回新的 page_token，下次遍历可采用该 page_token 获取查询结果。",
                  "max": null,
                  "min": null,
                  "name": "page_token",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The token of the parent node.",
                    "zh_Hans": "父节点 token"
                  },
                  "label": {
                    "en_US": "Parent Node Token",
                    "zh_Hans": "父节点 token"
                  },
                  "llm_description": "父节点 token",
                  "max": null,
                  "min": null,
                  "name": "parent_node_token",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-26T10:43:52Z",
        "version_updated_at": "2025-02-26T10:43:52Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents",
          "ja_JP": "PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents",
          "pt_BR": "PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents",
          "zh_Hans": "PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents"
        },
        "category": "tool",
        "created_at": "2025-03-19T07:47:58Z",
        "endpoint": {},
        "icon": "yevanchen/packages/pymupdf/_assets/pymupdf.png",
        "index_id": "yevanchen___pymupdf",
        "install_count": 933,
        "introduction": "# PyMuPDF Plugin for Dify\n\nA powerful PDF text extraction plugin for Dify powered by PyMuPDF (aka fitz).\n\n![Demo Screenshot](./_assets/image.png)\n\n## Overview\n\nPyMuPDF Plugin is a high-performance tool that allows you to extract, analyze, and manipulate text content from PDF documents directly within Dify applications. Built on the robust PyMuPDF library, this plugin provides accurate and efficient PDF text extraction capabilities.\n\n## Features\n\n- Extract complete text content from PDF files\n- Process single or multiple PDF documents simultaneously\n- Maintain page structure with clear page separations\n- Return both human-readable text and structured JSON data\n- Detailed metadata including page numbers and file information\n\n## Installation\n\nTo install the PyMuPDF Plugin:\n\n1. Navigate to the Plugin section in your Dify application\n2. Click \"Add Plugin\"\n3. Search for \"PyMuPDF\" or upload this plugin package\n4. Follow the on-screen instructions to complete installation\n\n## Requirements\n\n- PyMuPDF library (installed automatically with the plugin)\n- Compatible with Dify plugin system\n\n## Usage\n\nOnce installed, the plugin can be accessed through the Dify interface:\n\n1. Upload one or more PDF files using the file selector\n2. The plugin will process each file and return:\n   - Text content extracted from all pages\n   - Structured JSON data with page-by-page content and metadata\n   - Raw text content as a downloadable blob\n\n## Example Response\n\nThe plugin returns data in multiple formats:\n\n1. **Text Message**: Human-readable text with page breaks indicated\n2. **JSON Message**: Structured data containing:\n   ```json\n   {\n     \"example.pdf\": [\n       {\n         \"text\": \"Content from page 1...\",\n         \"metadata\": {\n           \"page\": 1,\n           \"file_name\": \"example.pdf\"\n         }\n       },\n       {\n         \"text\": \"Content from page 2...\",\n         \"metadata\": {\n           \"page\": 2,\n           \"file_name\": \"example.pdf\"\n         }\n       }\n     ]\n   }\n   ```\n3. **Blob Message**: Raw text content with MIME type specification\n\n## Privacy Policy\n\nThis plugin does not collect, store, or transmit any user data beyond what is necessary for processing the provided PDF files. All processing is done within the plugin execution environment, and no data is retained after processing completes.\n\n- No user information is collected\n- No PDF content is stored after processing\n- No data is sent to external services\n- All processing happens within the Dify environment\n\n## License\n\nThis plugin is licensed under the [AGPL-3.0 License](https://www.gnu.org/licenses/agpl-3.0.en.html).\n\n## Contact\n\nFor questions, support, or feedback, please contact:\n\n\n\n## Credits\n\n- Code generated with assistance from Cursor\n- Powered by PyMuPDF library\n\n## Disclaimer\n\nThis plugin is provided \"as is\" without warranty of any kind, express or implied. Users should ensure they have appropriate rights to process any PDF documents uploaded for extraction.\n\n\n\n",
        "label": {
          "en_US": "pymupdf",
          "ja_JP": "pymupdf",
          "pt_BR": "pymupdf",
          "zh_Hans": "pymupdf"
        },
        "latest_package_identifier": "yevanchen/pymupdf:0.0.2@97e7aa565e54a1e73f169c01c96436268f79019c26b78b4d61f155b70025e3f8",
        "latest_version": "0.0.2",
        "model": {},
        "name": "pymupdf",
        "org": "yevanchen",
        "plugin_id": "yevanchen/pymupdf",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/pymupdf.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {}
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "yevanchen",
            "description": {
              "en_US": "PyMuPDF is a high performance Python library for data extraction, analysis, conversion &amp; manipulation of PDF (and other) documents",
              "pt_BR": "PyMuPDF is a high performance Python library for data extraction, analysis, conversion &amp; manipulation of PDF (and other) documents",
              "zh_Hans": "PyMuPDF is a high performance Python library for data extraction, analysis, conversion &amp; manipulation of PDF (and other) documents"
            },
            "icon": "pymupdf.png",
            "label": {
              "en_US": "pymupdf",
              "pt_BR": "pymupdf",
              "zh_Hans": "pymupdf"
            },
            "name": "pymupdf",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "PyMuPDF is a high performance Python library for data extraction, analysis, conversion &amp; manipulation of PDF (and other) documents",
                  "pt_BR": "PyMuPDF is a high performance Python library for data extraction, analysis, conversion &amp; manipulation of PDF (and other) documents",
                  "zh_Hans": "PyMuPDF is a high performance Python library for data extraction, analysis, conversion &amp; manipulation of PDF (and other) documents"
                },
                "llm": "PyMuPDF is a high performance Python library for data extraction, analysis, conversion &amp; manipulation of PDF (and other) documents"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "yevanchen",
                "label": {
                  "en_US": "pymupdf",
                  "pt_BR": "pymupdf",
                  "zh_Hans": "pymupdf"
                },
                "name": "pymupdf"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Upload PDF files for processing",
                    "pt_BR": "Carregar arquivos PDF para processamento",
                    "zh_Hans": "上传PDF文件进行处理"
                  },
                  "label": {
                    "en_US": "Files",
                    "pt_BR": "Arquivos",
                    "zh_Hans": "文件"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "files",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "files"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-21T14:12:40Z",
        "version_updated_at": "2025-03-21T14:12:40Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "The art of crafting effective prompts for large language models",
          "ja_JP": "大規模言語モデルのための効果的なプロンプト作成の技術",
          "pt_BR": "A arte de criar prompts eficazes para modelos de linguagem grandes",
          "zh_Hans": "大模型提示词创作的艺术与技巧"
        },
        "category": "tool",
        "created_at": "2025-04-10T15:39:47Z",
        "endpoint": {},
        "icon": "jaguarliuu/packages/rookie_prompt_art/_assets/art.svg",
        "index_id": "jaguarliuu___rookie_prompt_art",
        "install_count": 926,
        "introduction": "## rookie_prompt_art\n\n**Author:** jaguarliuu\n**Version:** 0.0.1\n**Type:** tool\n\n### Description\n#### Prompt Art · Smart SVG Card Generator\n\n**Prompt Art** is an intelligent SVG card generator plugin powered by LLMs.  \nIt turns your natural language prompts into beautifully styled SVG image cards.\n\n---\n\n#### ✨ Features\n\n- 🧠 Natural language prompt support\n- 🎨 Multi-style SVG themes, designed for visual sharing\n- 📚 Creative, philosophical, or humorous outputs\n- 🧩 Easy integration with [Dify](https://dify.ai) platform\n\n---\n\n#### 🎨 Currently Supported Card Types\n\n| Type             | Description                                                             |\n|------------------|-------------------------------------------------------------------------|\n| I Ching Divination | Input any question, get a randomly selected hexagram with interpretation |\n| One-Sentence Novel | Generate a mini story in one sentence with a visually appealing layout  |\n| Programmer's Daily Quote | Generate a witty or reflective quote in a daily calendar card style     |\n\n---\n\n#### 🚀 How to Use\n\n1. Add this plugin to your Dify app.\n2. Send a message like:\n   - “Should I change jobs this year?” → triggers divination card\n   - “Theme: Horror” → generates one-sentence novel\n   - “Give me today's programmer's card” → generates a dev diary SVG\n3. You will receive a full SVG image as a response.\n\n---\n\n#### 📦 Output Format\n\n- `svg`: A complete string of valid SVG code.\n\n---\n\n#### 📄 License\n\nMIT License",
        "label": {
          "en_US": "Prompt Art",
          "ja_JP": "プロンプトアート",
          "pt_BR": "Arte de Prompt",
          "zh_Hans": "大模型提示词之美"
        },
        "latest_package_identifier": "jaguarliuu/rookie_prompt_art:0.0.1@041ac325afd77c8620eca24036721f3ebae586aea6f28909e721027f529bfd15",
        "latest_version": "0.0.1",
        "model": {},
        "name": "rookie_prompt_art",
        "org": "jaguarliuu",
        "plugin_id": "jaguarliuu/rookie_prompt_art",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/rookie_prompt_art.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "jaguarliuu",
            "description": {
              "en_US": "大模型提示词之美-prompt art",
              "pt_BR": "大模型提示词之美-prompt art",
              "zh_Hans": "大模型提示词之美-prompt art"
            },
            "icon": "art.svg",
            "label": {
              "en_US": "rookie_prompt_art",
              "pt_BR": "rookie_prompt_art",
              "zh_Hans": "rookie_prompt_art"
            },
            "name": "rookie_prompt_art",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "大模型提示词之美-prompt art",
                  "pt_BR": "大模型提示词之美-prompt art",
                  "zh_Hans": "大模型提示词之美-prompt art"
                },
                "llm": "大模型提示词之美-prompt art"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "jaguarliuu",
                "label": {
                  "en_US": "rookie_prompt_art",
                  "pt_BR": "rookie_prompt_art",
                  "zh_Hans": "rookie_prompt_art"
                },
                "name": "rookie_prompt_art"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "大模型提示词之美-prompt art",
                    "pt_BR": "大模型提示词之美-prompt art",
                    "zh_Hans": "大模型提示词之美-prompt art"
                  },
                  "label": {
                    "en_US": "Query string",
                    "pt_BR": "Query string",
                    "zh_Hans": "查询语句"
                  },
                  "llm_description": "大模型提示词之美-prompt art",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "LLM model for prompt art.",
                    "pt_BR": "LLM model for prompt art.",
                    "zh_Hans": "LLM model for prompt art."
                  },
                  "label": {
                    "en_US": "Model",
                    "pt_BR": "Model",
                    "zh_Hans": "模型"
                  },
                  "llm_description": "LLM model for prompt art.",
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": "llm",
                  "template": null,
                  "type": "model-selector"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "大模型提示词之美-prompt art",
                    "pt_BR": "大模型提示词之美-prompt art",
                    "zh_Hans": "大模型提示词之美-prompt art"
                  },
                  "label": {
                    "en_US": "Author",
                    "pt_BR": "Author",
                    "zh_Hans": "作者"
                  },
                  "llm_description": "大模型提示词之美-prompt art",
                  "max": null,
                  "min": null,
                  "name": "author",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "大模型提示词之美-prompt art",
                    "pt_BR": "大模型提示词之美-prompt art",
                    "zh_Hans": "大模型提示词之美-prompt art"
                  },
                  "label": {
                    "en_US": "Category",
                    "pt_BR": "Category",
                    "zh_Hans": "类别"
                  },
                  "llm_description": "大模型提示词之美-prompt art",
                  "max": null,
                  "min": null,
                  "name": "category",
                  "options": [
                    {
                      "label": {
                        "en_US": "one sentence novel",
                        "zh_Hans": "一句话小说"
                      },
                      "value": "one_sentence_novel"
                    },
                    {
                      "label": {
                        "en_US": "programmer daily",
                        "zh_Hans": "程序员日报"
                      },
                      "value": "programmer_daily"
                    },
                    {
                      "label": {
                        "en_US": "divination",
                        "zh_Hans": "占卜"
                      },
                      "value": "divination"
                    },
                    {
                      "label": {
                        "en_US": "history war",
                        "zh_Hans": "历史上的那些战争"
                      },
                      "value": "history_war"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-10T15:39:53Z",
        "version_updated_at": "2025-04-10T15:39:53Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Feishu message, requires the following permissions: im:message、im:message.group_msg.\n",
          "zh_Hans": "飞书消息，需要开通以下权限: im:message、im:message.group_msg。\n"
        },
        "category": "tool",
        "created_at": "2025-02-26T10:07:41Z",
        "endpoint": {},
        "icon": "langgenius/packages/feishu_message/_assets/icon.svg",
        "index_id": "langgenius___feishu_message",
        "install_count": 884,
        "introduction": "",
        "label": {
          "en_US": "Feishu Message",
          "zh_Hans": "飞书消息"
        },
        "latest_package_identifier": "langgenius/feishu_message:0.0.1@013b295e4bd0f6f5850cf529e3ec3078a31d07e061a5640a9c87e313ea11bf62",
        "latest_version": "0.0.1",
        "model": {},
        "name": "feishu_message",
        "org": "langgenius",
        "plugin_id": "langgenius/feishu_message",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/feishu_message.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "social"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "APP ID"
              },
              "name": "app_id",
              "options": null,
              "placeholder": {
                "en_US": "Please input your feishu app id",
                "zh_Hans": "请输入你的飞书 app id"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": "https://open.larkoffice.com/app"
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "APP Secret"
              },
              "name": "app_secret",
              "options": null,
              "placeholder": {
                "en_US": "Please input your app secret",
                "zh_Hans": "请输入你的飞书 app secret"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            }
          ],
          "identity": {
            "author": "Doug Lea",
            "description": {
              "en_US": "Lark message, requires the following permissions: im:message、im:message.group_msg.\n",
              "zh_Hans": "飞书消息，需要开通以下权限: im:message、im:message.group_msg。\n"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Lark Message",
              "zh_Hans": "飞书消息"
            },
            "name": "feishu_message",
            "tags": [
              "social",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Send bot message",
                  "zh_Hans": "发送飞书应用消息"
                },
                "llm": "A tool for sending Feishu application messages."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Send Bot Message",
                  "zh_Hans": "发送飞书应用消息"
                },
                "name": "send_bot_message"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the message receiver, the ID type is consistent with the value of the query parameter receive_id_type.",
                    "zh_Hans": "消息接收者的 ID，ID 类型与查询参数 receive_id_type 的取值一致。"
                  },
                  "label": {
                    "en_US": "receive_id",
                    "zh_Hans": "消息接收者的 ID"
                  },
                  "llm_description": "消息接收者的 ID，ID 类型与查询参数 receive_id_type 的取值一致。",
                  "max": null,
                  "min": null,
                  "name": "receive_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The ID type of the message receiver, optional values are open_id, union_id, user_id, email, chat_id, with a default value of open_id.",
                    "zh_Hans": "消息接收者的 ID 类型，可选值有 open_id、union_id、user_id、email、chat_id，默认值为 open_id。"
                  },
                  "label": {
                    "en_US": "receive_id_type",
                    "zh_Hans": "消息接收者的 ID 类型"
                  },
                  "llm_description": "消息接收者的 ID 类型，可选值有 open_id、union_id、user_id、email、chat_id，默认值为 open_id。",
                  "max": null,
                  "min": null,
                  "name": "receive_id_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "open_id",
                        "zh_Hans": "open_id"
                      },
                      "value": "open_id"
                    },
                    {
                      "label": {
                        "en_US": "union_id",
                        "zh_Hans": "union_id"
                      },
                      "value": "union_id"
                    },
                    {
                      "label": {
                        "en_US": "user_id",
                        "zh_Hans": "user_id"
                      },
                      "value": "user_id"
                    },
                    {
                      "label": {
                        "en_US": "email",
                        "zh_Hans": "email"
                      },
                      "value": "email"
                    },
                    {
                      "label": {
                        "en_US": "chat_id",
                        "zh_Hans": "chat_id"
                      },
                      "value": "chat_id"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Message type. Optional values are text, post, image, file, audio, media, sticker, interactive, share_chat, share_user, system. For detailed introduction of different message types, refer to the message content(https://open.larkoffice.com/document/server-docs/im-v1/message-content-description/create_json).",
                    "zh_Hans": "消息类型。可选值有：text、post、image、file、audio、media、sticker、interactive、share_chat、share_user、system。不同消息类型的详细介绍，参见发送消息内容(https://open.larkoffice.com/document/server-docs/im-v1/message-content-description/create_json)。"
                  },
                  "label": {
                    "en_US": "msg_type",
                    "zh_Hans": "消息类型"
                  },
                  "llm_description": "消息类型。可选值有：text、post、image、file、audio、media、sticker、interactive、share_chat、share_user、system。不同消息类型的详细介绍，参见发送消息内容(https://open.larkoffice.com/document/server-docs/im-v1/message-content-description/create_json)。",
                  "max": null,
                  "min": null,
                  "name": "msg_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "text",
                        "zh_Hans": "文本"
                      },
                      "value": "text"
                    },
                    {
                      "label": {
                        "en_US": "interactive",
                        "zh_Hans": "卡片"
                      },
                      "value": "interactive"
                    },
                    {
                      "label": {
                        "en_US": "post",
                        "zh_Hans": "富文本"
                      },
                      "value": "post"
                    },
                    {
                      "label": {
                        "en_US": "image",
                        "zh_Hans": "图片"
                      },
                      "value": "image"
                    },
                    {
                      "label": {
                        "en_US": "file",
                        "zh_Hans": "文件"
                      },
                      "value": "file"
                    },
                    {
                      "label": {
                        "en_US": "audio",
                        "zh_Hans": "语音"
                      },
                      "value": "audio"
                    },
                    {
                      "label": {
                        "en_US": "media",
                        "zh_Hans": "视频"
                      },
                      "value": "media"
                    },
                    {
                      "label": {
                        "en_US": "sticker",
                        "zh_Hans": "表情包"
                      },
                      "value": "sticker"
                    },
                    {
                      "label": {
                        "en_US": "share_chat",
                        "zh_Hans": "分享群名片"
                      },
                      "value": "share_chat"
                    },
                    {
                      "label": {
                        "en_US": "share_user",
                        "zh_Hans": "分享个人名片"
                      },
                      "value": "share_user"
                    },
                    {
                      "label": {
                        "en_US": "system",
                        "zh_Hans": "系统消息"
                      },
                      "value": "system"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Message content, a JSON structure serialized string. The value of this parameter corresponds to msg_type. For example, if msg_type is text, this parameter needs to pass in text type content. To understand the format and usage limitations of different message types, refer to the message content(https://open.larkoffice.com/document/server-docs/im-v1/message-content-description/create_json).",
                    "zh_Hans": "消息内容，JSON 结构序列化后的字符串。该参数的取值与 msg_type 对应，例如 msg_type 取值为 text，则该参数需要传入文本类型的内容。了解不同类型的消息内容格式、使用限制，可参见发送消息内容(https://open.larkoffice.com/document/server-docs/im-v1/message-content-description/create_json)。"
                  },
                  "label": {
                    "en_US": "content",
                    "zh_Hans": "消息内容"
                  },
                  "llm_description": "消息内容，JSON 结构序列化后的字符串。该参数的取值与 msg_type 对应，例如 msg_type 取值为 text，则该参数需要传入文本类型的内容。了解不同类型的消息内容格式、使用限制，可参见发送消息内容(https://open.larkoffice.com/document/server-docs/im-v1/message-content-description/create_json)。",
                  "max": null,
                  "min": null,
                  "name": "content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get Chat Messages",
                  "zh_Hans": "获取指定单聊、群聊的消息历史"
                },
                "llm": "A tool for getting chat messages from specific one-on-one chats or group chats.(获取指定单聊、群聊的消息历史)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Get Chat Messages",
                  "zh_Hans": "获取指定单聊、群聊的消息历史"
                },
                "name": "get_chat_messages"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the group chat or single chat. Refer to the group ID description for how to obtain it. https://open.feishu.cn/document/server-docs/group/chat/chat-id-description",
                    "zh_Hans": "群聊或单聊的 ID，获取方式参见群 ID 说明。https://open.feishu.cn/document/server-docs/group/chat/chat-id-description"
                  },
                  "label": {
                    "en_US": "Container Id",
                    "zh_Hans": "群聊或单聊的 ID"
                  },
                  "llm_description": "群聊或单聊的 ID，获取方式参见群 ID 说明。https://open.feishu.cn/document/server-docs/group/chat/chat-id-description",
                  "max": null,
                  "min": null,
                  "name": "container_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The start time for querying historical messages, formatted as \"2006-01-02 15:04:05\".",
                    "zh_Hans": "待查询历史信息的起始时间，格式为 \"2006-01-02 15:04:05\"。"
                  },
                  "label": {
                    "en_US": "Start Time",
                    "zh_Hans": "起始时间"
                  },
                  "llm_description": "待查询历史信息的起始时间，格式为 \"2006-01-02 15:04:05\"。",
                  "max": null,
                  "min": null,
                  "name": "start_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The end time for querying historical messages, formatted as \"2006-01-02 15:04:05\".",
                    "zh_Hans": "待查询历史信息的结束时间，格式为 \"2006-01-02 15:04:05\"。"
                  },
                  "label": {
                    "en_US": "End Time",
                    "zh_Hans": "结束时间"
                  },
                  "llm_description": "待查询历史信息的结束时间，格式为 \"2006-01-02 15:04:05\"。",
                  "max": null,
                  "min": null,
                  "name": "end_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "ByCreateTimeAsc",
                  "form": "form",
                  "human_description": {
                    "en_US": "The message sorting method. Optional values are ByCreateTimeAsc: sorted in ascending order by message creation time; ByCreateTimeDesc: sorted in descending order by message creation time. The default value is ByCreateTimeAsc. Note: When using page_token for pagination requests, the sorting method (sort_type) is consistent with the first request and cannot be changed midway.\n",
                    "zh_Hans": "消息排序方式，可选值有 ByCreateTimeAsc：按消息创建时间升序排列；ByCreateTimeDesc：按消息创建时间降序排列。默认值为：ByCreateTimeAsc。注意：使用 page_token 分页请求时，排序方式（sort_type）均与第一次请求一致，不支持中途改换排序方式。\n"
                  },
                  "label": {
                    "en_US": "Sort Type",
                    "zh_Hans": "排序方式"
                  },
                  "llm_description": "消息排序方式，可选值有 ByCreateTimeAsc：按消息创建时间升序排列；ByCreateTimeDesc：按消息创建时间降序排列。默认值为：ByCreateTimeAsc。注意：使用 page_token 分页请求时，排序方式（sort_type）均与第一次请求一致，不支持中途改换排序方式。",
                  "max": null,
                  "min": null,
                  "name": "sort_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "ByCreateTimeAsc",
                        "zh_Hans": "ByCreateTimeAsc"
                      },
                      "value": "ByCreateTimeAsc"
                    },
                    {
                      "label": {
                        "en_US": "ByCreateTimeDesc",
                        "zh_Hans": "ByCreateTimeDesc"
                      },
                      "value": "ByCreateTimeDesc"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 20,
                  "form": "form",
                  "human_description": {
                    "en_US": "The page size, i.e., the number of data entries returned in a single request. The default value is 20, and the value range is [1,50].",
                    "zh_Hans": "分页大小，即单次请求所返回的数据条目数。默认值为 20，取值范围为 [1,50]。"
                  },
                  "label": {
                    "en_US": "Page Size",
                    "zh_Hans": "分页大小"
                  },
                  "llm_description": "分页大小，即单次请求所返回的数据条目数。默认值为 20，取值范围为 [1,50]。",
                  "max": null,
                  "min": null,
                  "name": "page_size",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The pagination token. Leave it blank for the first request, indicating to start traversing from the beginning; when the pagination query result has more items, a new page_token will be returned simultaneously, which can be used to obtain the query result in the next traversal.",
                    "zh_Hans": "分页标记，第一次请求不填，表示从头开始遍历；分页查询结果还有更多项时会同时返回新的 page_token，下次遍历可采用该 page_token 获取查询结果。"
                  },
                  "label": {
                    "en_US": "Page Token",
                    "zh_Hans": "分页标记"
                  },
                  "llm_description": "分页标记，第一次请求不填，表示从头开始遍历；分页查询结果还有更多项时会同时返回新的 page_token，下次遍历可采用该 page_token 获取查询结果。",
                  "max": null,
                  "min": null,
                  "name": "page_token",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Send webhook message",
                  "zh_Hans": "使用自定义机器人发送飞书消息"
                },
                "llm": "A tool for sending Lark messages using a custom robot."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Send Webhook Message",
                  "zh_Hans": "使用自定义机器人发送飞书消息"
                },
                "name": "send_webhook_message"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The address of the webhook, the format of the webhook address corresponding to the bot is as follows: https://open.feishu.cn/open-apis/bot/v2/hook/xxxxxxxxxxxxxxxxx. For details, please refer to: Feishu Custom Bot Usage Guide(https://open.larkoffice.com/document/client-docs/bot-v3/add-custom-bot)\n",
                    "zh_Hans": "webhook 的地址，机器人对应的 webhook 地址格式如下: https://open.feishu.cn/open-apis/bot/v2/hook/xxxxxxxxxxxxxxxxx，详情可参考: 飞书自定义机器人使用指南(https://open.larkoffice.com/document/client-docs/bot-v3/add-custom-bot)\n"
                  },
                  "label": {
                    "en_US": "webhook",
                    "zh_Hans": "webhook"
                  },
                  "llm_description": "webhook 的地址，机器人对应的 webhook 地址格式如下: https://open.feishu.cn/open-apis/bot/v2/hook/xxxxxxxxxxxxxxxxx，详情可参考: 飞书自定义机器人使用指南(https://open.larkoffice.com/document/client-docs/bot-v3/add-custom-bot)\n",
                  "max": null,
                  "min": null,
                  "name": "webhook",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Message type. Optional values are text, image, interactive, share_chat. For detailed introduction of different message types, refer to the message content(https://open.larkoffice.com/document/server-docs/im-v1/message-content-description/create_json).",
                    "zh_Hans": "消息类型。可选值有：text、image、interactive、share_chat。不同消息类型的详细介绍，参见发送消息内容(https://open.larkoffice.com/document/server-docs/im-v1/message-content-description/create_json)。"
                  },
                  "label": {
                    "en_US": "msg_type",
                    "zh_Hans": "消息类型"
                  },
                  "llm_description": "消息类型。可选值有：text、image、interactive、share_chat。不同消息类型的详细介绍，参见发送消息内容(https://open.larkoffice.com/document/server-docs/im-v1/message-content-description/create_json)。",
                  "max": null,
                  "min": null,
                  "name": "msg_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "text",
                        "zh_Hans": "文本"
                      },
                      "value": "text"
                    },
                    {
                      "label": {
                        "en_US": "interactive",
                        "zh_Hans": "卡片"
                      },
                      "value": "interactive"
                    },
                    {
                      "label": {
                        "en_US": "image",
                        "zh_Hans": "图片"
                      },
                      "value": "image"
                    },
                    {
                      "label": {
                        "en_US": "share_chat",
                        "zh_Hans": "分享群名片"
                      },
                      "value": "share_chat"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Message content, a JSON structure serialized string. The value of this parameter corresponds to msg_type. For example, if msg_type is text, this parameter needs to pass in text type content. To understand the format and usage limitations of different message types, refer to the message content(https://open.larkoffice.com/document/server-docs/im-v1/message-content-description/create_json).",
                    "zh_Hans": "消息内容，JSON 结构序列化后的字符串。该参数的取值与 msg_type 对应，例如 msg_type 取值为 text，则该参数需要传入文本类型的内容。了解不同类型的消息内容格式、使用限制，可参见发送消息内容(https://open.larkoffice.com/document/server-docs/im-v1/message-content-description/create_json)。"
                  },
                  "label": {
                    "en_US": "content",
                    "zh_Hans": "消息内容"
                  },
                  "llm_description": "消息内容，JSON 结构序列化后的字符串。该参数的取值与 msg_type 对应，例如 msg_type 取值为 text，则该参数需要传入文本类型的内容。了解不同类型的消息内容格式、使用限制，可参见发送消息内容(https://open.larkoffice.com/document/server-docs/im-v1/message-content-description/create_json)。",
                  "max": null,
                  "min": null,
                  "name": "content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get Thread Messages",
                  "zh_Hans": "获取指定话题的消息历史"
                },
                "llm": "A tool for getting chat messages from specific threads.(获取指定话题的消息历史)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Get Thread Messages",
                  "zh_Hans": "获取指定话题的消息历史"
                },
                "name": "get_thread_messages"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the thread. Refer to the thread overview on how to obtain the thread_id. https://open.feishu.cn/document/uAjLw4CM/ukTMukTMukTM/reference/im-v1/message/thread-introduction",
                    "zh_Hans": "话题 ID，获取方式参见话题概述的如何获取 thread_id 章节。https://open.feishu.cn/document/uAjLw4CM/ukTMukTMukTM/reference/im-v1/message/thread-introduction"
                  },
                  "label": {
                    "en_US": "Thread Id",
                    "zh_Hans": "话题 ID"
                  },
                  "llm_description": "话题 ID，获取方式参见话题概述的如何获取 thread_id 章节。https://open.feishu.cn/document/uAjLw4CM/ukTMukTMukTM/reference/im-v1/message/thread-introduction",
                  "max": null,
                  "min": null,
                  "name": "container_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "ByCreateTimeAsc",
                  "form": "form",
                  "human_description": {
                    "en_US": "The message sorting method. Optional values are ByCreateTimeAsc: sorted in ascending order by message creation time; ByCreateTimeDesc: sorted in descending order by message creation time. The default value is ByCreateTimeAsc. Note: When using page_token for pagination requests, the sorting method (sort_type) is consistent with the first request and cannot be changed midway.\n",
                    "zh_Hans": "消息排序方式，可选值有 ByCreateTimeAsc：按消息创建时间升序排列；ByCreateTimeDesc：按消息创建时间降序排列。默认值为：ByCreateTimeAsc。注意：使用 page_token 分页请求时，排序方式（sort_type）均与第一次请求一致，不支持中途改换排序方式。\n"
                  },
                  "label": {
                    "en_US": "Sort Type",
                    "zh_Hans": "排序方式"
                  },
                  "llm_description": "消息排序方式，可选值有 ByCreateTimeAsc：按消息创建时间升序排列；ByCreateTimeDesc：按消息创建时间降序排列。默认值为：ByCreateTimeAsc。注意：使用 page_token 分页请求时，排序方式（sort_type）均与第一次请求一致，不支持中途改换排序方式。",
                  "max": null,
                  "min": null,
                  "name": "sort_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "ByCreateTimeAsc",
                        "zh_Hans": "ByCreateTimeAsc"
                      },
                      "value": "ByCreateTimeAsc"
                    },
                    {
                      "label": {
                        "en_US": "ByCreateTimeDesc",
                        "zh_Hans": "ByCreateTimeDesc"
                      },
                      "value": "ByCreateTimeDesc"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 20,
                  "form": "form",
                  "human_description": {
                    "en_US": "The page size, i.e., the number of data entries returned in a single request. The default value is 20, and the value range is [1,50].",
                    "zh_Hans": "分页大小，即单次请求所返回的数据条目数。默认值为 20，取值范围为 [1,50]。"
                  },
                  "label": {
                    "en_US": "Page Size",
                    "zh_Hans": "分页大小"
                  },
                  "llm_description": "分页大小，即单次请求所返回的数据条目数。默认值为 20，取值范围为 [1,50]。",
                  "max": null,
                  "min": null,
                  "name": "page_size",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The pagination token. Leave it blank for the first request, indicating to start traversing from the beginning; when the pagination query result has more items, a new page_token will be returned simultaneously, which can be used to obtain the query result in the next traversal.",
                    "zh_Hans": "分页标记，第一次请求不填，表示从头开始遍历；分页查询结果还有更多项时会同时返回新的 page_token，下次遍历可采用该 page_token 获取查询结果。"
                  },
                  "label": {
                    "en_US": "Page Token",
                    "zh_Hans": "分页标记"
                  },
                  "llm_description": "分页标记，第一次请求不填，表示从头开始遍历；分页查询结果还有更多项时会同时返回新的 page_token，下次遍历可采用该 page_token 获取查询结果。",
                  "max": null,
                  "min": null,
                  "name": "page_token",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-26T10:07:46Z",
        "version_updated_at": "2025-02-26T10:07:46Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "A search engine for biomedical literature.",
          "zh_Hans": "一款生物医学文献搜索引擎。"
        },
        "category": "tool",
        "created_at": "2024-12-04T04:38:19Z",
        "endpoint": {},
        "icon": "langgenius/packages/pubmed/_assets/icon.svg",
        "index_id": "langgenius___pubmed",
        "install_count": 874,
        "introduction": "# PubMed\n\n## Overview\n\nPubMed is a search engine providing access to biomedical literature and research. It indexes citations and abstracts from MEDLINE, life science journals, and online books. It offers features such as keyword searching, advanced filters, and citation tracking.\n\n## Configuration\n\n### 1. Get PubMed tools from Plugin Marketplace\n\nThe PubMed tools could be found at the Plugin Marketplace, please install it.\n\n![](./_assets/pubmed_1.png)\n\n### 2. You can use the PubMed tool in the following application types.\n\n![](./_assets/pubmed_2.png)\n\n#### Chatflow / Workflow applications\n\nBoth Chatflow and Workflow applications support the PubMed tool node.\n\n#### Agent applications\n\nAdd the PubMed tool in the Agent application, then enter the search query to call this tool.",
        "label": {
          "en_US": "PubMed",
          "zh_Hans": "PubMed"
        },
        "latest_package_identifier": "langgenius/pubmed:0.0.3@91d8f007a71c9fbb96bba926d6e1571e5dd2c66a5bdee767541984c478488595",
        "latest_version": "0.0.3",
        "model": {},
        "name": "pubmed",
        "org": "langgenius",
        "plugin_id": "langgenius/pubmed",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/pubmed.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "search"
          },
          {
            "name": "medical"
          }
        ],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "Pink Banana",
            "description": {
              "en_US": "A search engine for biomedical literature.",
              "zh_Hans": "一款生物医学文献搜索引擎。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "PubMed",
              "zh_Hans": "PubMed"
            },
            "name": "pubmed",
            "tags": [
              "medical",
              "search"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "PubMed® comprises more than 35 million citations for biomedical literature from MEDLINE, life science journals, and online books. Citations may include links to full text content from PubMed Central and publisher web sites.",
                  "zh_Hans": "PubMed® 包含来自 MEDLINE、生命科学期刊和在线书籍的超过 3500 万篇生物医学文献引用。引用可能包括来自 PubMed Central 和出版商网站的全文内容链接。"
                },
                "llm": "Perform searches on PubMed and get results."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Pink Banana",
                "label": {
                  "en_US": "PubMed Search",
                  "zh_Hans": "PubMed 搜索"
                },
                "name": "pubmed_search"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The search query.",
                    "zh_Hans": "搜索查询语句。"
                  },
                  "label": {
                    "en_US": "Query string",
                    "zh_Hans": "查询语句"
                  },
                  "llm_description": "Key words for searching",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:14:43Z",
        "version_updated_at": "2025-02-17T07:14:43Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Feishu group bot",
          "pt_BR": "Feishu group bot",
          "zh_Hans": "飞书群机器人"
        },
        "category": "tool",
        "created_at": "2025-02-26T10:40:53Z",
        "endpoint": {},
        "icon": "langgenius/packages/feishu/_assets/icon.svg",
        "index_id": "langgenius___feishu",
        "install_count": 849,
        "introduction": "",
        "label": {
          "en_US": "Feishu",
          "pt_BR": "Feishu",
          "zh_Hans": "飞书"
        },
        "latest_package_identifier": "langgenius/feishu:0.0.1@a885d31986acdaebfca7839e0270746da5574e7504835b387e79a934f53fcdee",
        "latest_version": "0.0.1",
        "model": {},
        "name": "feishu",
        "org": "langgenius",
        "plugin_id": "langgenius/feishu",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/feishu.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "social"
          }
        ],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "Arkii Sun",
            "description": {
              "en_US": "Feishu group bot",
              "pt_BR": "Feishu group bot",
              "zh_Hans": "飞书群机器人"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Feishu",
              "pt_BR": "Feishu",
              "zh_Hans": "飞书"
            },
            "name": "feishu",
            "tags": [
              "social",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Sending a group message on Feishu via the webhook of group bot",
                  "pt_BR": "Sending a group message on Feishu via the webhook of group bot",
                  "zh_Hans": "通过飞书的群机器人webhook发送群消息"
                },
                "llm": "A tool for sending messages to a chat group on Feishu(飞书) ."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Arkii Sun",
                "label": {
                  "en_US": "Send Group Message",
                  "pt_BR": "Send Group Message",
                  "zh_Hans": "发送群消息"
                },
                "name": "feishu_group_bot"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Feishu Group bot webhook key",
                    "pt_BR": "Feishu Group bot webhook key",
                    "zh_Hans": "群机器人webhook的key"
                  },
                  "label": {
                    "en_US": "Feishu Group bot webhook key",
                    "pt_BR": "Feishu Group bot webhook key",
                    "zh_Hans": "群机器人webhook的key"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "hook_key",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Content to sent to the group.",
                    "pt_BR": "Content to sent to the group.",
                    "zh_Hans": "群消息文本"
                  },
                  "label": {
                    "en_US": "content",
                    "pt_BR": "content",
                    "zh_Hans": "消息内容"
                  },
                  "llm_description": "Content of the message",
                  "max": null,
                  "min": null,
                  "name": "content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-26T10:40:57Z",
        "version_updated_at": "2025-02-26T10:40:57Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Serply.io is a robust real-time SERP API delivering structured data from a collection of search engines including Web Search, Jobs, News, and many more.",
          "pt_BR": "Serply.io is a robust real-time SERP API delivering structured data from a collection of search engines including Web Search, Jobs, News, and many more.",
          "zh_Hans": "Serply.io 是一个强大的实时 SERP API，可提供来自 搜索 招聘 新闻等搜索引擎集合的结构化数据。"
        },
        "category": "tool",
        "created_at": "2024-11-29T10:00:07Z",
        "endpoint": {},
        "icon": "langgenius/packages/websearch/_assets/icon.svg",
        "index_id": "langgenius___websearch",
        "install_count": 839,
        "introduction": "# Overview\n\nThe **Serply.io** plugin in Dify provides a comprehensive suite of tools for performing various types of web searches and retrieving structured data. These tools allow users to query for markdown content, job listings, news articles, academic research, and general web search results. By integrating Serply.io into your workflows, you can automate data retrieval tasks and enhance productivity.​\n\n# Tools Included:\n\n1. Get Markdown API: Retrieve markdown content from a specified URL.\n\n2. Job Search API: Search for job listings based on a query.\n\n3. News Search API: Fetch news articles based on a search term, with options to specify location, country, and language.​\n\n4. Scholar API: Search for academic research or scholarly articles using a query, with options to filter by location, country, and language.​\n\n5. Web Search API: Perform general web searches for any query.\n\n# Configure\n\n## 1. Install the Plugin\n\n1. Go to the **Dify Marketplace**.​\n\n2. Search for the **Serply.io Plugin**.\n\n3. Click \"Install\" to add the plugin to your workspace.\n\n![](./_assets/serply_install.png)\n\n## 2. Register and Obtain API Key\n\n1. Visit [Serply.io](https://serply.io/) to sign up for Serply.io and create an account if you don’t already have one.\n\n2. Log in to your Serply.io account and generate an API Key from the dashboard.\n\n## 3. Authorize the Plugin\n\n1. Add any of the Serply.io tools (e.g., \"News Search API\") to your workflow in Dify.\n\n2. Click on the \"To authorize\" button in the tool configuration panel.\n\n3. Enter your Serply.io API Key in the provided field.\n\n4. Save your credentials to complete the authorization process.\n\n## 4. Input Variables\n\nEach tool requires specific input variables:\n\n### Get Markdown API\n\nURL (String, Required): The URL of the webpage you want to retrieve markdown content from.​\n\nLocation (Optional): Defines where you want the request to originate (e.g., \"US\"or \"New York\").​\n\n![](./_assets/serply_get_markdown.png)\n\n### Job Search API​\n\nQuery (String, Required): The keyword or phrase defining the type of jobs you want to search for.​\n\nLocation (Optional): Defines where you want the search to originate.\n\n\n![](./_assets/serply_job_search.png)\n\n### News Search API​\n\nQuery (String, Required): The keyword or phrase defining the type of news articles you want to search for.​\n\nLocation (Optional): Defines where you want the search to originate.\n\nCountry (Optional): Specify a country filter (e.g., \"United States\").\n\nLanguage (Optional): Specify a language filter (e.g., \"English\").\n\n\n![](./_assets/serply_news_search.png)\n\n### Scholar API​\n\nQuery (String, Required): The keyword or phrase defining the type of academic research or scholarly articles you want to search for.​\n\nLocation (Optional): Defines where you want the search to originate.\n\nCountry (Optional): Specify a country filter (e.g., \"United States\")\n\nLanguage (Optional): Specify a language filter (e.g., \"English\").\n\n\n![](./_assets/serply_scholar_api.png)\n\n### Web Search API\n\nQuery (String, Required): The keyword or phrase defining what you want to search for on the web.​\n\nLocation (Optional): Defines where you want the search to originate.\n\n![](./_assets/serply_websearch_api.png)\n\n\n\n## Example Workflow\n\n1. Add the \"News Search API\" tool to your workflow in Dify.\n\n2. Input:\n\n° Query: \"AI advancements\"\n\n。Country: \"United States\"\n\n。 Language: \"English\"\n\n3. Run the tool to retrieve a list of relevant news articles about Al advancements from U.S.-based sources in English.\n\n![](./_assets/serply_example.png)\n\n\n\n",
        "label": {
          "en_US": "Serply.io",
          "pt_BR": "Serply.io",
          "zh_Hans": "Serply.io"
        },
        "latest_package_identifier": "langgenius/websearch:0.0.2@0994d3d43473fdbffa82666bdabd4a0de8f673c4b6bb1e3cf61bb23a982de4b1",
        "latest_version": "0.0.2",
        "model": {},
        "name": "websearch",
        "org": "langgenius",
        "plugin_id": "langgenius/websearch",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/websearch.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "search"
          },
          {
            "name": "business"
          },
          {
            "name": "news"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "Serply.io API key",
                "pt_BR": "Serply.io API key",
                "zh_Hans": "Serply.io API key"
              },
              "name": "serply_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Serply.io API key",
                "pt_BR": "Please input your Serply.io API key",
                "zh_Hans": "请输入你的 Serply.io API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://Serply.io/"
            }
          ],
          "identity": {
            "author": "Serply.io",
            "description": {
              "en_US": "Serply.io is a robust real-time SERP API delivering structured data from a collection of search engines including Web Search, Jobs, News, and many more.",
              "pt_BR": "Serply.io is a robust real-time SERP API delivering structured data from a collection of search engines including Web Search, Jobs, News, and many more.",
              "zh_Hans": "Serply.io 是一个强大的实时 SERP API，可提供来自 搜索 招聘 新闻等搜索引擎集合的结构化数据。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Serply.io",
              "pt_BR": "Serply.io",
              "zh_Hans": "Serply.io"
            },
            "name": "websearch",
            "tags": [
              "search",
              "business",
              "news",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool to perform convert a webpage to markdown to make it easier for LLMs to understand.",
                  "zh_Hans": "一个将网页转换为 Markdown 的工具，以便模型更容易理解"
                },
                "llm": "A tool to perform convert a webpage to markdown to make it easier for LLMs to understand."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Get Markdown API",
                  "zh_Hans": "Get Markdown API"
                },
                "name": "get_markdown"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "URL that you want to grab the content from",
                    "zh_Hans": "您要从中获取内容的 URL"
                  },
                  "label": {
                    "en_US": "URL",
                    "zh_Hans": "URL"
                  },
                  "llm_description": "Defines the link want to grab content from.",
                  "max": null,
                  "min": null,
                  "name": "url",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "US",
                  "form": "form",
                  "human_description": {
                    "en_US": "Defines from where you want the search to originate. (For example - New York)",
                    "zh_Hans": "定义您想要搜索的起始位置。 （例如 - 纽约）"
                  },
                  "label": {
                    "en_US": "Location",
                    "zh_Hans": "询问"
                  },
                  "llm_description": "Defines from where you want the search to originate. (For example - New York)",
                  "max": null,
                  "min": null,
                  "name": "location",
                  "options": [
                    {
                      "label": {
                        "en_US": "Australia",
                        "pt_BR": "Australia",
                        "zh_Hans": "澳大利亚"
                      },
                      "value": "AU"
                    },
                    {
                      "label": {
                        "en_US": "Brazil",
                        "pt_BR": "Brazil",
                        "zh_Hans": "巴西"
                      },
                      "value": "BR"
                    },
                    {
                      "label": {
                        "en_US": "Canada",
                        "pt_BR": "Canada",
                        "zh_Hans": "加拿大"
                      },
                      "value": "CA"
                    },
                    {
                      "label": {
                        "en_US": "Germany",
                        "pt_BR": "Germany",
                        "zh_Hans": "德国"
                      },
                      "value": "DE"
                    },
                    {
                      "label": {
                        "en_US": "France",
                        "pt_BR": "France",
                        "zh_Hans": "法国"
                      },
                      "value": "FR"
                    },
                    {
                      "label": {
                        "en_US": "United Kingdom",
                        "pt_BR": "United Kingdom",
                        "zh_Hans": "英国"
                      },
                      "value": "GB"
                    },
                    {
                      "label": {
                        "en_US": "United States",
                        "pt_BR": "United States",
                        "zh_Hans": "美国"
                      },
                      "value": "US"
                    },
                    {
                      "label": {
                        "en_US": "Japan",
                        "pt_BR": "Japan",
                        "zh_Hans": "日本"
                      },
                      "value": "JP"
                    },
                    {
                      "label": {
                        "en_US": "India",
                        "pt_BR": "India",
                        "zh_Hans": "印度"
                      },
                      "value": "IN"
                    },
                    {
                      "label": {
                        "en_US": "Korea",
                        "pt_BR": "Korea",
                        "zh_Hans": "韩国"
                      },
                      "value": "KR"
                    },
                    {
                      "label": {
                        "en_US": "Singapore",
                        "pt_BR": "Singapore",
                        "zh_Hans": "新加坡"
                      },
                      "value": "SG"
                    },
                    {
                      "label": {
                        "en_US": "Sweden",
                        "pt_BR": "Sweden",
                        "zh_Hans": "瑞典"
                      },
                      "value": "SE"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool to retrieve answer boxes, knowledge graphs, snippets, and webpages from Google Search engine.",
                  "zh_Hans": "一种从 Google 搜索引擎检索答案框、知识图、片段和网页的工具。"
                },
                "llm": "A tool to retrieve answer boxes, knowledge graphs, snippets, and webpages from Google Search engine."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Web Search API",
                  "zh_Hans": "Web Search API"
                },
                "name": "web_search"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Defines the query you want to search.",
                    "zh_Hans": "定义您要搜索的查询。"
                  },
                  "label": {
                    "en_US": "Query",
                    "zh_Hans": "询问"
                  },
                  "llm_description": "Defines the search query you want to search.",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "US",
                  "form": "form",
                  "human_description": {
                    "en_US": "Defines from where you want the search to originate. (For example - New York)",
                    "zh_Hans": "定义您想要搜索的起始位置。 （例如 - 纽约）"
                  },
                  "label": {
                    "en_US": "Location",
                    "zh_Hans": "询问"
                  },
                  "llm_description": "Defines from where you want the search to originate. (For example - New York)",
                  "max": null,
                  "min": null,
                  "name": "location",
                  "options": [
                    {
                      "label": {
                        "en_US": "Australia",
                        "pt_BR": "Australia",
                        "zh_Hans": "澳大利亚"
                      },
                      "value": "AU"
                    },
                    {
                      "label": {
                        "en_US": "Brazil",
                        "pt_BR": "Brazil",
                        "zh_Hans": "巴西"
                      },
                      "value": "BR"
                    },
                    {
                      "label": {
                        "en_US": "Canada",
                        "pt_BR": "Canada",
                        "zh_Hans": "加拿大"
                      },
                      "value": "CA"
                    },
                    {
                      "label": {
                        "en_US": "Germany",
                        "pt_BR": "Germany",
                        "zh_Hans": "德国"
                      },
                      "value": "DE"
                    },
                    {
                      "label": {
                        "en_US": "France",
                        "pt_BR": "France",
                        "zh_Hans": "法国"
                      },
                      "value": "FR"
                    },
                    {
                      "label": {
                        "en_US": "United Kingdom",
                        "pt_BR": "United Kingdom",
                        "zh_Hans": "英国"
                      },
                      "value": "GB"
                    },
                    {
                      "label": {
                        "en_US": "United States",
                        "pt_BR": "United States",
                        "zh_Hans": "美国"
                      },
                      "value": "US"
                    },
                    {
                      "label": {
                        "en_US": "Japan",
                        "pt_BR": "Japan",
                        "zh_Hans": "日本"
                      },
                      "value": "JP"
                    },
                    {
                      "label": {
                        "en_US": "India",
                        "pt_BR": "India",
                        "zh_Hans": "印度"
                      },
                      "value": "IN"
                    },
                    {
                      "label": {
                        "en_US": "Korea",
                        "pt_BR": "Korea",
                        "zh_Hans": "韩国"
                      },
                      "value": "KR"
                    },
                    {
                      "label": {
                        "en_US": "Singapore",
                        "pt_BR": "Singapore",
                        "zh_Hans": "新加坡"
                      },
                      "value": "SG"
                    },
                    {
                      "label": {
                        "en_US": "Sweden",
                        "pt_BR": "Sweden",
                        "zh_Hans": "瑞典"
                      },
                      "value": "SE"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "desktop",
                  "form": "form",
                  "human_description": {
                    "en_US": "Defines the device to make interface search. Default is \"desktop\".",
                    "zh_Hans": "定义进行接口搜索的设备。默认为“桌面”"
                  },
                  "label": {
                    "en_US": "Device Type",
                    "zh_Hans": "汉斯先生"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "device",
                  "options": [
                    {
                      "label": {
                        "en_US": "Desktop",
                        "zh_Hans": "桌面"
                      },
                      "value": "desktop"
                    },
                    {
                      "label": {
                        "en_US": "Mobile",
                        "zh_Hans": "移动的"
                      },
                      "value": "mobile"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "US",
                  "form": "form",
                  "human_description": {
                    "en_US": "Defines the country of the search. Default is \"US\".",
                    "zh_Hans": "定义搜索的国家/地区。默认为“美国”。"
                  },
                  "label": {
                    "en_US": "Country",
                    "zh_Hans": "国家/地区"
                  },
                  "llm_description": "Defines the gl parameter of the Google search.",
                  "max": null,
                  "min": null,
                  "name": "gl",
                  "options": [
                    {
                      "label": {
                        "en_US": "Australia",
                        "pt_BR": "Australia",
                        "zh_Hans": "澳大利亚"
                      },
                      "value": "AU"
                    },
                    {
                      "label": {
                        "en_US": "Brazil",
                        "pt_BR": "Brazil",
                        "zh_Hans": "巴西"
                      },
                      "value": "BR"
                    },
                    {
                      "label": {
                        "en_US": "Canada",
                        "pt_BR": "Canada",
                        "zh_Hans": "加拿大"
                      },
                      "value": "CA"
                    },
                    {
                      "label": {
                        "en_US": "Germany",
                        "pt_BR": "Germany",
                        "zh_Hans": "德国"
                      },
                      "value": "DE"
                    },
                    {
                      "label": {
                        "en_US": "France",
                        "pt_BR": "France",
                        "zh_Hans": "法国"
                      },
                      "value": "FR"
                    },
                    {
                      "label": {
                        "en_US": "United Kingdom",
                        "pt_BR": "United Kingdom",
                        "zh_Hans": "英国"
                      },
                      "value": "GB"
                    },
                    {
                      "label": {
                        "en_US": "India",
                        "pt_BR": "India",
                        "zh_Hans": "印度"
                      },
                      "value": "IN"
                    },
                    {
                      "label": {
                        "en_US": "Korea",
                        "pt_BR": "Korea",
                        "zh_Hans": "韩国"
                      },
                      "value": "KR"
                    },
                    {
                      "label": {
                        "en_US": "Sweden",
                        "pt_BR": "Sweden",
                        "zh_Hans": "瑞典"
                      },
                      "value": "SE"
                    },
                    {
                      "label": {
                        "en_US": "Singapore",
                        "pt_BR": "Singapore",
                        "zh_Hans": "新加坡"
                      },
                      "value": "SG"
                    },
                    {
                      "label": {
                        "en_US": "United States",
                        "pt_BR": "United States",
                        "zh_Hans": "美国"
                      },
                      "value": "US"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "en",
                  "form": "form",
                  "human_description": {
                    "en_US": "Defines the interface language of the search. Default is \"en\".",
                    "zh_Hans": "定义搜索的界面语言。默认为“en”。"
                  },
                  "label": {
                    "en_US": "Language",
                    "zh_Hans": "语言"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "hl",
                  "options": [
                    {
                      "label": {
                        "en_US": "Arabic",
                        "zh_Hans": "阿拉伯语"
                      },
                      "value": "ar"
                    },
                    {
                      "label": {
                        "en_US": "Bulgarian",
                        "zh_Hans": "保加利亚语"
                      },
                      "value": "bg"
                    },
                    {
                      "label": {
                        "en_US": "Catalan",
                        "zh_Hans": "加泰罗尼亚语"
                      },
                      "value": "ca"
                    },
                    {
                      "label": {
                        "en_US": "Chinese (Simplified)",
                        "zh_Hans": "中文（简体）"
                      },
                      "value": "zh-cn"
                    },
                    {
                      "label": {
                        "en_US": "Chinese (Traditional)",
                        "zh_Hans": "中文（繁体）"
                      },
                      "value": "zh-tw"
                    },
                    {
                      "label": {
                        "en_US": "Czech",
                        "zh_Hans": "捷克语"
                      },
                      "value": "cs"
                    },
                    {
                      "label": {
                        "en_US": "Danish",
                        "zh_Hans": "丹麦语"
                      },
                      "value": "da"
                    },
                    {
                      "label": {
                        "en_US": "Dutch",
                        "zh_Hans": "荷兰语"
                      },
                      "value": "nl"
                    },
                    {
                      "label": {
                        "en_US": "English",
                        "zh_Hans": "英语"
                      },
                      "value": "en"
                    },
                    {
                      "label": {
                        "en_US": "Estonian",
                        "zh_Hans": "爱沙尼亚语"
                      },
                      "value": "et"
                    },
                    {
                      "label": {
                        "en_US": "Finnish",
                        "zh_Hans": "芬兰语"
                      },
                      "value": "fi"
                    },
                    {
                      "label": {
                        "en_US": "French",
                        "zh_Hans": "法语"
                      },
                      "value": "fr"
                    },
                    {
                      "label": {
                        "en_US": "German",
                        "zh_Hans": "德语"
                      },
                      "value": "de"
                    },
                    {
                      "label": {
                        "en_US": "Greek",
                        "zh_Hans": "希腊语"
                      },
                      "value": "el"
                    },
                    {
                      "label": {
                        "en_US": "Hebrew",
                        "zh_Hans": "希伯来语"
                      },
                      "value": "iw"
                    },
                    {
                      "label": {
                        "en_US": "Hindi",
                        "zh_Hans": "印地语"
                      },
                      "value": "hi"
                    },
                    {
                      "label": {
                        "en_US": "Hungarian",
                        "zh_Hans": "匈牙利语"
                      },
                      "value": "hu"
                    },
                    {
                      "label": {
                        "en_US": "Indonesian",
                        "zh_Hans": "印尼语"
                      },
                      "value": "id"
                    },
                    {
                      "label": {
                        "en_US": "Italian",
                        "zh_Hans": "意大利语"
                      },
                      "value": "it"
                    },
                    {
                      "label": {
                        "en_US": "Japanese",
                        "zh_Hans": "日语"
                      },
                      "value": "ja"
                    },
                    {
                      "label": {
                        "en_US": "Kannada",
                        "zh_Hans": "卡纳达语"
                      },
                      "value": "kn"
                    },
                    {
                      "label": {
                        "en_US": "Korean",
                        "zh_Hans": "韩语"
                      },
                      "value": "ko"
                    },
                    {
                      "label": {
                        "en_US": "Latvian",
                        "zh_Hans": "拉脱维亚语"
                      },
                      "value": "lv"
                    },
                    {
                      "label": {
                        "en_US": "Lithuanian",
                        "zh_Hans": "立陶宛语"
                      },
                      "value": "lt"
                    },
                    {
                      "label": {
                        "en_US": "Malay",
                        "zh_Hans": "马来语"
                      },
                      "value": "my"
                    },
                    {
                      "label": {
                        "en_US": "Malayalam",
                        "zh_Hans": "马拉雅拉姆语"
                      },
                      "value": "ml"
                    },
                    {
                      "label": {
                        "en_US": "Marathi",
                        "zh_Hans": "马拉地语"
                      },
                      "value": "mr"
                    },
                    {
                      "label": {
                        "en_US": "Norwegian",
                        "zh_Hans": "挪威语"
                      },
                      "value": "no"
                    },
                    {
                      "label": {
                        "en_US": "Polish",
                        "zh_Hans": "波兰语"
                      },
                      "value": "pl"
                    },
                    {
                      "label": {
                        "en_US": "Portuguese (Brazil)",
                        "zh_Hans": "葡萄牙语（巴西）"
                      },
                      "value": "pt-br"
                    },
                    {
                      "label": {
                        "en_US": "Portuguese (Portugal)",
                        "zh_Hans": "葡萄牙语（葡萄牙）"
                      },
                      "value": "pt-pt"
                    },
                    {
                      "label": {
                        "en_US": "Punjabi",
                        "zh_Hans": "旁遮普语"
                      },
                      "value": "pa"
                    },
                    {
                      "label": {
                        "en_US": "Romanian",
                        "zh_Hans": "罗马尼亚语"
                      },
                      "value": "ro"
                    },
                    {
                      "label": {
                        "en_US": "Russian",
                        "zh_Hans": "俄语"
                      },
                      "value": "ru"
                    },
                    {
                      "label": {
                        "en_US": "Serbian",
                        "zh_Hans": "塞尔维亚语"
                      },
                      "value": "sr"
                    },
                    {
                      "label": {
                        "en_US": "Slovak",
                        "zh_Hans": "斯洛伐克语"
                      },
                      "value": "sk"
                    },
                    {
                      "label": {
                        "en_US": "Slovenian",
                        "zh_Hans": "斯洛文尼亚语"
                      },
                      "value": "sl"
                    },
                    {
                      "label": {
                        "en_US": "Spanish",
                        "zh_Hans": "西班牙语"
                      },
                      "value": "es"
                    },
                    {
                      "label": {
                        "en_US": "Swedish",
                        "zh_Hans": "瑞典语"
                      },
                      "value": "sv"
                    },
                    {
                      "label": {
                        "en_US": "Tamil",
                        "zh_Hans": "泰米尔语"
                      },
                      "value": "ta"
                    },
                    {
                      "label": {
                        "en_US": "Telugu",
                        "zh_Hans": "泰卢固语"
                      },
                      "value": "te"
                    },
                    {
                      "label": {
                        "en_US": "Thai",
                        "zh_Hans": "泰语"
                      },
                      "value": "th"
                    },
                    {
                      "label": {
                        "en_US": "Turkish",
                        "zh_Hans": "土耳其语"
                      },
                      "value": "tr"
                    },
                    {
                      "label": {
                        "en_US": "Ukrainian",
                        "zh_Hans": "乌克兰语"
                      },
                      "value": "uk"
                    },
                    {
                      "label": {
                        "en_US": "Vietnamese",
                        "zh_Hans": "越南语"
                      },
                      "value": "vi"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool to retrieve scholarly literature.",
                  "zh_Hans": "学术文献检索工具"
                },
                "llm": "A tool to retrieve scholarly literature."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Scholar API",
                  "zh_Hans": "Scholar API"
                },
                "name": "scholar_search"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Defines the query you want to search.",
                    "zh_Hans": "定义您要搜索的查询。"
                  },
                  "label": {
                    "en_US": "Query",
                    "zh_Hans": "询问"
                  },
                  "llm_description": "Defines the search query you want to search.",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "US",
                  "form": "form",
                  "human_description": {
                    "en_US": "Defines from where you want the search to originate. (For example - New York)",
                    "zh_Hans": "定义您想要搜索的起始位置。 （例如 - 纽约）"
                  },
                  "label": {
                    "en_US": "Location",
                    "zh_Hans": "询问"
                  },
                  "llm_description": "Defines from where you want the search to originate. (For example - New York)",
                  "max": null,
                  "min": null,
                  "name": "location",
                  "options": [
                    {
                      "label": {
                        "en_US": "Australia",
                        "pt_BR": "Australia",
                        "zh_Hans": "澳大利亚"
                      },
                      "value": "AU"
                    },
                    {
                      "label": {
                        "en_US": "Brazil",
                        "pt_BR": "Brazil",
                        "zh_Hans": "巴西"
                      },
                      "value": "BR"
                    },
                    {
                      "label": {
                        "en_US": "Canada",
                        "pt_BR": "Canada",
                        "zh_Hans": "加拿大"
                      },
                      "value": "CA"
                    },
                    {
                      "label": {
                        "en_US": "Germany",
                        "pt_BR": "Germany",
                        "zh_Hans": "德国"
                      },
                      "value": "DE"
                    },
                    {
                      "label": {
                        "en_US": "France",
                        "pt_BR": "France",
                        "zh_Hans": "法国"
                      },
                      "value": "FR"
                    },
                    {
                      "label": {
                        "en_US": "United Kingdom",
                        "pt_BR": "United Kingdom",
                        "zh_Hans": "英国"
                      },
                      "value": "GB"
                    },
                    {
                      "label": {
                        "en_US": "United States",
                        "pt_BR": "United States",
                        "zh_Hans": "美国"
                      },
                      "value": "US"
                    },
                    {
                      "label": {
                        "en_US": "Japan",
                        "pt_BR": "Japan",
                        "zh_Hans": "日本"
                      },
                      "value": "JP"
                    },
                    {
                      "label": {
                        "en_US": "India",
                        "pt_BR": "India",
                        "zh_Hans": "印度"
                      },
                      "value": "IN"
                    },
                    {
                      "label": {
                        "en_US": "Korea",
                        "pt_BR": "Korea",
                        "zh_Hans": "韩国"
                      },
                      "value": "KR"
                    },
                    {
                      "label": {
                        "en_US": "Singapore",
                        "pt_BR": "Singapore",
                        "zh_Hans": "新加坡"
                      },
                      "value": "SG"
                    },
                    {
                      "label": {
                        "en_US": "Sweden",
                        "pt_BR": "Sweden",
                        "zh_Hans": "瑞典"
                      },
                      "value": "SE"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "US",
                  "form": "form",
                  "human_description": {
                    "en_US": "Defines the country of the search. Default is \"US\".",
                    "zh_Hans": "定义搜索的国家/地区。默认为“美国”。"
                  },
                  "label": {
                    "en_US": "Country",
                    "zh_Hans": "国家/地区"
                  },
                  "llm_description": "Defines the gl parameter of the Google search.",
                  "max": null,
                  "min": null,
                  "name": "gl",
                  "options": [
                    {
                      "label": {
                        "en_US": "Argentina",
                        "pt_BR": "Argentina",
                        "zh_Hans": "阿根廷"
                      },
                      "value": "AR"
                    },
                    {
                      "label": {
                        "en_US": "Australia",
                        "pt_BR": "Australia",
                        "zh_Hans": "澳大利亚"
                      },
                      "value": "AU"
                    },
                    {
                      "label": {
                        "en_US": "Austria",
                        "pt_BR": "Austria",
                        "zh_Hans": "奥地利"
                      },
                      "value": "AT"
                    },
                    {
                      "label": {
                        "en_US": "Belgium",
                        "pt_BR": "Belgium",
                        "zh_Hans": "比利时"
                      },
                      "value": "BE"
                    },
                    {
                      "label": {
                        "en_US": "Brazil",
                        "pt_BR": "Brazil",
                        "zh_Hans": "巴西"
                      },
                      "value": "BR"
                    },
                    {
                      "label": {
                        "en_US": "Canada",
                        "pt_BR": "Canada",
                        "zh_Hans": "加拿大"
                      },
                      "value": "CA"
                    },
                    {
                      "label": {
                        "en_US": "Chile",
                        "pt_BR": "Chile",
                        "zh_Hans": "智利"
                      },
                      "value": "CL"
                    },
                    {
                      "label": {
                        "en_US": "Colombia",
                        "pt_BR": "Colombia",
                        "zh_Hans": "哥伦比亚"
                      },
                      "value": "CO"
                    },
                    {
                      "label": {
                        "en_US": "China",
                        "pt_BR": "China",
                        "zh_Hans": "中国"
                      },
                      "value": "CN"
                    },
                    {
                      "label": {
                        "en_US": "Czech Republic",
                        "pt_BR": "Czech Republic",
                        "zh_Hans": "捷克共和国"
                      },
                      "value": "CZ"
                    },
                    {
                      "label": {
                        "en_US": "Denmark",
                        "pt_BR": "Denmark",
                        "zh_Hans": "丹麦"
                      },
                      "value": "DK"
                    },
                    {
                      "label": {
                        "en_US": "Finland",
                        "pt_BR": "Finland",
                        "zh_Hans": "芬兰"
                      },
                      "value": "FI"
                    },
                    {
                      "label": {
                        "en_US": "France",
                        "pt_BR": "France",
                        "zh_Hans": "法国"
                      },
                      "value": "FR"
                    },
                    {
                      "label": {
                        "en_US": "Germany",
                        "pt_BR": "Germany",
                        "zh_Hans": "德国"
                      },
                      "value": "DE"
                    },
                    {
                      "label": {
                        "en_US": "Hong Kong",
                        "pt_BR": "Hong Kong",
                        "zh_Hans": "香港"
                      },
                      "value": "HK"
                    },
                    {
                      "label": {
                        "en_US": "India",
                        "pt_BR": "India",
                        "zh_Hans": "印度"
                      },
                      "value": "IN"
                    },
                    {
                      "label": {
                        "en_US": "Indonesia",
                        "pt_BR": "Indonesia",
                        "zh_Hans": "印度尼西亚"
                      },
                      "value": "ID"
                    },
                    {
                      "label": {
                        "en_US": "Italy",
                        "pt_BR": "Italy",
                        "zh_Hans": "意大利"
                      },
                      "value": "IT"
                    },
                    {
                      "label": {
                        "en_US": "Japan",
                        "pt_BR": "Japan",
                        "zh_Hans": "日本"
                      },
                      "value": "JP"
                    },
                    {
                      "label": {
                        "en_US": "Korea",
                        "pt_BR": "Korea",
                        "zh_Hans": "韩国"
                      },
                      "value": "KR"
                    },
                    {
                      "label": {
                        "en_US": "Malaysia",
                        "pt_BR": "Malaysia",
                        "zh_Hans": "马来西亚"
                      },
                      "value": "MY"
                    },
                    {
                      "label": {
                        "en_US": "Mexico",
                        "pt_BR": "Mexico",
                        "zh_Hans": "墨西哥"
                      },
                      "value": "MX"
                    },
                    {
                      "label": {
                        "en_US": "Netherlands",
                        "pt_BR": "Netherlands",
                        "zh_Hans": "荷兰"
                      },
                      "value": "NL"
                    },
                    {
                      "label": {
                        "en_US": "New Zealand",
                        "pt_BR": "New Zealand",
                        "zh_Hans": "新西兰"
                      },
                      "value": "NZ"
                    },
                    {
                      "label": {
                        "en_US": "Norway",
                        "pt_BR": "Norway",
                        "zh_Hans": "挪威"
                      },
                      "value": "NO"
                    },
                    {
                      "label": {
                        "en_US": "Philippines",
                        "pt_BR": "Philippines",
                        "zh_Hans": "菲律宾"
                      },
                      "value": "PH"
                    },
                    {
                      "label": {
                        "en_US": "Poland",
                        "pt_BR": "Poland",
                        "zh_Hans": "波兰"
                      },
                      "value": "PL"
                    },
                    {
                      "label": {
                        "en_US": "Portugal",
                        "pt_BR": "Portugal",
                        "zh_Hans": "葡萄牙"
                      },
                      "value": "PT"
                    },
                    {
                      "label": {
                        "en_US": "Russia",
                        "pt_BR": "Russia",
                        "zh_Hans": "俄罗斯"
                      },
                      "value": "RU"
                    },
                    {
                      "label": {
                        "en_US": "Saudi Arabia",
                        "pt_BR": "Saudi Arabia",
                        "zh_Hans": "沙特阿拉伯"
                      },
                      "value": "SA"
                    },
                    {
                      "label": {
                        "en_US": "Singapore",
                        "pt_BR": "Singapore",
                        "zh_Hans": "新加坡"
                      },
                      "value": "SG"
                    },
                    {
                      "label": {
                        "en_US": "South Africa",
                        "pt_BR": "South Africa",
                        "zh_Hans": "南非"
                      },
                      "value": "ZA"
                    },
                    {
                      "label": {
                        "en_US": "Spain",
                        "pt_BR": "Spain",
                        "zh_Hans": "西班牙"
                      },
                      "value": "ES"
                    },
                    {
                      "label": {
                        "en_US": "Sweden",
                        "pt_BR": "Sweden",
                        "zh_Hans": "瑞典"
                      },
                      "value": "SE"
                    },
                    {
                      "label": {
                        "en_US": "Switzerland",
                        "pt_BR": "Switzerland",
                        "zh_Hans": "瑞士"
                      },
                      "value": "CH"
                    },
                    {
                      "label": {
                        "en_US": "Taiwan",
                        "pt_BR": "Taiwan",
                        "zh_Hans": "台湾"
                      },
                      "value": "TW"
                    },
                    {
                      "label": {
                        "en_US": "Thailand",
                        "pt_BR": "Thailand",
                        "zh_Hans": "泰国"
                      },
                      "value": "TH"
                    },
                    {
                      "label": {
                        "en_US": "Turkey",
                        "pt_BR": "Turkey",
                        "zh_Hans": "土耳其"
                      },
                      "value": "TR"
                    },
                    {
                      "label": {
                        "en_US": "United Kingdom",
                        "pt_BR": "United Kingdom",
                        "zh_Hans": "英国"
                      },
                      "value": "GB"
                    },
                    {
                      "label": {
                        "en_US": "United States",
                        "pt_BR": "United States",
                        "zh_Hans": "美国"
                      },
                      "value": "US"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "en",
                  "form": "form",
                  "human_description": {
                    "en_US": "Defines the interface language of the search. Default is \"en\".",
                    "zh_Hans": "定义搜索的界面语言。默认为“en”。"
                  },
                  "label": {
                    "en_US": "Language",
                    "zh_Hans": "语言"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "hl",
                  "options": [
                    {
                      "label": {
                        "en_US": "Arabic",
                        "zh_Hans": "阿拉伯语"
                      },
                      "value": "ar"
                    },
                    {
                      "label": {
                        "en_US": "Bulgarian",
                        "zh_Hans": "保加利亚语"
                      },
                      "value": "bg"
                    },
                    {
                      "label": {
                        "en_US": "Catalan",
                        "zh_Hans": "加泰罗尼亚语"
                      },
                      "value": "ca"
                    },
                    {
                      "label": {
                        "en_US": "Chinese (Simplified)",
                        "zh_Hans": "中文（简体）"
                      },
                      "value": "zh-cn"
                    },
                    {
                      "label": {
                        "en_US": "Chinese (Traditional)",
                        "zh_Hans": "中文（繁体）"
                      },
                      "value": "zh-tw"
                    },
                    {
                      "label": {
                        "en_US": "Czech",
                        "zh_Hans": "捷克语"
                      },
                      "value": "cs"
                    },
                    {
                      "label": {
                        "en_US": "Danish",
                        "zh_Hans": "丹麦语"
                      },
                      "value": "da"
                    },
                    {
                      "label": {
                        "en_US": "Dutch",
                        "zh_Hans": "荷兰语"
                      },
                      "value": "nl"
                    },
                    {
                      "label": {
                        "en_US": "English",
                        "zh_Hans": "英语"
                      },
                      "value": "en"
                    },
                    {
                      "label": {
                        "en_US": "Estonian",
                        "zh_Hans": "爱沙尼亚语"
                      },
                      "value": "et"
                    },
                    {
                      "label": {
                        "en_US": "Finnish",
                        "zh_Hans": "芬兰语"
                      },
                      "value": "fi"
                    },
                    {
                      "label": {
                        "en_US": "French",
                        "zh_Hans": "法语"
                      },
                      "value": "fr"
                    },
                    {
                      "label": {
                        "en_US": "German",
                        "zh_Hans": "德语"
                      },
                      "value": "de"
                    },
                    {
                      "label": {
                        "en_US": "Greek",
                        "zh_Hans": "希腊语"
                      },
                      "value": "el"
                    },
                    {
                      "label": {
                        "en_US": "Hebrew",
                        "zh_Hans": "希伯来语"
                      },
                      "value": "iw"
                    },
                    {
                      "label": {
                        "en_US": "Hindi",
                        "zh_Hans": "印地语"
                      },
                      "value": "hi"
                    },
                    {
                      "label": {
                        "en_US": "Hungarian",
                        "zh_Hans": "匈牙利语"
                      },
                      "value": "hu"
                    },
                    {
                      "label": {
                        "en_US": "Indonesian",
                        "zh_Hans": "印尼语"
                      },
                      "value": "id"
                    },
                    {
                      "label": {
                        "en_US": "Italian",
                        "zh_Hans": "意大利语"
                      },
                      "value": "it"
                    },
                    {
                      "label": {
                        "en_US": "Japanese",
                        "zh_Hans": "日语"
                      },
                      "value": "ja"
                    },
                    {
                      "label": {
                        "en_US": "Kannada",
                        "zh_Hans": "卡纳达语"
                      },
                      "value": "kn"
                    },
                    {
                      "label": {
                        "en_US": "Korean",
                        "zh_Hans": "韩语"
                      },
                      "value": "ko"
                    },
                    {
                      "label": {
                        "en_US": "Latvian",
                        "zh_Hans": "拉脱维亚语"
                      },
                      "value": "lv"
                    },
                    {
                      "label": {
                        "en_US": "Lithuanian",
                        "zh_Hans": "立陶宛语"
                      },
                      "value": "lt"
                    },
                    {
                      "label": {
                        "en_US": "Malay",
                        "zh_Hans": "马来语"
                      },
                      "value": "my"
                    },
                    {
                      "label": {
                        "en_US": "Malayalam",
                        "zh_Hans": "马拉雅拉姆语"
                      },
                      "value": "ml"
                    },
                    {
                      "label": {
                        "en_US": "Marathi",
                        "zh_Hans": "马拉地语"
                      },
                      "value": "mr"
                    },
                    {
                      "label": {
                        "en_US": "Norwegian",
                        "zh_Hans": "挪威语"
                      },
                      "value": "no"
                    },
                    {
                      "label": {
                        "en_US": "Polish",
                        "zh_Hans": "波兰语"
                      },
                      "value": "pl"
                    },
                    {
                      "label": {
                        "en_US": "Portuguese (Brazil)",
                        "zh_Hans": "葡萄牙语（巴西）"
                      },
                      "value": "pt-br"
                    },
                    {
                      "label": {
                        "en_US": "Portuguese (Portugal)",
                        "zh_Hans": "葡萄牙语（葡萄牙）"
                      },
                      "value": "pt-pt"
                    },
                    {
                      "label": {
                        "en_US": "Punjabi",
                        "zh_Hans": "旁遮普语"
                      },
                      "value": "pa"
                    },
                    {
                      "label": {
                        "en_US": "Romanian",
                        "zh_Hans": "罗马尼亚语"
                      },
                      "value": "ro"
                    },
                    {
                      "label": {
                        "en_US": "Russian",
                        "zh_Hans": "俄语"
                      },
                      "value": "ru"
                    },
                    {
                      "label": {
                        "en_US": "Serbian",
                        "zh_Hans": "塞尔维亚语"
                      },
                      "value": "sr"
                    },
                    {
                      "label": {
                        "en_US": "Slovak",
                        "zh_Hans": "斯洛伐克语"
                      },
                      "value": "sk"
                    },
                    {
                      "label": {
                        "en_US": "Slovenian",
                        "zh_Hans": "斯洛文尼亚语"
                      },
                      "value": "sl"
                    },
                    {
                      "label": {
                        "en_US": "Spanish",
                        "zh_Hans": "西班牙语"
                      },
                      "value": "es"
                    },
                    {
                      "label": {
                        "en_US": "Swedish",
                        "zh_Hans": "瑞典语"
                      },
                      "value": "sv"
                    },
                    {
                      "label": {
                        "en_US": "Tamil",
                        "zh_Hans": "泰米尔语"
                      },
                      "value": "ta"
                    },
                    {
                      "label": {
                        "en_US": "Telugu",
                        "zh_Hans": "泰卢固语"
                      },
                      "value": "te"
                    },
                    {
                      "label": {
                        "en_US": "Thai",
                        "zh_Hans": "泰语"
                      },
                      "value": "th"
                    },
                    {
                      "label": {
                        "en_US": "Turkish",
                        "zh_Hans": "土耳其语"
                      },
                      "value": "tr"
                    },
                    {
                      "label": {
                        "en_US": "Ukrainian",
                        "zh_Hans": "乌克兰语"
                      },
                      "value": "uk"
                    },
                    {
                      "label": {
                        "en_US": "Vietnamese",
                        "zh_Hans": "越南语"
                      },
                      "value": "vi"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool to retrieve job titles, company names and description from Google Jobs engine.",
                  "zh_Hans": "一个从 Google 招聘引擎检索职位名称、公司名称和描述的工具。"
                },
                "llm": "A tool to retrieve job titles, company names and description from Google Jobs engine."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Job Search API",
                  "zh_Hans": "Job Search API"
                },
                "name": "job_search"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Defines the query you want to search.",
                    "zh_Hans": "定义您要搜索的查询。"
                  },
                  "label": {
                    "en_US": "Query",
                    "zh_Hans": "询问"
                  },
                  "llm_description": "Defines the search query you want to search.",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "US",
                  "form": "form",
                  "human_description": {
                    "en_US": "Defines from where you want the search to originate. (For example - New York)",
                    "zh_Hans": "定义您想要搜索的起始位置。 （例如 - 纽约）"
                  },
                  "label": {
                    "en_US": "Location",
                    "zh_Hans": "询问"
                  },
                  "llm_description": "Defines from where you want the search to originate. (For example - New York)",
                  "max": null,
                  "min": null,
                  "name": "location",
                  "options": [
                    {
                      "label": {
                        "en_US": "United States",
                        "pt_BR": "United States",
                        "zh_Hans": "美国"
                      },
                      "value": "US"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool to retrieve organic search results snippets and links from Google News engine.",
                  "zh_Hans": "一种从 Google 新闻引擎检索有机搜索结果片段和链接的工具。"
                },
                "llm": "A tool to retrieve organic search results snippets and links from Google News engine."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "News Search API",
                  "zh_Hans": "News Search API"
                },
                "name": "news_search"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Defines the query you want to search.",
                    "zh_Hans": "定义您要搜索的查询。"
                  },
                  "label": {
                    "en_US": "Query",
                    "zh_Hans": "询问"
                  },
                  "llm_description": "Defines the search query you want to search.",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "US",
                  "form": "form",
                  "human_description": {
                    "en_US": "Defines from where you want the search to originate. (For example - New York)",
                    "zh_Hans": "定义您想要搜索的起始位置。 （例如 - 纽约）"
                  },
                  "label": {
                    "en_US": "Location",
                    "zh_Hans": "询问"
                  },
                  "llm_description": "Defines from where you want the search to originate. (For example - New York)",
                  "max": null,
                  "min": null,
                  "name": "location",
                  "options": [
                    {
                      "label": {
                        "en_US": "Australia",
                        "pt_BR": "Australia",
                        "zh_Hans": "澳大利亚"
                      },
                      "value": "AU"
                    },
                    {
                      "label": {
                        "en_US": "Brazil",
                        "pt_BR": "Brazil",
                        "zh_Hans": "巴西"
                      },
                      "value": "BR"
                    },
                    {
                      "label": {
                        "en_US": "Canada",
                        "pt_BR": "Canada",
                        "zh_Hans": "加拿大"
                      },
                      "value": "CA"
                    },
                    {
                      "label": {
                        "en_US": "Germany",
                        "pt_BR": "Germany",
                        "zh_Hans": "德国"
                      },
                      "value": "DE"
                    },
                    {
                      "label": {
                        "en_US": "France",
                        "pt_BR": "France",
                        "zh_Hans": "法国"
                      },
                      "value": "FR"
                    },
                    {
                      "label": {
                        "en_US": "United Kingdom",
                        "pt_BR": "United Kingdom",
                        "zh_Hans": "英国"
                      },
                      "value": "GB"
                    },
                    {
                      "label": {
                        "en_US": "United States",
                        "pt_BR": "United States",
                        "zh_Hans": "美国"
                      },
                      "value": "US"
                    },
                    {
                      "label": {
                        "en_US": "Japan",
                        "pt_BR": "Japan",
                        "zh_Hans": "日本"
                      },
                      "value": "JP"
                    },
                    {
                      "label": {
                        "en_US": "India",
                        "pt_BR": "India",
                        "zh_Hans": "印度"
                      },
                      "value": "IN"
                    },
                    {
                      "label": {
                        "en_US": "Korea",
                        "pt_BR": "Korea",
                        "zh_Hans": "韩国"
                      },
                      "value": "KR"
                    },
                    {
                      "label": {
                        "en_US": "Singapore",
                        "pt_BR": "Singapore",
                        "zh_Hans": "新加坡"
                      },
                      "value": "SG"
                    },
                    {
                      "label": {
                        "en_US": "Sweden",
                        "pt_BR": "Sweden",
                        "zh_Hans": "瑞典"
                      },
                      "value": "SE"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "US",
                  "form": "form",
                  "human_description": {
                    "en_US": "Defines the country of the search. Default is \"US\".",
                    "zh_Hans": "定义搜索的国家/地区。默认为“美国”。"
                  },
                  "label": {
                    "en_US": "Country",
                    "zh_Hans": "国家/地区"
                  },
                  "llm_description": "Defines the gl parameter of the Google search.",
                  "max": null,
                  "min": null,
                  "name": "gl",
                  "options": [
                    {
                      "label": {
                        "en_US": "Argentina",
                        "pt_BR": "Argentina",
                        "zh_Hans": "阿根廷"
                      },
                      "value": "AR"
                    },
                    {
                      "label": {
                        "en_US": "Australia",
                        "pt_BR": "Australia",
                        "zh_Hans": "澳大利亚"
                      },
                      "value": "AU"
                    },
                    {
                      "label": {
                        "en_US": "Austria",
                        "pt_BR": "Austria",
                        "zh_Hans": "奥地利"
                      },
                      "value": "AT"
                    },
                    {
                      "label": {
                        "en_US": "Belgium",
                        "pt_BR": "Belgium",
                        "zh_Hans": "比利时"
                      },
                      "value": "BE"
                    },
                    {
                      "label": {
                        "en_US": "Brazil",
                        "pt_BR": "Brazil",
                        "zh_Hans": "巴西"
                      },
                      "value": "BR"
                    },
                    {
                      "label": {
                        "en_US": "Canada",
                        "pt_BR": "Canada",
                        "zh_Hans": "加拿大"
                      },
                      "value": "CA"
                    },
                    {
                      "label": {
                        "en_US": "Chile",
                        "pt_BR": "Chile",
                        "zh_Hans": "智利"
                      },
                      "value": "CL"
                    },
                    {
                      "label": {
                        "en_US": "Colombia",
                        "pt_BR": "Colombia",
                        "zh_Hans": "哥伦比亚"
                      },
                      "value": "CO"
                    },
                    {
                      "label": {
                        "en_US": "China",
                        "pt_BR": "China",
                        "zh_Hans": "中国"
                      },
                      "value": "CN"
                    },
                    {
                      "label": {
                        "en_US": "Czech Republic",
                        "pt_BR": "Czech Republic",
                        "zh_Hans": "捷克共和国"
                      },
                      "value": "CZ"
                    },
                    {
                      "label": {
                        "en_US": "Denmark",
                        "pt_BR": "Denmark",
                        "zh_Hans": "丹麦"
                      },
                      "value": "DK"
                    },
                    {
                      "label": {
                        "en_US": "Finland",
                        "pt_BR": "Finland",
                        "zh_Hans": "芬兰"
                      },
                      "value": "FI"
                    },
                    {
                      "label": {
                        "en_US": "France",
                        "pt_BR": "France",
                        "zh_Hans": "法国"
                      },
                      "value": "FR"
                    },
                    {
                      "label": {
                        "en_US": "Germany",
                        "pt_BR": "Germany",
                        "zh_Hans": "德国"
                      },
                      "value": "DE"
                    },
                    {
                      "label": {
                        "en_US": "Hong Kong",
                        "pt_BR": "Hong Kong",
                        "zh_Hans": "香港"
                      },
                      "value": "HK"
                    },
                    {
                      "label": {
                        "en_US": "India",
                        "pt_BR": "India",
                        "zh_Hans": "印度"
                      },
                      "value": "IN"
                    },
                    {
                      "label": {
                        "en_US": "Indonesia",
                        "pt_BR": "Indonesia",
                        "zh_Hans": "印度尼西亚"
                      },
                      "value": "ID"
                    },
                    {
                      "label": {
                        "en_US": "Italy",
                        "pt_BR": "Italy",
                        "zh_Hans": "意大利"
                      },
                      "value": "IT"
                    },
                    {
                      "label": {
                        "en_US": "Japan",
                        "pt_BR": "Japan",
                        "zh_Hans": "日本"
                      },
                      "value": "JP"
                    },
                    {
                      "label": {
                        "en_US": "Korea",
                        "pt_BR": "Korea",
                        "zh_Hans": "韩国"
                      },
                      "value": "KR"
                    },
                    {
                      "label": {
                        "en_US": "Malaysia",
                        "pt_BR": "Malaysia",
                        "zh_Hans": "马来西亚"
                      },
                      "value": "MY"
                    },
                    {
                      "label": {
                        "en_US": "Mexico",
                        "pt_BR": "Mexico",
                        "zh_Hans": "墨西哥"
                      },
                      "value": "MX"
                    },
                    {
                      "label": {
                        "en_US": "Netherlands",
                        "pt_BR": "Netherlands",
                        "zh_Hans": "荷兰"
                      },
                      "value": "NL"
                    },
                    {
                      "label": {
                        "en_US": "New Zealand",
                        "pt_BR": "New Zealand",
                        "zh_Hans": "新西兰"
                      },
                      "value": "NZ"
                    },
                    {
                      "label": {
                        "en_US": "Norway",
                        "pt_BR": "Norway",
                        "zh_Hans": "挪威"
                      },
                      "value": "false"
                    },
                    {
                      "label": {
                        "en_US": "Philippines",
                        "pt_BR": "Philippines",
                        "zh_Hans": "菲律宾"
                      },
                      "value": "PH"
                    },
                    {
                      "label": {
                        "en_US": "Poland",
                        "pt_BR": "Poland",
                        "zh_Hans": "波兰"
                      },
                      "value": "PL"
                    },
                    {
                      "label": {
                        "en_US": "Portugal",
                        "pt_BR": "Portugal",
                        "zh_Hans": "葡萄牙"
                      },
                      "value": "PT"
                    },
                    {
                      "label": {
                        "en_US": "Russia",
                        "pt_BR": "Russia",
                        "zh_Hans": "俄罗斯"
                      },
                      "value": "RU"
                    },
                    {
                      "label": {
                        "en_US": "Saudi Arabia",
                        "pt_BR": "Saudi Arabia",
                        "zh_Hans": "沙特阿拉伯"
                      },
                      "value": "SA"
                    },
                    {
                      "label": {
                        "en_US": "Singapore",
                        "pt_BR": "Singapore",
                        "zh_Hans": "新加坡"
                      },
                      "value": "SG"
                    },
                    {
                      "label": {
                        "en_US": "South Africa",
                        "pt_BR": "South Africa",
                        "zh_Hans": "南非"
                      },
                      "value": "ZA"
                    },
                    {
                      "label": {
                        "en_US": "Spain",
                        "pt_BR": "Spain",
                        "zh_Hans": "西班牙"
                      },
                      "value": "ES"
                    },
                    {
                      "label": {
                        "en_US": "Sweden",
                        "pt_BR": "Sweden",
                        "zh_Hans": "瑞典"
                      },
                      "value": "SE"
                    },
                    {
                      "label": {
                        "en_US": "Switzerland",
                        "pt_BR": "Switzerland",
                        "zh_Hans": "瑞士"
                      },
                      "value": "CH"
                    },
                    {
                      "label": {
                        "en_US": "Taiwan",
                        "pt_BR": "Taiwan",
                        "zh_Hans": "台湾"
                      },
                      "value": "TW"
                    },
                    {
                      "label": {
                        "en_US": "Thailand",
                        "pt_BR": "Thailand",
                        "zh_Hans": "泰国"
                      },
                      "value": "TH"
                    },
                    {
                      "label": {
                        "en_US": "Turkey",
                        "pt_BR": "Turkey",
                        "zh_Hans": "土耳其"
                      },
                      "value": "TR"
                    },
                    {
                      "label": {
                        "en_US": "United Kingdom",
                        "pt_BR": "United Kingdom",
                        "zh_Hans": "英国"
                      },
                      "value": "GB"
                    },
                    {
                      "label": {
                        "en_US": "United States",
                        "pt_BR": "United States",
                        "zh_Hans": "美国"
                      },
                      "value": "US"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "en",
                  "form": "form",
                  "human_description": {
                    "en_US": "Defines the interface language of the search. Default is \"en\".",
                    "zh_Hans": "定义搜索的界面语言。默认为“en”。"
                  },
                  "label": {
                    "en_US": "Language",
                    "zh_Hans": "语言"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "hl",
                  "options": [
                    {
                      "label": {
                        "en_US": "Arabic",
                        "zh_Hans": "阿拉伯语"
                      },
                      "value": "ar"
                    },
                    {
                      "label": {
                        "en_US": "Bulgarian",
                        "zh_Hans": "保加利亚语"
                      },
                      "value": "bg"
                    },
                    {
                      "label": {
                        "en_US": "Catalan",
                        "zh_Hans": "加泰罗尼亚语"
                      },
                      "value": "ca"
                    },
                    {
                      "label": {
                        "en_US": "Chinese (Simplified)",
                        "zh_Hans": "中文（简体）"
                      },
                      "value": "zh-cn"
                    },
                    {
                      "label": {
                        "en_US": "Chinese (Traditional)",
                        "zh_Hans": "中文（繁体）"
                      },
                      "value": "zh-tw"
                    },
                    {
                      "label": {
                        "en_US": "Czech",
                        "zh_Hans": "捷克语"
                      },
                      "value": "cs"
                    },
                    {
                      "label": {
                        "en_US": "Danish",
                        "zh_Hans": "丹麦语"
                      },
                      "value": "da"
                    },
                    {
                      "label": {
                        "en_US": "Dutch",
                        "zh_Hans": "荷兰语"
                      },
                      "value": "nl"
                    },
                    {
                      "label": {
                        "en_US": "English",
                        "zh_Hans": "英语"
                      },
                      "value": "en"
                    },
                    {
                      "label": {
                        "en_US": "Estonian",
                        "zh_Hans": "爱沙尼亚语"
                      },
                      "value": "et"
                    },
                    {
                      "label": {
                        "en_US": "Finnish",
                        "zh_Hans": "芬兰语"
                      },
                      "value": "fi"
                    },
                    {
                      "label": {
                        "en_US": "French",
                        "zh_Hans": "法语"
                      },
                      "value": "fr"
                    },
                    {
                      "label": {
                        "en_US": "German",
                        "zh_Hans": "德语"
                      },
                      "value": "de"
                    },
                    {
                      "label": {
                        "en_US": "Greek",
                        "zh_Hans": "希腊语"
                      },
                      "value": "el"
                    },
                    {
                      "label": {
                        "en_US": "Hebrew",
                        "zh_Hans": "希伯来语"
                      },
                      "value": "iw"
                    },
                    {
                      "label": {
                        "en_US": "Hindi",
                        "zh_Hans": "印地语"
                      },
                      "value": "hi"
                    },
                    {
                      "label": {
                        "en_US": "Hungarian",
                        "zh_Hans": "匈牙利语"
                      },
                      "value": "hu"
                    },
                    {
                      "label": {
                        "en_US": "Indonesian",
                        "zh_Hans": "印尼语"
                      },
                      "value": "id"
                    },
                    {
                      "label": {
                        "en_US": "Italian",
                        "zh_Hans": "意大利语"
                      },
                      "value": "it"
                    },
                    {
                      "label": {
                        "en_US": "Japanese",
                        "zh_Hans": "日语"
                      },
                      "value": "ja"
                    },
                    {
                      "label": {
                        "en_US": "Kannada",
                        "zh_Hans": "卡纳达语"
                      },
                      "value": "kn"
                    },
                    {
                      "label": {
                        "en_US": "Korean",
                        "zh_Hans": "韩语"
                      },
                      "value": "ko"
                    },
                    {
                      "label": {
                        "en_US": "Latvian",
                        "zh_Hans": "拉脱维亚语"
                      },
                      "value": "lv"
                    },
                    {
                      "label": {
                        "en_US": "Lithuanian",
                        "zh_Hans": "立陶宛语"
                      },
                      "value": "lt"
                    },
                    {
                      "label": {
                        "en_US": "Malay",
                        "zh_Hans": "马来语"
                      },
                      "value": "my"
                    },
                    {
                      "label": {
                        "en_US": "Malayalam",
                        "zh_Hans": "马拉雅拉姆语"
                      },
                      "value": "ml"
                    },
                    {
                      "label": {
                        "en_US": "Marathi",
                        "zh_Hans": "马拉地语"
                      },
                      "value": "mr"
                    },
                    {
                      "label": {
                        "en_US": "Norwegian",
                        "zh_Hans": "挪威语"
                      },
                      "value": "no"
                    },
                    {
                      "label": {
                        "en_US": "Polish",
                        "zh_Hans": "波兰语"
                      },
                      "value": "pl"
                    },
                    {
                      "label": {
                        "en_US": "Portuguese (Brazil)",
                        "zh_Hans": "葡萄牙语（巴西）"
                      },
                      "value": "pt-br"
                    },
                    {
                      "label": {
                        "en_US": "Portuguese (Portugal)",
                        "zh_Hans": "葡萄牙语（葡萄牙）"
                      },
                      "value": "pt-pt"
                    },
                    {
                      "label": {
                        "en_US": "Punjabi",
                        "zh_Hans": "旁遮普语"
                      },
                      "value": "pa"
                    },
                    {
                      "label": {
                        "en_US": "Romanian",
                        "zh_Hans": "罗马尼亚语"
                      },
                      "value": "ro"
                    },
                    {
                      "label": {
                        "en_US": "Russian",
                        "zh_Hans": "俄语"
                      },
                      "value": "ru"
                    },
                    {
                      "label": {
                        "en_US": "Serbian",
                        "zh_Hans": "塞尔维亚语"
                      },
                      "value": "sr"
                    },
                    {
                      "label": {
                        "en_US": "Slovak",
                        "zh_Hans": "斯洛伐克语"
                      },
                      "value": "sk"
                    },
                    {
                      "label": {
                        "en_US": "Slovenian",
                        "zh_Hans": "斯洛文尼亚语"
                      },
                      "value": "sl"
                    },
                    {
                      "label": {
                        "en_US": "Spanish",
                        "zh_Hans": "西班牙语"
                      },
                      "value": "es"
                    },
                    {
                      "label": {
                        "en_US": "Swedish",
                        "zh_Hans": "瑞典语"
                      },
                      "value": "sv"
                    },
                    {
                      "label": {
                        "en_US": "Tamil",
                        "zh_Hans": "泰米尔语"
                      },
                      "value": "ta"
                    },
                    {
                      "label": {
                        "en_US": "Telugu",
                        "zh_Hans": "泰卢固语"
                      },
                      "value": "te"
                    },
                    {
                      "label": {
                        "en_US": "Thai",
                        "zh_Hans": "泰语"
                      },
                      "value": "th"
                    },
                    {
                      "label": {
                        "en_US": "Turkish",
                        "zh_Hans": "土耳其语"
                      },
                      "value": "tr"
                    },
                    {
                      "label": {
                        "en_US": "Ukrainian",
                        "zh_Hans": "乌克兰语"
                      },
                      "value": "uk"
                    },
                    {
                      "label": {
                        "en_US": "Vietnamese",
                        "zh_Hans": "越南语"
                      },
                      "value": "vi"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:09:44Z",
        "version_updated_at": "2025-02-17T07:09:44Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "store and access conversations",
          "ja_JP": "会話を保存してアクセスする",
          "pt_BR": "armazenar e acessar conversas",
          "zh_Hans": "存储和访问会话"
        },
        "category": "tool",
        "created_at": "2025-03-28T21:36:07Z",
        "endpoint": {},
        "icon": "alterxyz/packages/data_function_conversation_memory/_assets/book-solid.svg",
        "index_id": "alterxyz___data_function_conversation_memory",
        "install_count": 821,
        "introduction": "## Conversation Memory\n\nBrings memory to any nodes.\n\nYou will need a Cloudflare account to use this function.\n\n![DEMO](_assets/screenshot1.png)\n\n## Roadmap\n\n- [x] Add memory to any node\n- [ ] Allow retry and edit feature\n- [ ] Deeper integration to Dify\n- [ ] Allow other storage options\n- [ ] \"Project\" - long term memory for agentic AI\n\n## Beta\n\nYou can also install beta version by using this GitHub URL:\n\n```plaintext\nhttps://github.com/alterxyz/dify-plugin-conversation-memory\n```\n\n## Issues\n\nPlease report any issues to the [GitHub repository](https://github.com/alterxyz/dify-plugin-conversation-memory/issues/new/choose).\n",
        "label": {
          "en_US": "Conversational Memory",
          "ja_JP": "会話メモリ",
          "pt_BR": "Memória Conversacional",
          "zh_Hans": "会话记忆"
        },
        "latest_package_identifier": "alterxyz/data_function_conversation_memory:0.0.4@70766901c6688b05f35e9ac1436591a2a9b0cff656c1d45bb45599f8fbce503f",
        "latest_version": "0.0.4",
        "model": {},
        "name": "data_function_conversation_memory",
        "org": "alterxyz",
        "plugin_id": "alterxyz/data_function_conversation_memory",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/data_function_conversation_memory.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "endpoint": {
              "enabled": true
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "alterxyz",
            "description": {
              "en_US": "store and access conversations",
              "ja_JP": "会話を保存してアクセスする",
              "pt_BR": "armazenar e acessar conversas",
              "zh_Hans": "存储和访问会话"
            },
            "icon": "book-solid.svg",
            "label": {
              "en_US": "Conversational Memory",
              "ja_JP": "会話メモリ",
              "pt_BR": "Memória Conversacional",
              "zh_Hans": "会话记忆"
            },
            "name": "data_function_conversation_memory",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Initialize Database at Cloudflare D1 that create tables such as Conversation and Message",
                  "pt_BR": "Inicializar Banco de Dados no Cloudflare D1 que cria tabelas como Conversation e Message",
                  "zh_Hans": "在 Cloudflare D1 初始化数据库，创建 Conversation 和 Message 等表"
                },
                "llm": "Initialize Database at Cloudflare D1 that create tables such as Conversation and Message. Normally, this function is called only once."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "alterxyz",
                "label": {
                  "en_US": "Initialize Memory Base at Cloudflare D1",
                  "pt_BR": "Inicializar Memória Base no Cloudflare D1",
                  "zh_Hans": "初始化记忆库 - Cloudflare D1"
                },
                "name": "memory_init_cloudflare_d1"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Cloudflare Account ID",
                    "pt_BR": "ID da Conta Cloudflare",
                    "zh_Hans": "Cloudflare 账户 ID"
                  },
                  "label": {
                    "en_US": "Cloudflare Account ID",
                    "pt_BR": "ID da Conta Cloudflare",
                    "zh_Hans": "Cloudflare 账户 ID"
                  },
                  "llm_description": "Cloudflare Account ID, normally it is provided by Human.",
                  "max": null,
                  "min": null,
                  "name": "cloudflare_account_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Cloudflare Database ID",
                    "pt_BR": "ID do Banco de Dados Cloudflare",
                    "zh_Hans": "Cloudflare 数据库 ID"
                  },
                  "label": {
                    "en_US": "Cloudflare Database ID",
                    "pt_BR": "ID do Banco de Dados Cloudflare",
                    "zh_Hans": "Cloudflare 数据库 ID"
                  },
                  "llm_description": "Cloudflare Database ID, normally it is provided by Human.",
                  "max": null,
                  "min": null,
                  "name": "cloudflare_d1_database_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Cloudflare API Token with D1 permissions",
                    "pt_BR": "Token de API Cloudflare com permissões D1",
                    "zh_Hans": "具有 D1 权限的 Cloudflare API 令牌"
                  },
                  "label": {
                    "en_US": "Cloudflare API Token",
                    "pt_BR": "Token de API Cloudflare",
                    "zh_Hans": "Cloudflare API 令牌"
                  },
                  "llm_description": "Cloudflare API Token with D1 permissions, normally it is provided by Human.",
                  "max": null,
                  "min": null,
                  "name": "cloudflare_api_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Retrieve conversation history from the conversation memory database in XML format",
                  "pt_BR": "Recuperar histórico de conversa do banco de dados de memória de conversação em formato XML",
                  "zh_Hans": "从对话记忆数据库中以XML格式获取会话历史"
                },
                "llm": "Retrieve conversation history from the conversation memory database at Cloudflare D1 in XML format."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "alterxyz",
                "label": {
                  "en_US": "Load Conversation",
                  "pt_BR": "Carregar Conversa",
                  "zh_Hans": "加载对话"
                },
                "name": "get_conversation"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Cloudflare Account ID",
                    "pt_BR": "ID da Conta Cloudflare",
                    "zh_Hans": "Cloudflare 账户 ID"
                  },
                  "label": {
                    "en_US": "Cloudflare Account ID",
                    "pt_BR": "ID da Conta Cloudflare",
                    "zh_Hans": "Cloudflare 账户 ID"
                  },
                  "llm_description": "Cloudflare Account ID, normally it is provided by Human.",
                  "max": null,
                  "min": null,
                  "name": "cloudflare_account_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Cloudflare Database ID",
                    "pt_BR": "ID do Banco de Dados Cloudflare",
                    "zh_Hans": "Cloudflare 数据库 ID"
                  },
                  "label": {
                    "en_US": "Cloudflare Database ID",
                    "pt_BR": "ID do Banco de Dados Cloudflare",
                    "zh_Hans": "Cloudflare 数据库 ID"
                  },
                  "llm_description": "Cloudflare Database ID, normally it is provided by Human.",
                  "max": null,
                  "min": null,
                  "name": "cloudflare_d1_database_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Cloudflare API Token with D1 permissions",
                    "pt_BR": "Token de API Cloudflare com permissões D1",
                    "zh_Hans": "具有 D1 权限的 Cloudflare API 令牌"
                  },
                  "label": {
                    "en_US": "Cloudflare API Token",
                    "pt_BR": "Token de API Cloudflare",
                    "zh_Hans": "Cloudflare API 令牌"
                  },
                  "llm_description": "Cloudflare API Token with D1 permissions, normally it is provided by Human.",
                  "max": null,
                  "min": null,
                  "name": "cloudflare_api_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The unique identifier of the conversation to retrieve",
                    "zh_Hans": "要获取的对话的唯一标识符"
                  },
                  "label": {
                    "en_US": "Conversation ID",
                    "zh_Hans": "对话 ID"
                  },
                  "llm_description": "The unique identifier of the conversation to retrieve",
                  "max": null,
                  "min": null,
                  "name": "conversation_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 50,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Maximum number of message rounds to return (default 50)",
                    "zh_Hans": "返回的最大消息轮数（默认为 50）"
                  },
                  "label": {
                    "en_US": "Maximum Message Rounds",
                    "zh_Hans": "最大消息轮数"
                  },
                  "llm_description": "Maximum number of message rounds to return. Default is 50 if not specified.",
                  "max": null,
                  "min": null,
                  "name": "max_round",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional user input to append to conversation",
                    "zh_Hans": "可选的用户输入，将添加到对话末尾"
                  },
                  "label": {
                    "en_US": "User Input",
                    "zh_Hans": "用户输入"
                  },
                  "llm_description": "Optional user input text to append to the end of the conversation as a new message",
                  "max": null,
                  "min": null,
                  "name": "user_input",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "xml",
                  "form": "form",
                  "human_description": {
                    "en_US": "Choose the format of conversation output (XML or JSON)",
                    "zh_Hans": "选择对话输出格式（XML或JSON）"
                  },
                  "label": {
                    "en_US": "Output Format",
                    "zh_Hans": "输出格式"
                  },
                  "llm_description": "The format of conversation output, can be 'xml' or 'json'",
                  "max": null,
                  "min": null,
                  "name": "format",
                  "options": [
                    {
                      "label": {
                        "en_US": "XML Format",
                        "zh_Hans": "XML格式"
                      },
                      "value": "xml"
                    },
                    {
                      "label": {
                        "en_US": "JSON Format",
                        "zh_Hans": "JSON格式"
                      },
                      "value": "json"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Store a message with specific role into the conversation memory database",
                  "pt_BR": "Armazenar uma mensagem com função específica no banco de dados de memória de conversação",
                  "zh_Hans": "将特定角色的消息存储到对话记忆数据库中"
                },
                "llm": "Store a message with specific role (human or assistant) into the conversation memory database at Cloudflare D1."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "alterxyz",
                "label": {
                  "en_US": "Store Message",
                  "pt_BR": "Armazenar Mensagem",
                  "zh_Hans": "存储消息"
                },
                "name": "put_message"
              },
              "output_schema": {
                "properties": {
                  "conversation_id": {
                    "description": "The unique identifier of the conversation",
                    "type": "string"
                  },
                  "message_id": {
                    "description": "The unique identifier of the message",
                    "type": "string"
                  }
                },
                "type": "object"
              },
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Cloudflare Account ID",
                    "pt_BR": "ID da Conta Cloudflare",
                    "zh_Hans": "Cloudflare 账户 ID"
                  },
                  "label": {
                    "en_US": "Cloudflare Account ID",
                    "pt_BR": "ID da Conta Cloudflare",
                    "zh_Hans": "Cloudflare 账户 ID"
                  },
                  "llm_description": "Cloudflare Account ID, normally it is provided by Human.",
                  "max": null,
                  "min": null,
                  "name": "cloudflare_account_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Cloudflare Database ID",
                    "pt_BR": "ID do Banco de Dados Cloudflare",
                    "zh_Hans": "Cloudflare 数据库 ID"
                  },
                  "label": {
                    "en_US": "Cloudflare Database ID",
                    "pt_BR": "ID do Banco de Dados Cloudflare",
                    "zh_Hans": "Cloudflare 数据库 ID"
                  },
                  "llm_description": "Cloudflare Database ID, normally it is provided by Human.",
                  "max": null,
                  "min": null,
                  "name": "cloudflare_d1_database_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Cloudflare API Token with D1 permissions",
                    "pt_BR": "Token de API Cloudflare com permissões D1",
                    "zh_Hans": "具有 D1 权限的 Cloudflare API 令牌"
                  },
                  "label": {
                    "en_US": "Cloudflare API Token",
                    "pt_BR": "Token de API Cloudflare",
                    "zh_Hans": "Cloudflare API 令牌"
                  },
                  "llm_description": "Cloudflare API Token with D1 permissions, normally it is provided by Human.",
                  "max": null,
                  "min": null,
                  "name": "cloudflare_api_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The role of the message, can be human or assistant",
                    "zh_Hans": "消息的角色，可以是human或assistant"
                  },
                  "label": {
                    "en_US": "role",
                    "zh_Hans": "角色"
                  },
                  "llm_description": "The role of the message, can be human or assistant",
                  "max": null,
                  "min": null,
                  "name": "role",
                  "options": [
                    {
                      "label": {
                        "en_US": "user",
                        "zh_Hans": "user / 用户"
                      },
                      "value": "user"
                    },
                    {
                      "label": {
                        "en_US": "assistant / AI",
                        "zh_Hans": "assistant / AI"
                      },
                      "value": "assistant"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The text content of the message",
                    "pt_BR": "O conteúdo de texto da mensagem",
                    "zh_Hans": "消息的文本内容"
                  },
                  "label": {
                    "en_US": "Message Text",
                    "pt_BR": "Texto da Mensagem",
                    "zh_Hans": "消息文本"
                  },
                  "llm_description": "The text content of the message to be stored in the database.",
                  "max": null,
                  "min": null,
                  "name": "text",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The unique identifier of the conversation to store the message",
                    "zh_Hans": "要存储消息的对话的唯一标识符"
                  },
                  "label": {
                    "en_US": "Conversation ID",
                    "zh_Hans": "对话 ID"
                  },
                  "llm_description": "The unique identifier of the conversation to store the message",
                  "max": null,
                  "min": null,
                  "name": "conversation_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-18T19:27:43Z",
        "version_updated_at": "2025-04-18T19:27:43Z"
      },
      {
        "agent_strategy": null,
        "badges": [],
        "brief": {
          "en_US": "Neko is a cute cat.",
          "zh_Hans": "这是一只可爱的小猫。"
        },
        "category": "extension",
        "created_at": "2024-11-22T08:07:10Z",
        "endpoint": {
          "endpoints": [
            {
              "method": "GET",
              "path": "/duck/<app_id>"
            },
            {
              "method": "GET",
              "path": "/neko"
            }
          ],
          "settings": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "API key",
                "pt_BR": "API key",
                "zh_Hans": "API key"
              },
              "name": "api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your API key",
                "pt_BR": "Please input your API key",
                "zh_Hans": "请输入你的 API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            }
          ]
        },
        "icon": "langgenius/packages/neko/_assets/neko.gif",
        "index_id": "langgenius___neko",
        "install_count": 810,
        "introduction": "# Neko Plugin\n\nThis is an example of Dify Endpoint Plugin.",
        "label": {
          "en_US": "Neko"
        },
        "latest_package_identifier": "langgenius/neko:0.0.2@2adb9952e0f63b489ef8bf4b14c8c80c6621b5b5592787c57243ef94d6fd4b28",
        "latest_version": "0.0.2",
        "model": {},
        "name": "neko",
        "org": "langgenius",
        "plugin_id": "langgenius/neko",
        "plugins": {
          "endpoints": [
            "provider/neko.yaml"
          ],
          "models": null,
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "other"
          }
        ],
        "tool": {},
        "type": "plugin",
        "updated_at": "2024-11-22T08:07:15Z",
        "version_updated_at": "2024-11-22T08:07:15Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "PPIO is a cloud infrastructure provider offering a wide range of AI model services.",
          "zh_Hans": "PPIO 提供满血版 DeepSeek R1/V3 模型，以及 Qwen、Llama、Yi 等一系列模型。"
        },
        "category": "model",
        "created_at": "2025-02-28T07:39:42Z",
        "endpoint": {},
        "icon": "cnjasonz/packages/ppio/_assets/icon_s_en.svg",
        "index_id": "cnjasonz___ppio",
        "install_count": 793,
        "introduction": "# 总览\n\nPPIO 派欧云提供稳定、高性价比的开源模型 API 服务，支持 DeepSeek 全系列、Llama、Qwen 等行业领先大模型。\n\n# 配置\n\n安装插件后，进入设置页面，输入您的 API Key。从 [这里](https://ppinfra.com/settings/key-management) 创建您的 API Key 并保存。新注册用户赠送 ￥5 元代金券。\n\n![](_assets/ppio-01.png)\n\n",
        "label": {
          "en_US": "PPIO",
          "zh_Hans": "PPIO 派欧云"
        },
        "latest_package_identifier": "cnjasonz/ppio:0.0.1@a86313a2367d2e162edf10c34f035d4f13efea6d78f40119438eadb0633d6eeb",
        "latest_version": "0.0.1",
        "model": {
          "background": "#b5cefc",
          "configurate_methods": [
            "predefined-model"
          ],
          "description": {
            "en_US": "PPIO is a cloud infrastructure provider offering a wide range of AI model services.",
            "zh_Hans": "PPIO 提供满血版 DeepSeek R1/V3 模型，以及 Qwen、Llama、Yi 等一系列模型。"
          },
          "help": {
            "title": {
              "en_US": "Get your API key from PPIO",
              "zh_Hans": "从 PPIO 获取 API Key"
            },
            "url": {
              "en_US": "https://ppinfra.com/settings/key-management?utm_source=github_dify&utm_medium=github_readme&utm_campaign=link"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.svg",
            "zh_Hans": "icon_l_zh.svg"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "PPIO",
            "zh_Hans": "PPIO 派欧云"
          },
          "model_credential_schema": null,
          "models": [
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "baichuan/baichuan2-13b-chat",
                "zh_Hans": "baichuan/baichuan2-13b-chat"
              },
              "model": "baichuan/baichuan2-13b-chat",
              "model_properties": {
                "context_size": 14336,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "CNY",
                "input": "0.0175",
                "output": "0.0175",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "DeepSeek: DeepSeek R1（Community）",
                "zh_Hans": "DeepSeek: DeepSeek R1（Community）"
              },
              "model": "deepseek/deepseek-r1/community",
              "model_properties": {
                "context_size": 64000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "CNY",
                "input": "0.04",
                "output": "0.16",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "DeepSeek R1 Distill Llama 70B",
                "zh_Hans": "DeepSeek R1 Distill Llama 70B"
              },
              "model": "deepseek/deepseek-r1-distill-llama-70b",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "CNY",
                "input": "0.058",
                "output": "0.058",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "DeepSeek: DeepSeek R1 Distill Llama 8B",
                "zh_Hans": "DeepSeek: DeepSeek R1 Distill Llama 8B"
              },
              "model": "deepseek/deepseek-r1-distill-llama-8b",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "CNY",
                "input": "0.003",
                "output": "0.003",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "DeepSeek: DeepSeek R1 Distill Qwen 14B",
                "zh_Hans": "DeepSeek: DeepSeek R1 Distill Qwen 14B"
              },
              "model": "deepseek/deepseek-r1-distill-qwen-14b",
              "model_properties": {
                "context_size": 64000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "CNY",
                "input": "0.01",
                "output": "0.01",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "DeepSeek: DeepSeek R1 Distill Qwen 32B",
                "zh_Hans": "DeepSeek: DeepSeek R1 Distill Qwen 32B"
              },
              "model": "deepseek/deepseek-r1-distill-qwen-32b",
              "model_properties": {
                "context_size": 64000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "CNY",
                "input": "0.0218",
                "output": "0.0218",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "DeepSeek R1",
                "zh_Hans": "DeepSeek R1"
              },
              "model": "deepseek/deepseek-r1",
              "model_properties": {
                "context_size": 64000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "CNY",
                "input": "0.04",
                "output": "0.16",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "DeepSeek: DeepSeek V3（Community）",
                "zh_Hans": "DeepSeek: DeepSeek V3（Community）"
              },
              "model": "deepseek/deepseek-v3/community",
              "model_properties": {
                "context_size": 64000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "CNY",
                "input": "0.01",
                "output": "0.02",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "DeepSeek V3",
                "zh_Hans": "DeepSeek V3"
              },
              "model": "deepseek/deepseek-v3",
              "model_properties": {
                "context_size": 64000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "CNY",
                "input": "0.01",
                "output": "0.02",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "thudm/glm-4-9b-chat",
                "zh_Hans": "thudm/glm-4-9b-chat"
              },
              "model": "thudm/glm-4-9b-chat",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "CNY",
                "input": "0.005",
                "output": "0.005",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "meta-llama/llama-3.1-70b-instruct",
                "zh_Hans": "meta-llama/llama-3.1-70b-instruct"
              },
              "model": "meta-llama/llama-3.1-70b-instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "CNY",
                "input": "0.0245",
                "output": "0.0282",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "meta-llama/llama-3.1-8b-instruct",
                "zh_Hans": "meta-llama/llama-3.1-8b-instruct"
              },
              "model": "meta-llama/llama-3.1-8b-instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "CNY",
                "input": "0.004",
                "output": "0.004",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "meta-llama/llama-3.2-3b-instruct",
                "zh_Hans": "meta-llama/llama-3.2-3b-instruct"
              },
              "model": "meta-llama/llama-3.2-3b-instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "CNY",
                "input": "0.00216",
                "output": "0.0036",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen/qwen-2-7b-instruct",
                "zh_Hans": "qwen/qwen-2-7b-instruct"
              },
              "model": "qwen/qwen-2-7b-instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "CNY",
                "input": "0.0032",
                "output": "0.0032",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen/qwen-2-vl-72b-instruct",
                "zh_Hans": "qwen/qwen-2-vl-72b-instruct"
              },
              "model": "qwen/qwen-2-vl-72b-instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "CNY",
                "input": "0.045",
                "output": "0.045",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen/qwen-2.5-72b-instruct",
                "zh_Hans": "qwen/qwen-2.5-72b-instruct"
              },
              "model": "qwen/qwen-2.5-72b-instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "CNY",
                "input": "0.0275",
                "output": "0.0288",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen/qwen2.5-32b-instruct",
                "zh_Hans": "qwen/qwen2.5-32b-instruct"
              },
              "model": "qwen/qwen2.5-32b-instruct",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "CNY",
                "input": "0.0126",
                "output": "0.0126",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "01-ai/yi-1.5-34b-chat",
                "zh_Hans": "01-ai/yi-1.5-34b-chat"
              },
              "model": "01-ai/yi-1.5-34b-chat",
              "model_properties": {
                "context_size": 16384,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "CNY",
                "input": "0.011",
                "output": "0.011",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "01-ai/yi-1.5-9b-chat",
                "zh_Hans": "01-ai/yi-1.5-9b-chat"
              },
              "model": "01-ai/yi-1.5-9b-chat",
              "model_properties": {
                "context_size": 16384,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "CNY",
                "input": "0.004",
                "output": "0.004",
                "unit": "0.0001"
              }
            }
          ],
          "position": {
            "llm": [
              "deepseek/deepseek-r1/community",
              "deepseek/deepseek-v3/community",
              "deepseek/deepseek-r1",
              "deepseek/deepseek-v3",
              "deepseek/deepseek-r1-distill-llama-70b",
              "deepseek/deepseek-r1-distill-qwen-32b",
              "deepseek/deepseek-r1-distill-qwen-14b",
              "deepseek/deepseek-r1-distill-llama-8b",
              "qwen/qwen-2.5-72b-instruct",
              "qwen/qwen-2-vl-72b-instruct",
              "qwen/qwen2.5-32b-instruct",
              "qwen/qwen-2-7b-instruct",
              "meta-llama/llama-3.2-3b-instruct",
              "meta-llama/llama-3.1-70b-instruct",
              "meta-llama/llama-3.1-8b-instruct",
              "baichuan/baichuan2-13b-chat",
              "01-ai/yi-1.5-34b-chat",
              "01-ai/yi-1.5-9b-chat",
              "thudm/glm-4-9b-chat"
            ]
          },
          "provider": "ppio",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key",
                  "zh_Hans": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Please input your  API Key",
                  "zh_Hans": "请输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              }
            ]
          },
          "supported_model_types": [
            "llm"
          ]
        },
        "name": "ppio",
        "org": "cnjasonz",
        "plugin_id": "cnjasonz/ppio",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/ppio.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "https://ppinfra.com/legal/privacy-policy",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-02-28T07:39:50Z",
        "version_updated_at": "2025-02-28T07:39:50Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "The Tianditu tool provided the functions of place name search, geocoding, static maps generation, etc. in China region.",
          "pt_BR": "The Tianditu tool provided the functions of place name search, geocoding, static maps generation, etc. in China region.",
          "zh_Hans": "天地图工具可以调用天地图的接口，实现中国区域内的地名搜索、地理编码、静态地图等功能。"
        },
        "category": "tool",
        "created_at": "2024-12-02T05:34:38Z",
        "endpoint": {},
        "icon": "langgenius/packages/tianditu/_assets/icon.svg",
        "index_id": "langgenius___tianditu",
        "install_count": 777,
        "introduction": "# Overview\nThe Tianditu plugin provides seamless integration with Tianditu (天地图), China's national map service platform. \n\nThis plugin enables users to access various geospatial tools for location-based services, including address-to-coordinate conversion, point-of-interest (POI) searches, and static map generation.\n\n# Configure\n1. Install the Plugin\n2. Go to the Dify Marketplace.\n3. Search for the Tianditu Plugin.\n4. Click \"Install\" to add the plugin to your workspace.\n![](./_assets/tianditu_install.PNG)\n5. Register for a Tianditu API Key\n6. Visit [Tianditu Registration Page](https://passport.tianditu.gov.cn/register) and create an account.\n7. After registering, log in to [Tianditu API Management](http://lbs.tianditu.gov.cn/home.html).\n8. Generate an API Key to use with the plugin.\n9. Authorize the Plugin\n\nBefore using the tools, you need to authorize the plugin with your Tianditu API Key:\n1. In your workflow, add any of the Tianditu tools (e.g., \"Get Coords Converted from Address Name\").\n2. Click on the \"To authorize\" button in the tool configuration panel.\n3. Enter your Tianditu API Key.\n4. Save your credentials to complete the authorization process.\n5. Configure Input Variables\nEach tool requires specific input variables:\n## Get Coords Converted from Address Name\n- Address Name (Required): The address you want to convert into geographic coordinates.\n![](./_assets/tianditu_get_coords.PNG)\n\n## Point of Interest Search\n- poi keyword (String, Required): The keyword for the type of POI you want to search for (e.g., \"restaurant,\" \"hotel,\" \"park\").\n- base current point (String, Required): The base location for the search in the format `latitude,longitude` (e.g., `39.9,116.4` for Beijing).\n![](./_assets/tianditu_point_of_interest.PNG)\n\n## Generate a Static Map\n- keyword (String, required)\n\n![](./_assets/tianditu_static_map.PNG)",
        "label": {
          "en_US": "Tianditu",
          "pt_BR": "Tianditu",
          "zh_Hans": "天地图"
        },
        "latest_package_identifier": "langgenius/tianditu:0.0.2@5ed963120bf2395db2e2db9d920ae1c99762f44496d0b87533a34e89585224b1",
        "latest_version": "0.0.2",
        "model": {},
        "name": "tianditu",
        "org": "langgenius",
        "plugin_id": "langgenius/tianditu",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/tianditu.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "utilities"
          },
          {
            "name": "travel"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "Tianditu API Key",
                "pt_BR": "Tianditu API key",
                "zh_Hans": "天地图Key"
              },
              "name": "tianditu_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Tianditu API key",
                "pt_BR": "Please input your Tianditu API key",
                "zh_Hans": "请输入你的天地图Key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "http://lbs.tianditu.gov.cn/home.html"
            }
          ],
          "identity": {
            "author": "Listeng",
            "description": {
              "en_US": "The Tianditu tool provided the functions of place name search, geocoding, static maps generation, etc. in China region.",
              "pt_BR": "The Tianditu tool provided the functions of place name search, geocoding, static maps generation, etc. in China region.",
              "zh_Hans": "天地图工具可以调用天地图的接口，实现中国区域内的地名搜索、地理编码、静态地图等功能。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Tianditu",
              "pt_BR": "Tianditu",
              "zh_Hans": "天地图"
            },
            "name": "tianditu",
            "tags": [
              "utilities",
              "travel"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Generate a static map",
                  "pt_BR": "Generate a static map",
                  "zh_Hans": "生成静态地图"
                },
                "llm": "A tool for generate a static map"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Listeng",
                "label": {
                  "en_US": "Generate a static map",
                  "pt_BR": "Generate a static map",
                  "zh_Hans": "生成静态地图"
                },
                "name": "generate_static_map"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "keyword",
                    "pt_BR": "keyword",
                    "zh_Hans": "搜索的关键字"
                  },
                  "label": {
                    "en_US": "keyword",
                    "pt_BR": "keyword",
                    "zh_Hans": "搜索的关键字"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "keyword",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Geocoder",
                  "pt_BR": "Geocoder",
                  "zh_Hans": "中国区域地理编码查询"
                },
                "llm": "A tool for geocoder in China"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Listeng",
                "label": {
                  "en_US": "Get coords converted from address name",
                  "pt_BR": "Get coords converted from address name",
                  "zh_Hans": "地理编码"
                },
                "name": "geocoder"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "keyword",
                    "pt_BR": "keyword",
                    "zh_Hans": "搜索的关键字"
                  },
                  "label": {
                    "en_US": "keyword",
                    "pt_BR": "keyword",
                    "zh_Hans": "搜索的关键字"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "keyword",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Search for certain types of points of interest around a location",
                  "pt_BR": "Search for certain types of points of interest around a location",
                  "zh_Hans": "搜索某个位置周边的5公里内某种类型的兴趣点"
                },
                "llm": "A tool for searching for certain types of points of interest around a location"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Listeng",
                "label": {
                  "en_US": "Point of Interest search",
                  "pt_BR": "Point of Interest search",
                  "zh_Hans": "兴趣点搜索"
                },
                "name": "point_of_interest_search"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "poi keyword",
                    "pt_BR": "poi keyword",
                    "zh_Hans": "兴趣点的关键字"
                  },
                  "label": {
                    "en_US": "poi keyword",
                    "pt_BR": "poi keyword",
                    "zh_Hans": "兴趣点的关键字"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "keyword",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "base current point",
                    "pt_BR": "base current point",
                    "zh_Hans": "当前位置的关键字"
                  },
                  "label": {
                    "en_US": "base current point",
                    "pt_BR": "base current point",
                    "zh_Hans": "当前位置的关键字"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "baseAddress",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:17:33Z",
        "version_updated_at": "2025-02-17T07:17:33Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Replicate"
        },
        "category": "model",
        "created_at": "2024-12-05T08:52:57Z",
        "endpoint": {},
        "icon": "langgenius/packages/replicate/_assets/icon_s_en.svg",
        "index_id": "langgenius___replicate",
        "install_count": 766,
        "introduction": "# Overview\nReplicate is a cloud-based platform designed to simplify the deployment and scaling of machine learning models. It provides users with access to a vast library of open-source AI models, enabling developers to run and fine-tune these models with minimal coding effort. The platform aims to democratize machine learning by making it accessible to a broader audience, including software engineers, data scientists, and product managers.\n\nDify supports accessing [Language models](https://replicate.com/collections/language-models) and [Embedding models](https://replicate.com/collections/embedding-models) on Replicate. Language models correspond to Dify's reasoning model, and Embedding models correspond to Dify's Embedding model.\n\n# Configure\n1. You need to have a [Replicate account](https://replicate.com/signin?next=/docs).\n2. [Get API Key](https://replicate.com/signin?next=/docs).\n3. Pick a model. Select the model under [Language models](https://replicate.com/collections/language-models) and [Embedding models](https://replicate.com/collections/embedding-models).\n4. Add models in Dify's Settings -> Model Provider -> Replicate.\n\n![](_assets/create_replicate_model.png)\n\nThe API key is the API Key set in step 2. Model Name and Model Version can be found on the model details page:\n\n![](_assets/api_key.png)",
        "label": {
          "en_US": "Replicate"
        },
        "latest_package_identifier": "langgenius/replicate:0.0.3@29d878cbb3fe1140bf994eb8efc8070a1210c4cbb3a4ccb76345bfb2f0be08c3",
        "latest_version": "0.0.3",
        "model": {
          "background": "#E5E7EB",
          "configurate_methods": [
            "customizable-model"
          ],
          "description": {
            "en_US": "Replicate"
          },
          "help": {
            "title": {
              "en_US": "Get your API Key from Replicate",
              "zh_Hans": "从 Replicate 获取 API Key"
            },
            "url": {
              "en_US": "https://replicate.com/account/api-tokens"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.svg"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "Replicate"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Replicate API Key",
                  "zh_Hans": "在此输入您的 Replicate API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "replicate_api_token"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Model Version"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your model version, default to the latest version",
                  "zh_Hans": "在此输入您的模型版本，默认为最新版本"
                },
                "required": false,
                "show_on": [],
                "type": "text-input",
                "variable": "model_version"
              }
            ],
            "model": {
              "label": {
                "en_US": "Model Name",
                "zh_Hans": "模型名称"
              },
              "placeholder": null
            }
          },
          "models": [],
          "provider": "replicate",
          "provider_credential_schema": null,
          "supported_model_types": [
            "llm",
            "text-embedding"
          ]
        },
        "name": "replicate",
        "org": "langgenius",
        "plugin_id": "langgenius/replicate",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/replicate.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": false,
              "llm": false,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-02-28T03:52:50Z",
        "version_updated_at": "2025-02-28T03:52:50Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Line Bot",
          "ja_JP": "Line Bot",
          "pt_BR": "Line Bot",
          "zh_Hans": "Line Bot"
        },
        "category": "extension",
        "created_at": "2025-03-13T16:20:03Z",
        "endpoint": {
          "endpoints": [
            {
              "hidden": false,
              "method": "POST",
              "path": "/"
            }
          ],
          "settings": [
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Channel Secret",
                "ja_JP": "チャンネルシークレット",
                "pt_BR": "Segredo do Canal",
                "zh_Hans": "频道密钥"
              },
              "name": "channel_secret",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Channel Secret",
                "ja_JP": "チャネルシークレットを入力してください",
                "pt_BR": "Por favor, insira seu Segredo do Canal",
                "zh_Hans": "请输入你的频道密钥"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Channel Access Token",
                "ja_JP": "チャネルアクセストークン",
                "pt_BR": "Token de Acesso do Canal",
                "zh_Hans": "频道访问令牌"
              },
              "name": "channel_access_token",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Channel Access Token",
                "ja_JP": "チャネルアクセストークンを入力してください",
                "pt_BR": "Por favor, insira seu Token de Acesso do Canal",
                "zh_Hans": "请输入你的频道访问令牌"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "App",
                "ja_JP": "アプリ",
                "pt_BR": "App",
                "zh_Hans": "应用"
              },
              "name": "app",
              "options": null,
              "placeholder": {
                "en_US": "the app you want to use to answer Line messages",
                "ja_JP": "あなたが Line メッセージに回答するために使用するアプリ",
                "pt_BR": "o app que você deseja usar para responder mensagens do Line",
                "zh_Hans": "你想要用来回答 Line 消息的应用"
              },
              "required": true,
              "scope": null,
              "type": "app-selector",
              "url": null
            }
          ]
        },
        "icon": "kevintsai/packages/linebot/_assets/LINE_Brand_icon.png",
        "index_id": "kevintsai___linebot",
        "install_count": 749,
        "introduction": "# Line Bot Plugin Integration Guide\nAuthor: @kevintsai1202 (https://github.com/kevintsai1202/difyplugin.git)\nVersion: 0.0.3\nType: extension\n\n## What's Changed\n  Bug fixed\n\n## Plugin Overview\nThe Line Bot plugin integrates the Dify chat workflow application with the Line Official Account Messaging API. It enables users to interact with AI through a Line Official Account. The plugin only processes message reception and responses; it does not store any user information.\n\n## Setup Steps\nFollow these steps to install and configure the Line Bot plugin:\n1. Create a Provider and Messaging API Channel\n  Go to the [LINE Developers](https://developers.line.biz) website。 \n  <img src=\"./_assets/2025-03-10 20 34 06.png\" width=\"600\" />\n\n2. Copy the Channel Secret and Channel Access Token of the Messaging API\n  - Navigate to the Basic settings page.\n  - Copy the Channel Secret (if it hasn’t been generated yet, click \"Issue\" to create one).\n  <img src=\"./_assets/2025-03-10 21 07 14.png\" width=\"600\" />\n  - Navigate to the Messaging API page.\n  - Enable Use Webhook.\n  - Copy the Channel Access Token (if it hasn’t been generated yet, click \"Issue\" to create one).\n  <img src=\"./_assets/2025-03-10 21 06 36.png\" width=\"600\" /> \n\n3. Set Up the Dify Line Bot Endpoint\n  - Set an Endpoint Name.\n  - Paste the Channel Secret and Channel Access Token.\n  - Select a Chat Workflow. \n  <img src=\"./_assets/2025-03-10 21 08 10.png\" width=\"600\" />\n\n4. Save and Copy the Line Bot Webhook URL\n  <img src=\"./_assets/2025-03-10 21 02 33.png\" width=\"600\" />\n\n5. Set the Webhook URL and Verify\n  - Return to the Messaging API page on the LINE Developers platform.\n  - Paste the Webhook URL obtained in the previous step.\n  - Verify the Line Bot. \n  <img src=\"./_assets/2025-03-10 21 03 50.png\" width=\"600\" /> \n  <img src=\"./_assets/2025-03-10 21 08 36.png\" width=\"600\" />\n6. Use Line to add the Line Official Account and start chatting with AI.\n  <img src=\"./_assets/S__320659478.jpg\" width=\"600\" />",
        "label": {
          "en_US": "Line Bot",
          "ja_JP": "Line Bot",
          "pt_BR": "Line Bot",
          "zh_Hans": "Line Bot"
        },
        "latest_package_identifier": "kevintsai/linebot:0.0.3@7375a053291d3a926a8c1edb1e258340b6a5d45a8d138d25425077f2fb2241e4",
        "latest_version": "0.0.3",
        "model": {},
        "name": "linebot",
        "org": "kevintsai",
        "plugin_id": "kevintsai/linebot",
        "plugins": {
          "agent_strategies": null,
          "endpoints": [
            "group/linebot.yaml"
          ],
          "models": null,
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "model": {
              "enabled": false,
              "llm": false,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-03-19T02:45:12Z",
        "version_updated_at": "2025-03-19T02:45:12Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Get transcripts from YouTube videos",
          "zh_Hans": "获取 YouTube 视频的字幕/转录文本"
        },
        "category": "tool",
        "created_at": "2024-11-29T06:13:48Z",
        "endpoint": {},
        "icon": "langgenius/packages/transcript/_assets/icon.svg",
        "index_id": "langgenius___transcript",
        "install_count": 746,
        "introduction": "# Overview\nTranscript is a useful tool for converting spoken content from videos into written text, enhancing accessibility, improving SEO, and facilitating content analysis.\n\n# Configure\n1. Install Transcript from Dify Marketplace.\n![](./_assets/transcript_install.png)\n2. Add Transcript to your workflow.\n3. Fill in the variables. A video ID is required. \nFor video `https://www.youtube.com/watch?v=GbdqZsFSRr0`, the ID is `GbdqZsFSRr0`.\n![](./_assets/transcript_parameter.png)",
        "label": {
          "en_US": "Transcript",
          "zh_Hans": "Transcript"
        },
        "latest_package_identifier": "langgenius/transcript:0.0.2@aa792aa9b1f954aabedc631e2b2ecf61bd417c78b64dff62973b963fd8bf45e5",
        "latest_version": "0.0.2",
        "model": {},
        "name": "transcript",
        "org": "langgenius",
        "plugin_id": "langgenius/transcript",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/transcript.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "videos"
          }
        ],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "Tao Wang",
            "description": {
              "en_US": "Get transcripts from YouTube videos",
              "zh_Hans": "获取 YouTube 视频的字幕/转录文本"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Transcript",
              "zh_Hans": "Transcript"
            },
            "name": "transcript",
            "tags": [
              "videos"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Get transcript from a YouTube video for free.",
                  "zh_Hans": "免费获取 YouTube 视频的转录文案。"
                },
                "llm": "A tool for retrieving transcript from YouTube videos."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Tao Wang",
                "label": {
                  "en_US": "Free YouTube Transcript API",
                  "zh_Hans": "免费获取 YouTube 转录"
                },
                "name": "free_youtube_transcript"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Used to define the video from which the transcript will be fetched. You can find the id in the video url. For example - https://www.youtube.com/watch?v=video_id.",
                    "zh_Hans": "您要哪条视频的转录文案？您可以在视频链接中找到id。例如 - https://www.youtube.com/watch?v=video_id。"
                  },
                  "label": {
                    "en_US": "Video ID/URL",
                    "zh_Hans": "视频ID"
                  },
                  "llm_description": "Used to define the video from which the transcript will be fetched. For example - https://www.youtube.com/watch?v=video_id.",
                  "max": null,
                  "min": null,
                  "name": "video_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Language code (e.g. 'en', 'zh') for the transcript.",
                    "zh_Hans": "字幕语言代码（如'en'、'zh'）。留空则自动选择。"
                  },
                  "label": {
                    "en_US": "Language Code",
                    "zh_Hans": "语言"
                  },
                  "llm_description": "Used to set the language for transcripts.",
                  "max": null,
                  "min": null,
                  "name": "language",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "text",
                  "form": "form",
                  "human_description": {
                    "en_US": "Format of the transcript output",
                    "zh_Hans": "字幕输出格式"
                  },
                  "label": {
                    "en_US": "Output Format",
                    "zh_Hans": "输出格式"
                  },
                  "llm_description": "The format to output the transcript in. Options are text (plain text), json (raw transcript data), srt (SubRip format), or vtt (WebVTT format)",
                  "max": null,
                  "min": null,
                  "name": "format",
                  "options": [
                    {
                      "label": {
                        "en_US": "Plain Text",
                        "zh_Hans": "纯文本"
                      },
                      "value": "text"
                    },
                    {
                      "label": {
                        "en_US": "JSON Format",
                        "zh_Hans": "JSON 格式"
                      },
                      "value": "json"
                    },
                    {
                      "label": {
                        "en_US": "Pretty Print Format",
                        "zh_Hans": "美化格式"
                      },
                      "value": "pretty"
                    },
                    {
                      "label": {
                        "en_US": "SRT Format",
                        "zh_Hans": "SRT 格式"
                      },
                      "value": "srt"
                    },
                    {
                      "label": {
                        "en_US": "WebVTT Format",
                        "zh_Hans": "WebVTT 格式"
                      },
                      "value": "vtt"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Keep HTML formatting elements like <i> (italics) and <b> (bold)",
                    "zh_Hans": "保留HTML格式元素，如<i>（斜体）和<b>（粗体）"
                  },
                  "label": {
                    "en_US": "Preserve Formatting",
                    "zh_Hans": "保留格式"
                  },
                  "llm_description": "Whether to preserve HTML formatting elements in the transcript text",
                  "max": null,
                  "min": null,
                  "name": "preserve_formatting",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "HTTPS proxy URL (e.g. https://user:pass@domain:port)",
                    "zh_Hans": "HTTPS 代理地址（如 https://user:pass@domain:port）"
                  },
                  "label": {
                    "en_US": "HTTPS Proxy",
                    "zh_Hans": "HTTPS 代理"
                  },
                  "llm_description": "HTTPS proxy to use for the request. Format should be https://user:pass@domain:port",
                  "max": null,
                  "min": null,
                  "name": "proxy",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Path to cookies.txt file for accessing age-restricted videos",
                    "zh_Hans": "用于访问年龄限制视频的 cookies.txt 文件路径"
                  },
                  "label": {
                    "en_US": "Cookies File Path",
                    "zh_Hans": "Cookies 文件路径"
                  },
                  "llm_description": "Path to a cookies.txt file containing YouTube cookies, needed for accessing age-restricted videos",
                  "max": null,
                  "min": null,
                  "name": "cookies",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:08:24Z",
        "version_updated_at": "2025-02-17T07:08:24Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "GitLab plugin, API v4 only.",
          "zh_Hans": "用于获取GitLab内容的插件，目前仅支持 API v4。"
        },
        "category": "tool",
        "created_at": "2024-12-04T04:45:02Z",
        "endpoint": {},
        "icon": "langgenius/packages/gitlab/_assets/gitlab.svg",
        "index_id": "langgenius___gitlab",
        "install_count": 738,
        "introduction": "# GitLab Tool\n\n## Overview\n\nGitLab is a web-based DevOps platform providing tools for software development, with core functionalities including query commits, file uploads, merge requests, and project creation and management. It enables version control, code collaboration, and CI/CD (Continuous Integration/Continuous Deployment) workflows.\n\n## Configuration\n\n### 1. Apply for GitLab Access Token\nPlease follow the [offical documents](https://archives.docs.gitlab.com/16.9/ee/api/oauth2.html) to get the access token.\n\n### 2. Get GitLab tools from Plugin Marketplace\nThe GitLab tools could be found at the Plugin Marketplace, please install it.\n\n### 3. Fill in the configuration in Dify\nOn the Dify navigation page, click `Tools > GitLab > To Authorize` and fill in the access token.\n\n![](./_assets/gitlab_1.png)\n\n### 4. Use the tool\nYou can use the GitLab tool in the following application types.\n\n![](./_assets/gitlab_2.png)\n\n#### Chatflow / Workflow applications\nBoth Chatflow and Workflow applications support adding a GitLab tool node for data processing tasks.\n\n#### Agent applications\nAdd the GitLab tool in the Agent application, then enter data processing commands to call this tool.",
        "label": {
          "en_US": "GitLab",
          "zh_Hans": "GitLab"
        },
        "latest_package_identifier": "langgenius/gitlab:0.0.2@710ca514fa167bd2f69c3f5b7aa371197e6c7d778413f414603948a34352ad72",
        "latest_version": "0.0.2",
        "model": {},
        "name": "gitlab",
        "org": "langgenius",
        "plugin_id": "langgenius/gitlab",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/gitlab.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "GitLab access token",
                "zh_Hans": "GitLab access token"
              },
              "name": "access_tokens",
              "options": null,
              "placeholder": {
                "en_US": "Please input your GitLab access token",
                "zh_Hans": "请输入你的 GitLab access token"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://docs.gitlab.com/16.9/ee/api/oauth2.html"
            },
            {
              "default": "https://gitlab.com",
              "helper": null,
              "label": {
                "en_US": "GitLab site url",
                "zh_Hans": "GitLab site url"
              },
              "name": "site_url",
              "options": null,
              "placeholder": {
                "en_US": "Please input your GitLab site url",
                "zh_Hans": "请输入你的 GitLab site url"
              },
              "required": false,
              "scope": null,
              "type": "text-input",
              "url": "https://gitlab.com/help"
            }
          ],
          "identity": {
            "author": "Leo.Wang",
            "description": {
              "en_US": "GitLab plugin, API v4 only.",
              "zh_Hans": "用于获取GitLab内容的插件，目前仅支持 API v4。"
            },
            "icon": "gitlab.svg",
            "label": {
              "en_US": "GitLab",
              "zh_Hans": "GitLab"
            },
            "name": "gitlab",
            "tags": []
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool for query GitLab files, Input should be branch and a exists file or directory path.",
                  "zh_Hans": "一个用于查询 GitLab 文件的工具，输入的内容应该是分支和一个已存在文件或者文件夹路径。"
                },
                "llm": "A tool for query GitLab files, Input should be a exists file or directory path."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Leo.Wang",
                "label": {
                  "en_US": "GitLab Files",
                  "zh_Hans": "GitLab 文件获取"
                },
                "name": "gitlab_files"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "repository",
                    "zh_Hans": "仓库路径，以namespace/project_name的形式。"
                  },
                  "label": {
                    "en_US": "repository",
                    "zh_Hans": "仓库路径"
                  },
                  "llm_description": "Repository path for GitLab, like namespace/project_name.",
                  "max": null,
                  "min": null,
                  "name": "repository",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "project",
                    "zh_Hans": "项目"
                  },
                  "label": {
                    "en_US": "project",
                    "zh_Hans": "项目"
                  },
                  "llm_description": "Project for GitLab",
                  "max": null,
                  "min": null,
                  "name": "project",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "branch",
                    "zh_Hans": "分支"
                  },
                  "label": {
                    "en_US": "branch",
                    "zh_Hans": "分支"
                  },
                  "llm_description": "Branch for GitLab",
                  "max": null,
                  "min": null,
                  "name": "branch",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "path",
                    "zh_Hans": "文件路径"
                  },
                  "label": {
                    "en_US": "path",
                    "zh_Hans": "文件路径"
                  },
                  "llm_description": "File path for GitLab",
                  "max": null,
                  "min": null,
                  "name": "path",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for query GitLab commits, Input should be a exists username or project.",
                  "zh_Hans": "一个用于查询 GitLab 代码提交内容的工具，输入的内容应该是一个已存在的用户名或者项目名。"
                },
                "llm": "A tool for query GitLab commits, Input should be a exists username or project."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Leo.Wang",
                "label": {
                  "en_US": "GitLab Commits",
                  "zh_Hans": "GitLab 提交内容查询"
                },
                "name": "gitlab_commits"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "username",
                    "zh_Hans": "员工用户名"
                  },
                  "label": {
                    "en_US": "username",
                    "zh_Hans": "员工用户名"
                  },
                  "llm_description": "User name for GitLab",
                  "max": null,
                  "min": null,
                  "name": "username",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "repository",
                    "zh_Hans": "仓库路径，以namespace/project_name的形式。"
                  },
                  "label": {
                    "en_US": "repository",
                    "zh_Hans": "仓库路径"
                  },
                  "llm_description": "Repository path for GitLab, like namespace/project_name.",
                  "max": null,
                  "min": null,
                  "name": "repository",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "branch",
                    "zh_Hans": "分支名"
                  },
                  "label": {
                    "en_US": "branch",
                    "zh_Hans": "分支名"
                  },
                  "llm_description": "branch for GitLab",
                  "max": null,
                  "min": null,
                  "name": "branch",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "start_time",
                    "zh_Hans": "开始时间"
                  },
                  "label": {
                    "en_US": "start_time",
                    "zh_Hans": "开始时间"
                  },
                  "llm_description": "Start time for GitLab",
                  "max": null,
                  "min": null,
                  "name": "start_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "end_time",
                    "zh_Hans": "结束时间"
                  },
                  "label": {
                    "en_US": "end_time",
                    "zh_Hans": "结束时间"
                  },
                  "llm_description": "End time for GitLab",
                  "max": null,
                  "min": null,
                  "name": "end_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "all",
                  "form": "llm",
                  "human_description": {
                    "en_US": "change_type",
                    "zh_Hans": "变更类型"
                  },
                  "label": {
                    "en_US": "change_type",
                    "zh_Hans": "变更类型"
                  },
                  "llm_description": "Content change type for GitLab",
                  "max": null,
                  "min": null,
                  "name": "change_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "all",
                        "zh_Hans": "所有"
                      },
                      "value": "all"
                    },
                    {
                      "label": {
                        "en_US": "new",
                        "zh_Hans": "新增"
                      },
                      "value": "new"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for query GitLab merge requests, Input should be a exists reposity or branch.",
                  "zh_Hans": "一个用于查询 GitLab 代码合并请求的工具，输入的内容应该是一个已存在的仓库名或者分支。"
                },
                "llm": "A tool for query GitLab merge requests, Input should be a exists reposity or branch."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Leo.Wang",
                "label": {
                  "en_US": "GitLab Merge Requests",
                  "zh_Hans": "GitLab 合并请求查询"
                },
                "name": "gitlab_mergerequests"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "repository",
                    "zh_Hans": "仓库路径，以namespace/project_name的形式。"
                  },
                  "label": {
                    "en_US": "repository",
                    "zh_Hans": "仓库路径"
                  },
                  "llm_description": "Repository path for GitLab, like namespace/project_name.",
                  "max": null,
                  "min": null,
                  "name": "repository",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "branch",
                    "zh_Hans": "分支名"
                  },
                  "label": {
                    "en_US": "branch",
                    "zh_Hans": "分支名"
                  },
                  "llm_description": "branch for GitLab",
                  "max": null,
                  "min": null,
                  "name": "branch",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "start_time",
                    "zh_Hans": "开始时间"
                  },
                  "label": {
                    "en_US": "start_time",
                    "zh_Hans": "开始时间"
                  },
                  "llm_description": "Start time for GitLab",
                  "max": null,
                  "min": null,
                  "name": "start_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "end_time",
                    "zh_Hans": "结束时间"
                  },
                  "label": {
                    "en_US": "end_time",
                    "zh_Hans": "结束时间"
                  },
                  "llm_description": "End time for GitLab",
                  "max": null,
                  "min": null,
                  "name": "end_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "opened",
                  "form": "llm",
                  "human_description": {
                    "en_US": "state",
                    "zh_Hans": "变更状态"
                  },
                  "label": {
                    "en_US": "state",
                    "zh_Hans": "变更状态"
                  },
                  "llm_description": "Merge request state type for GitLab",
                  "max": null,
                  "min": null,
                  "name": "state",
                  "options": [
                    {
                      "label": {
                        "en_US": "opened",
                        "zh_Hans": "打开"
                      },
                      "value": "opened"
                    },
                    {
                      "label": {
                        "en_US": "closed",
                        "zh_Hans": "关闭"
                      },
                      "value": "closed"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for query GitLab projects, Input should be a project name.",
                  "zh_Hans": "一个用于查询 GitLab 项目列表的工具，输入的内容应该是一个项目名称。"
                },
                "llm": "A tool for query GitLab projects, Input should be a project name."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Leo.Wang",
                "label": {
                  "en_US": "GitLab Projects",
                  "zh_Hans": "GitLab 项目列表查询"
                },
                "name": "gitlab_projects"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "project_name",
                    "zh_Hans": "项目名称"
                  },
                  "label": {
                    "en_US": "project_name",
                    "zh_Hans": "项目名称"
                  },
                  "llm_description": "Project name for GitLab",
                  "max": null,
                  "min": null,
                  "name": "project_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "page",
                    "zh_Hans": "页码"
                  },
                  "label": {
                    "en_US": "page",
                    "zh_Hans": "页码"
                  },
                  "llm_description": "Page index for GitLab",
                  "max": null,
                  "min": null,
                  "name": "page",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "page_size",
                    "zh_Hans": "每页数量"
                  },
                  "label": {
                    "en_US": "page_size",
                    "zh_Hans": "每页数量"
                  },
                  "llm_description": "Page size for GitLab",
                  "max": null,
                  "min": null,
                  "name": "page_size",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:05:01Z",
        "version_updated_at": "2025-02-17T07:05:01Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "The image/video generation API provided  by ZhipuAI, support cogview and cogvideox models.",
          "zh_Hans": "智谱AI提供的图片、视频API，支持 cogview 和 cogvideox 模型。"
        },
        "category": "tool",
        "created_at": "2025-03-11T12:55:34Z",
        "endpoint": {},
        "icon": "langgenius/packages/zhipuai_tool/_assets/icon_s_en.svg",
        "index_id": "langgenius___zhipuai_tool",
        "install_count": 709,
        "introduction": "# CogView\n\n## Overview\n\nZhipuAI is an AI model for text-to-image and text-to-video generation. It can create both images and videos based on textual descriptions provided by users. The model offers a variety of artistic styles and content generation options across both image and video formats.\n\n## Configuration\n\n### 1. Ensure that you are allowed to use the BigModel service\n> If you don't have an account, go to the [BigModel site](https://bigmodel.cn/) and follow their instruction to create an account.\n\nYou can get the API key from the [ZHIPU AI OPEN PLATFORM](https://bigmodel.cn/).\n\n### 2. Get CogView tools from Plugin Marketplace\nThe ZhipuAI tools could be found at the Plugin Marketplace, please install it.\n\n### 3. Setup the CogView API in the Dify Tool page\nOn the Dify navigation page, click `Tools > zhipuai > To Authorize` and fill the API Key.\n\n![](./_assets/zhipuai_1.png)\n\n### 4. Using the tool\nYou can use the ZhipuAI tool in the following application types.\n\n![](./_assets/zhipuai_2.png)\n\n#### Chatflow / Workflow applications\nBoth Chatflow and Workflow applications support adding a ZhipuAI tool node.\n\n#### Agent applications\nAdd the ZhipuAI tool in the Agent application, then enter online search instructions to call this tool.",
        "label": {
          "en_US": "ZhipuAI",
          "pt_BR": "ZhipuAI",
          "zh_Hans": "智谱AI"
        },
        "latest_package_identifier": "langgenius/zhipuai_tool:0.0.1@3dddabe4e219bc9b082ba1669b707688bd2b4aa7ea1c5d035314fbe484d21824",
        "latest_version": "0.0.1",
        "model": {},
        "name": "zhipuai_tool",
        "org": "langgenius",
        "plugin_id": "langgenius/zhipuai_tool",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/zhipuai.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "image"
          },
          {
            "name": "videos"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Please input your ZhipuAI API key",
                "pt_BR": "Please input your ZhipuAI API key",
                "zh_Hans": "请输入你的 ZhipuAI API key"
              },
              "label": {
                "en_US": "ZhipuAI API key",
                "pt_BR": "ZhipuAI API key",
                "zh_Hans": "ZhipuAI API key"
              },
              "name": "zhipuai_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your ZhipuAI API key",
                "pt_BR": "Please input your ZhipuAI API key",
                "zh_Hans": "请输入你的 ZhipuAI API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "help": {
                "en_US": "Please input your ZhipuAI base URL",
                "pt_BR": "Please input your ZhipuAI base URL",
                "zh_Hans": "请输入你的 ZhipuAI base URL"
              },
              "label": {
                "en_US": "ZhipuAI base URL",
                "pt_BR": "ZhipuAI base URL",
                "zh_Hans": "ZhipuAI base URL"
              },
              "name": "zhipuai_base_url",
              "options": null,
              "placeholder": {
                "en_US": "Please input your ZhipuAI base URL",
                "pt_BR": "Please input your ZhipuAI base URL",
                "zh_Hans": "请输入你的 ZhipuAI base URL"
              },
              "required": false,
              "scope": null,
              "type": "text-input",
              "url": null
            }
          ],
          "identity": {
            "author": "langgenius",
            "description": {
              "en_US": "ZhipuAI",
              "pt_BR": "ZhipuAI",
              "zh_Hans": "ZhipuAI"
            },
            "icon": "icon_s_en.svg",
            "label": {
              "en_US": "ZhipuAI",
              "pt_BR": "ZhipuAI",
              "zh_Hans": "智谱AI"
            },
            "name": "zhipuai",
            "tags": [
              "image",
              "videos"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "CogView is a text to image tool",
                  "zh_Hans": "CogView 是一个文本到图像的工具"
                },
                "llm": "CogView is a tool used to generate images from text"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "CogView Series",
                  "zh_Hans": "CogView系列绘画"
                },
                "name": "cogview"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": "cogview-3-flash",
                  "form": "form",
                  "human_description": {
                    "en_US": "Model code, Support \"cogview-3-flash\", \"cogview-4\"",
                    "zh_Hans": "模型编码，支持：cogview-3-flash，cogview-4"
                  },
                  "label": {
                    "en_US": "model",
                    "zh_Hans": "模型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Text description of the desired image",
                    "zh_Hans": "所需图像的文本描述"
                  },
                  "label": {
                    "en_US": "Prompt",
                    "zh_Hans": "提示词"
                  },
                  "llm_description": "Image prompt of CogView, you should describe the image you want to generate as a list of words as possible as detailed",
                  "max": null,
                  "min": null,
                  "name": "prompt",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "1024x1024",
                  "form": "form",
                  "human_description": {
                    "en_US": "selecting the image size",
                    "zh_Hans": "选择图像大小"
                  },
                  "label": {
                    "en_US": "Image size",
                    "zh_Hans": "图像大小"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "size",
                  "options": [
                    {
                      "label": {
                        "en_US": "1024x1024"
                      },
                      "value": "1024x1024"
                    },
                    {
                      "label": {
                        "en_US": "768x1344"
                      },
                      "value": "768x1344"
                    },
                    {
                      "label": {
                        "en_US": "864x1152"
                      },
                      "value": "864x1152"
                    },
                    {
                      "label": {
                        "en_US": "1344x768"
                      },
                      "value": "1344x768"
                    },
                    {
                      "label": {
                        "en_US": "1152x864"
                      },
                      "value": "1152x864"
                    },
                    {
                      "label": {
                        "en_US": "1440x720"
                      },
                      "value": "1440x720"
                    },
                    {
                      "label": {
                        "en_US": "720x1440"
                      },
                      "value": "720x1440"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Use the CogVideo model provided by ZhipuAI to generate videos based on user prompts and images.",
                  "zh_Hans": "使用智谱cogvideo模型，根据用户输入的提示词和图片，生成视频。"
                },
                "llm": "A tool for generating videos. The input is user's prompt or image url or both of them, the output is a task id. You can use another tool with this task id to check the status and get the video."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "CogVideo",
                  "zh_Hans": "CogVideo 视频生成"
                },
                "name": "cogvideo"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The prompt text used to generate video.",
                    "zh_Hans": "用于生成视频的提示词。"
                  },
                  "label": {
                    "en_US": "prompt",
                    "zh_Hans": "提示词"
                  },
                  "llm_description": "The prompt text used to generate video. Optional.",
                  "max": null,
                  "min": null,
                  "name": "prompt",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The image url used to generate video.",
                    "zh_Hans": "输入一个图片链接，生成的视频将基于该图片和提示词。"
                  },
                  "label": {
                    "en_US": "image url",
                    "zh_Hans": "图片链接"
                  },
                  "llm_description": "The image url used to generate video. Optional.",
                  "max": null,
                  "min": null,
                  "name": "image_url",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "cogvideox-flash",
                  "form": "form",
                  "human_description": {
                    "en_US": "Model code, Support：cogvideox-2, cogvideox-flash",
                    "pt_BR": "Model code, Support：cogvideox-2, cogvideox-flash",
                    "zh_Hans": "模型编码，支持：cogvideox-2, cogvideox-flash"
                  },
                  "label": {
                    "en_US": "model",
                    "pt_BR": "model",
                    "zh_Hans": "模型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "speed",
                  "form": "form",
                  "human_description": {
                    "en_US": "Output mode, default is \"speed\". cogvideox-flash does not support.",
                    "pt_BR": "Output mode, default is \"speed\". cogvideox-flash does not support.",
                    "zh_Hans": "输出模式，默认为 \"speed\"。 cogvideox-flash 不支持"
                  },
                  "label": {
                    "en_US": "quality",
                    "pt_BR": "quality",
                    "zh_Hans": "输出模式"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "quality",
                  "options": [
                    {
                      "label": {
                        "en_US": "Prioritizes quality, higher generation quality.",
                        "zh_Hans": "质量优先，生成质量高"
                      },
                      "value": "quality"
                    },
                    {
                      "label": {
                        "en_US": "Prioritizes speed, faster generation time, relatively lower quality.",
                        "zh_Hans": "速度优先，生成时间更快。"
                      },
                      "value": "speed"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to generate AI sound effects. Default False.",
                    "pt_BR": "Whether to generate AI sound effects. Default False.",
                    "zh_Hans": "是否生成AI音效，默认 False"
                  },
                  "label": {
                    "en_US": "with_audio",
                    "pt_BR": "with_audio",
                    "zh_Hans": "是否生成AI音效"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "with_audio",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "If not specified, the short side of the generated video defaults to 1080, with the long side scaled according to the original image ratio. cogvideox-flash does not support.",
                    "pt_BR": "If not specified, the short side of the generated video defaults to 1080, with the long side scaled according to the original image ratio. cogvideox-flash does not support.",
                    "zh_Hans": "若不指定，默认生成视频的短边为 1080，长边根据原图片比例缩放，cogvideox-flash 不支持"
                  },
                  "label": {
                    "en_US": "size",
                    "pt_BR": "size",
                    "zh_Hans": "尺寸"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "size",
                  "options": [
                    {
                      "label": {
                        "en_US": "720x480"
                      },
                      "value": "720x480"
                    },
                    {
                      "label": {
                        "en_US": "1024x1024"
                      },
                      "value": "1024x1024"
                    },
                    {
                      "label": {
                        "en_US": "1280x960"
                      },
                      "value": "1280x960"
                    },
                    {
                      "label": {
                        "en_US": "960x1280"
                      },
                      "value": "960x1280"
                    },
                    {
                      "label": {
                        "en_US": "1920x1080"
                      },
                      "value": "1920x1080"
                    },
                    {
                      "label": {
                        "en_US": "1080x1920"
                      },
                      "value": "1080x1920"
                    },
                    {
                      "label": {
                        "en_US": "2048x1080"
                      },
                      "value": "2048x1080"
                    },
                    {
                      "label": {
                        "en_US": "3840x2160"
                      },
                      "value": "3840x2160"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "FPS, 30 or 60. default 30. cogvideox-flash does not support.",
                    "pt_BR": "FPS, 30 or 60. default 30. cogvideox-flash does not support.",
                    "zh_Hans": "视频帧率（FPS）,30或60，默认值 30，cogvideox-flash 不支持"
                  },
                  "label": {
                    "en_US": "fps",
                    "pt_BR": "fps",
                    "zh_Hans": "视频帧率"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "fps",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "10",
                  "form": "form",
                  "human_description": {
                    "en_US": "Number of retries to obtain the generated video",
                    "zh_Hans": "获取生成后的视频的重试次数"
                  },
                  "label": {
                    "en_US": "retry count",
                    "zh_Hans": "重试次数"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "retry_count",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "10",
                  "form": "form",
                  "human_description": {
                    "en_US": "Waiting duration for retries to obtain the generated video, in seconds(s)",
                    "zh_Hans": "获取生成后的视频的重试的等待时长，单位(秒)"
                  },
                  "label": {
                    "en_US": "wait time",
                    "zh_Hans": "等待时长"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "wait_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-11T12:55:45Z",
        "version_updated_at": "2025-03-11T12:55:45Z"
      },
      {
        "agent_strategy": {},
        "badges": [
          "partner"
        ],
        "brief": {
          "en_US": "DupDub",
          "ja_JP": "DupDub",
          "pt_BR": "DupDub",
          "zh_Hans": "DupDub"
        },
        "category": "tool",
        "created_at": "2025-02-17T09:47:58Z",
        "endpoint": {},
        "icon": "dupdub-dify/packages/dupdub/_assets/icon.svg",
        "index_id": "dupdub-dify___dupdub",
        "install_count": 695,
        "introduction": "# dupdub\n\n**Author:** dupdub\n**Version:** 0.0.1\n**Type:** extension\n\n## Description\ndupdub is a powerful AI-powered platform that provides a wide range of services, including speech recognition, voice cloning, dubbing, and more. With its advanced AI algorithms and cutting-edge technology, dupdub offers a comprehensive suite of tools for enhancing the quality of audio content and improving user experiences.\n\n## Features\n\n### Transcribe speech\n  This feature provides an AI transcription service that converts audio or video content into text. By using DupDub's ASR (Automatic Speech Recognition) API, users can upload audio or video files and get transcriptions with each segment's start and end timestamps. The transcriptions can be used for applications like subtitle generation, content analysis, and speech-to-text conversion.\n---\n\n#### Response\n```json\n{\n        \"url\": \"https://cdn-static.dupdub.com/backend/subtitles/2024-03-28-3330050169139501912.mp4\",\n        \"language\": \"english\",\n        \"duration\": 52.220001220703125,\n        \"text\": \"The million dollar question is how can I use DupDup to make money? The million dollar question is how can I use DupDup to make money?\",\n        \"segments\": [\n          {\n            \"id\": 0,\n            \"start\": 0.0,\n            \"end\": 4.0,\n            \"text\": \" The million dollar question is how can I use DupDup to make money?\"\n          },\n          {\n            \"id\": 1,\n            \"start\": 4.0,\n            \"end\": 7.039999961853027,\n            \"text\": \" The million dollar question is how can I use DupDup to make money?\"\n          }\n        ]\n      }\n```\n\n|name|message|\n|---|---|\n|url|URL of the audio file processed|\n|language|Language of the transcribed content|\n|duration|Duration of the audio in seconds|\n|text|Transcription result text|\n|segments|Detailed segment information within the transcription|\n|id|Paragraph ID within the transcription|\n|start|Start time of the segment|\n|end|End time of the segment|\n|text|Transcribed text of the segment|\n\n\n\n\n### Voice Cloning\n  This feature allows users to clone the voice of a specific speaker by providing a speech sample. The cloned voice can then be used for text-to-speech (TTS) or other voice applications, generating synthetic speech that closely resembles the original speaker's voice.\n\n#### Response\n```json\n  {\n    \"id\": 16169,\n    \"speaker\": \"uranus||||0acd3a6248c6aade4f20b7c28bb0a13f\",\n    \"name\": \"test_cloned\"\n  }\n```\n\n|name|message|\n|---|---|\n|id|Unique identifier of the cloned speaker|\n|speaker|Speaker identifier for the cloned speaker.|\n|name|Speaker's name|\n\n\n\n### Dubbing\n  This feature allows users to synthesize speech by providing a cloned speaker's identity, speech speed, pitch, and the text to be spoken. By sending these parameters via an API request, users can generate personalized speech content that mimics the voice of the selected speaker. This can be used for applications like voice assistants, voice-over services, and other text-to-speech (TTS) scenarios. \n\n#### Response\n```json\n  \n    { \n        \"success\": true,\n        \"code\": 200,\n        \"message\": \"Succeed\",\n        \"length\": 21,\n        \"result\": {\n          \"duration_address\": \"https://oci-useast-ohio-speech-public.dupdub.com/mobvoi-tts/voice-maker/duration/null/1711372316698/3c49a4d5d2eadd6a5472d24734898d07.json?v=1711372316862\",\n          \"lengthOfTime\": 1.890125,\n          \"message\": \"ok\",\n          \"ossFile\": \"https://oci-useast-ohio-speech-public.dupdub.com/mobvoi-tts/voice-maker/synthesis_audio/null/1711372316698/3c49a4d5d2eadd6a5472d24734898d07.wav\",\n          \"size\": \"90770\",\n          \"srt_address\": \"https://oci-useast-ohio-speech-public.dupdub.com/mobvoi-tts/voice-maker/subtitle/null/1711372316698/3c49a4d5d2eadd6a5472d24734898d07.srt?v=1711372317113\",\n        }\n      }\n```\n\n|name|message|\n|---|---|\n|success|Indicates if the dubbing operation was successful|\n|code|Status code related to the dubbing operation|\n|message|Detailed message or information about the operation|\n|length|Length of the request in characters|\n|result|Container for detailed results of the operation|\n| duration_address|URL or path to the audio duration information|\n| lengthOfTime|Duration of the generated audio in seconds|\n| ossFile|URL or path to the audio file|\n| size|Size of the generated audio file (bytes)|\n| srt_address|URL or path to the subtitle (SRT) file, if generated|\n| code|Response code indicating success or failure\n  200: Succeed\n  400: Parameter validation failed\n  403: No relevant permissions\n  500: Failed\n  502: Gateway service exception\n  2001: Login failed, please login again|\n| message|A message providing additional information about the response code|\n\n\n### Get speaker ID\n  This feature allows users to query a list of voiceover actors based on specified criteria such as language, accent, and domain. By using the searchSpeakerList API, users can filter voice actors according to their language preference (e.g., English), accent (e.g., American), and domain (e.g., commercial or educational). This is useful for selecting the most appropriate voice talent for specific projects\n\n#### Response\n```json\n  {\n    \"speakerId\": 16169,\n    \"speaker\": \"uranus||||0acd3a6248c6aade4f20b7c28bb0a13f\",\n    \"name\": \"test_cloned\"\n  }\n```\n\n|name|message|\n|---|---|\n|speakerId|Unique identifier of the cloned speaker|\n|speaker|Speaker identifier for the cloned speaker.|\n|name|Speaker's name|\n\n\n\n",
        "label": {
          "en_US": "DupDub",
          "ja_JP": "DupDub",
          "pt_BR": "DupDub",
          "zh_Hans": "DupDub"
        },
        "latest_package_identifier": "dupdub-dify/dupdub:0.0.3@693757f894492a9bb7c737666f00d425704e1b6683ae7319fceca9b816e3ad82",
        "latest_version": "0.0.3",
        "model": {},
        "name": "dupdub",
        "org": "dupdub-dify",
        "plugin_id": "dupdub-dify/dupdub",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/dupdub.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {}
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "DupDub token",
                "pt_BR": "DupDub token",
                "zh_Hans": "DupDub token"
              },
              "name": "dupdub_token",
              "options": null,
              "placeholder": null,
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://www.dupdub.com/?utm_source=dify&utm_medium=dify&utm_campaign=dify&utm_id=20250211"
            }
          ],
          "identity": {
            "author": "dupdub-dify",
            "description": {
              "en_US": "DupDub",
              "pt_BR": "DupDub",
              "zh_Hans": "DupDub"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "DupDub",
              "pt_BR": "DupDub",
              "zh_Hans": "DupDub"
            },
            "name": "dupdub",
            "tags": [
              "design",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "TranscribeSpeech",
                  "pt_BR": "TranscribeSpeech",
                  "zh_Hans": "提取文案"
                },
                "llm": "TranscribeSpeech"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "dupdub-dify",
                "label": {
                  "en_US": "TranscribeSpeech",
                  "pt_BR": "TranscribeSpeech",
                  "zh_Hans": "提取文案"
                },
                "name": "TranscribeSpeech"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Duration of the video",
                    "pt_BR": "Duração do vídeo",
                    "zh_Hans": "视频时长"
                  },
                  "label": {
                    "en_US": "Duration",
                    "pt_BR": "Duration",
                    "zh_Hans": "时长"
                  },
                  "llm_description": "Duration of the video",
                  "max": null,
                  "min": null,
                  "name": "duration",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "URL of the video",
                    "pt_BR": "URL do vídeo",
                    "zh_Hans": "视频链接"
                  },
                  "label": {
                    "en_US": "URL",
                    "pt_BR": "URL do vídeo",
                    "zh_Hans": "视频链接"
                  },
                  "llm_description": "URL of the video",
                  "max": null,
                  "min": null,
                  "name": "url",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "US",
                  "form": "llm",
                  "human_description": {
                    "en_US": "Languageoftheaudio/videocontent",
                    "pt_BR": "Languageoftheaudio/videocontent",
                    "zh_Hans": "视频支持的语言"
                  },
                  "label": {
                    "en_US": "Language",
                    "pt_BR": "Idioma",
                    "zh_Hans": "语言"
                  },
                  "llm_description": "Language of the video",
                  "max": null,
                  "min": null,
                  "name": "language",
                  "options": [
                    {
                      "label": {
                        "en_US": "Afrikaans",
                        "pt_BR": "Afrikáans",
                        "zh_Hans": "南非语"
                      },
                      "value": "Afrikaans"
                    },
                    {
                      "label": {
                        "en_US": "Arabic",
                        "pt_BR": "Árabe",
                        "zh_Hans": "阿拉伯语"
                      },
                      "value": "Arabic"
                    },
                    {
                      "label": {
                        "en_US": "Armenian",
                        "pt_BR": "Armênio",
                        "zh_Hans": "亚美尼亚语"
                      },
                      "value": "Armenian"
                    },
                    {
                      "label": {
                        "en_US": "Azerbaijani",
                        "pt_BR": "Azeri",
                        "zh_Hans": "阿塞拜疆语"
                      },
                      "value": "Azerbaijani"
                    },
                    {
                      "label": {
                        "en_US": "Belarusian",
                        "pt_BR": "Bielorrusso",
                        "zh_Hans": "白俄罗斯语"
                      },
                      "value": "Belarusian"
                    },
                    {
                      "label": {
                        "en_US": "Bosnian",
                        "pt_BR": "Bósnio",
                        "zh_Hans": "波斯尼亚语"
                      },
                      "value": "Bosnian"
                    },
                    {
                      "label": {
                        "en_US": "Bulgarian",
                        "pt_BR": "Búlgaro",
                        "zh_Hans": "保加利亚语"
                      },
                      "value": "Bulgarian"
                    },
                    {
                      "label": {
                        "en_US": "Catalan",
                        "pt_BR": "Catalão",
                        "zh_Hans": "加泰罗尼亚语"
                      },
                      "value": "Catalan"
                    },
                    {
                      "label": {
                        "en_US": "Chinese(simplified)",
                        "pt_BR": "Chinese(simplified)",
                        "zh_Hans": "简体中文"
                      },
                      "value": "Chinese(simplified)"
                    },
                    {
                      "label": {
                        "en_US": "Chinese(traditional)",
                        "pt_BR": "Chinese(traditional)",
                        "zh_Hans": "繁体中文"
                      },
                      "value": "Chinese(traditional)"
                    },
                    {
                      "label": {
                        "en_US": "Croatian",
                        "pt_BR": "Croata",
                        "zh_Hans": "克罗地亚语"
                      },
                      "value": "Croatian"
                    },
                    {
                      "label": {
                        "en_US": "Czech",
                        "pt_BR": "Tcheco",
                        "zh_Hans": "捷克语"
                      },
                      "value": "Czech"
                    },
                    {
                      "label": {
                        "en_US": "Danish",
                        "pt_BR": "Dinamarquês",
                        "zh_Hans": "丹麦语"
                      },
                      "value": "Danish"
                    },
                    {
                      "label": {
                        "en_US": "Dutch",
                        "pt_BR": "Holandês",
                        "zh_Hans": "荷兰语"
                      },
                      "value": "Dutch"
                    },
                    {
                      "label": {
                        "en_US": "English",
                        "pt_BR": "Inglês",
                        "zh_Hans": "英语"
                      },
                      "value": "English"
                    },
                    {
                      "label": {
                        "en_US": "Estonian",
                        "pt_BR": "Estônio",
                        "zh_Hans": "爱沙尼亚语"
                      },
                      "value": "Estonian"
                    },
                    {
                      "label": {
                        "en_US": "Finnish",
                        "pt_BR": "Finlândes",
                        "zh_Hans": "芬兰语"
                      },
                      "value": "Finnish"
                    },
                    {
                      "label": {
                        "en_US": "French",
                        "pt_BR": "Francês",
                        "zh_Hans": "法语"
                      },
                      "value": "French"
                    },
                    {
                      "label": {
                        "en_US": "Galician",
                        "pt_BR": "Galês",
                        "zh_Hans": "加利西亚语"
                      },
                      "value": "Galician"
                    },
                    {
                      "label": {
                        "en_US": "German",
                        "pt_BR": "Alemão",
                        "zh_Hans": "德语"
                      },
                      "value": "German"
                    },
                    {
                      "label": {
                        "en_US": "Greek",
                        "pt_BR": "Grego",
                        "zh_Hans": "希腊语"
                      },
                      "value": "Greek"
                    },
                    {
                      "label": {
                        "en_US": "Hebrew",
                        "pt_BR": "Hebraico",
                        "zh_Hans": "希伯来语"
                      },
                      "value": "Hebrew"
                    },
                    {
                      "label": {
                        "en_US": "Hindi",
                        "pt_BR": "Hindi",
                        "zh_Hans": "印地语"
                      },
                      "value": "Hindi"
                    },
                    {
                      "label": {
                        "en_US": "Hungarian",
                        "pt_BR": "Húngaro",
                        "zh_Hans": "匈牙利语"
                      },
                      "value": "Hungarian"
                    },
                    {
                      "label": {
                        "en_US": "Icelandic",
                        "pt_BR": "Islandês",
                        "zh_Hans": "冰岛语"
                      },
                      "value": "Icelandic"
                    },
                    {
                      "label": {
                        "en_US": "Indonesian",
                        "pt_BR": "Indonésio",
                        "zh_Hans": "印度尼西亚语"
                      },
                      "value": "Indonesian"
                    },
                    {
                      "label": {
                        "en_US": "Italian",
                        "pt_BR": "Italiano",
                        "zh_Hans": "意大利语"
                      },
                      "value": "Italian"
                    },
                    {
                      "label": {
                        "en_US": "Japanese",
                        "pt_BR": "Japonês",
                        "zh_Hans": "日语"
                      },
                      "value": "Japanese"
                    },
                    {
                      "label": {
                        "en_US": "Kannada",
                        "pt_BR": "Kannada",
                        "zh_Hans": "卡纳达语"
                      },
                      "value": "Kannada"
                    },
                    {
                      "label": {
                        "en_US": "Kazakh",
                        "pt_BR": "Cazaque",
                        "zh_Hans": "哈萨克语"
                      },
                      "value": "Kazakh"
                    },
                    {
                      "label": {
                        "en_US": "Korean",
                        "pt_BR": "Coreano",
                        "zh_Hans": "韩语"
                      },
                      "value": "Korean"
                    },
                    {
                      "label": {
                        "en_US": "Latvian",
                        "pt_BR": "Letão",
                        "zh_Hans": "拉脱维亚语"
                      },
                      "value": "Latvian"
                    },
                    {
                      "label": {
                        "en_US": "Lithuanian",
                        "pt_BR": "Lituano",
                        "zh_Hans": "立陶宛语"
                      },
                      "value": "Lithuanian"
                    },
                    {
                      "label": {
                        "en_US": "Macedonian",
                        "pt_BR": "Mazedônico",
                        "zh_Hans": "马其顿语"
                      },
                      "value": "Macedonian"
                    },
                    {
                      "label": {
                        "en_US": "Malay",
                        "pt_BR": "Malaio",
                        "zh_Hans": "马来语"
                      },
                      "value": "Malay"
                    },
                    {
                      "label": {
                        "en_US": "Marathi",
                        "pt_BR": "Marathi",
                        "zh_Hans": "马拉地语"
                      },
                      "value": "Marathi"
                    },
                    {
                      "label": {
                        "en_US": "Maori",
                        "pt_BR": "Maori",
                        "zh_Hans": "毛利语"
                      },
                      "value": "Maori"
                    },
                    {
                      "label": {
                        "en_US": "Nepali",
                        "pt_BR": "Nepalês",
                        "zh_Hans": "尼泊尔语"
                      },
                      "value": "Nepali"
                    },
                    {
                      "label": {
                        "en_US": "Norwegian",
                        "pt_BR": "Norueguês",
                        "zh_Hans": "挪威语"
                      },
                      "value": "Norwegian"
                    },
                    {
                      "label": {
                        "en_US": "Persian",
                        "pt_BR": "Persa",
                        "zh_Hans": "波斯语"
                      },
                      "value": "Persian"
                    },
                    {
                      "label": {
                        "en_US": "Polish",
                        "pt_BR": "Polonês",
                        "zh_Hans": "波兰语"
                      },
                      "value": "Polish"
                    },
                    {
                      "label": {
                        "en_US": "Portuguese",
                        "pt_BR": "Português",
                        "zh_Hans": "葡萄牙语"
                      },
                      "value": "Portuguese"
                    },
                    {
                      "label": {
                        "en_US": "Romanian",
                        "pt_BR": "Romeno",
                        "zh_Hans": "罗马尼亚语"
                      },
                      "value": "Romanian"
                    },
                    {
                      "label": {
                        "en_US": "Russian",
                        "pt_BR": "Russo",
                        "zh_Hans": "俄语"
                      },
                      "value": "Russian"
                    },
                    {
                      "label": {
                        "en_US": "Serbian",
                        "pt_BR": "Sérvio",
                        "zh_Hans": "塞尔维亚语"
                      },
                      "value": "Serbian"
                    },
                    {
                      "label": {
                        "en_US": "Slovak",
                        "pt_BR": "Eslovaco",
                        "zh_Hans": "斯洛伐克语"
                      },
                      "value": "Slovak"
                    },
                    {
                      "label": {
                        "en_US": "Slovenian",
                        "pt_BR": "Esloveno",
                        "zh_Hans": "斯洛文尼亚语"
                      },
                      "value": "Slovenian"
                    },
                    {
                      "label": {
                        "en_US": "Spanish",
                        "pt_BR": "Espanhol",
                        "zh_Hans": "西班牙语"
                      },
                      "value": "Spanish"
                    },
                    {
                      "label": {
                        "en_US": "Swahili",
                        "pt_BR": "Swahili",
                        "zh_Hans": "斯瓦希里语"
                      },
                      "value": "Swahili"
                    },
                    {
                      "label": {
                        "en_US": "Swedish",
                        "pt_BR": "Sueco",
                        "zh_Hans": "瑞典语"
                      },
                      "value": "Swedish"
                    },
                    {
                      "label": {
                        "en_US": "Tagalog",
                        "pt_BR": "Tagalo",
                        "zh_Hans": "菲律宾语"
                      },
                      "value": "Tagalog"
                    },
                    {
                      "label": {
                        "en_US": "Tamil",
                        "pt_BR": "Tamil",
                        "zh_Hans": "泰米尔语"
                      },
                      "value": "Tamil"
                    },
                    {
                      "label": {
                        "en_US": "Thai",
                        "pt_BR": "Tailandês",
                        "zh_Hans": "泰语"
                      },
                      "value": "Thai"
                    },
                    {
                      "label": {
                        "en_US": "Turkish",
                        "pt_BR": "Turco",
                        "zh_Hans": "土耳其语"
                      },
                      "value": "Turkish"
                    },
                    {
                      "label": {
                        "en_US": "Ukrainian",
                        "pt_BR": "Ucraniano",
                        "zh_Hans": "乌克兰语"
                      },
                      "value": "Ukrainian"
                    },
                    {
                      "label": {
                        "en_US": "Urdu",
                        "pt_BR": "Urdu",
                        "zh_Hans": "乌尔都语"
                      },
                      "value": "Urdu"
                    },
                    {
                      "label": {
                        "en_US": "Vietnamese",
                        "pt_BR": "Vietnamita",
                        "zh_Hans": "越南语"
                      },
                      "value": "Vietnamese"
                    },
                    {
                      "label": {
                        "en_US": "Welsh",
                        "pt_BR": "Galês",
                        "zh_Hans": "威尔士语"
                      },
                      "value": "Welsh"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Voice Cloning",
                  "pt_BR": "Voice Cloning",
                  "zh_Hans": "声音克隆"
                },
                "llm": "Voice Cloning"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "dupdub-dify",
                "label": {
                  "en_US": "Voice Cloning",
                  "pt_BR": "Voice Cloning",
                  "zh_Hans": "声音克隆"
                },
                "name": "VoiceCloning"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Speaker Name",
                    "pt_BR": "Speaker Name",
                    "zh_Hans": "克隆名称"
                  },
                  "label": {
                    "en_US": "Speaker Name",
                    "pt_BR": "Speaker Name",
                    "zh_Hans": "克隆名称"
                  },
                  "llm_description": "Speaker Name",
                  "max": null,
                  "min": null,
                  "name": "name",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "URL of the speech samples to be cloned. Supports wav, mp3, mp4 format",
                    "pt_BR": "URL of the speech samples to be cloned. Supports wav, mp3, mp4 format",
                    "zh_Hans": "要克隆的语音样本的URL。支持wav、mp3、mp4格式"
                  },
                  "label": {
                    "en_US": "url",
                    "pt_BR": "url",
                    "zh_Hans": "url"
                  },
                  "llm_description": "URL of the speech samples to be cloned. Supports wav, mp3, mp4 format",
                  "max": null,
                  "min": null,
                  "name": "url",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Language:English、apanese、Chinese、German、Hindi、French、Korean、Portuguese、Italian、Spanish、Indonesian、Dutch、Turkish、Filipino、Polish、Swedish、Bulgarian、Romanian、Arabic、Czech、Greek、Finnish、Croatian、Malay、Slovak、Danish、Tamil、Ukrainian、Russian",
                    "pt_BR": "Language:English、apanese、Chinese、German、Hindi、French、Korean、Portuguese、Italian、Spanish、Indonesian、Dutch、Turkish、Filipino、Polish、Swedish、Bulgarian、Romanian、Arabic、Czech、Greek、Finnish、Croatian、Malay、Slovak、Danish、Tamil、Ukrainian、Russian",
                    "zh_Hans": "支持的语言有 English、apanese、Chinese、German、Hindi、French、Korean、Portuguese、Italian、Spanish、Indonesian、Dutch、Turkish、Filipino、Polish、Swedish、Bulgarian、Romanian、Arabic、Czech、Greek、Finnish、Croatian、Malay、Slovak、Danish、Tamil、Ukrainian、Russian"
                  },
                  "label": {
                    "en_US": "Language",
                    "pt_BR": "Language",
                    "zh_Hans": "语言"
                  },
                  "llm_description": "clone in Language",
                  "max": null,
                  "min": null,
                  "name": "language",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Speaker's gender:MALE、FEMALE",
                    "pt_BR": "Speaker's gender:MALE、FEMALE",
                    "zh_Hans": "性别:MALE、FEMALE"
                  },
                  "label": {
                    "en_US": "gender",
                    "pt_BR": "gender",
                    "zh_Hans": "性别"
                  },
                  "llm_description": "clone Speaker's gender:MALE、FEMALE",
                  "max": null,
                  "min": null,
                  "name": "gender",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Speaker's age:Children、 Youth、 Adults、 Seniors",
                    "pt_BR": "Speaker's age:Children、 Youth、 Adults、 Seniors",
                    "zh_Hans": "年龄选择:Children、 Youth、 Adults、 Seniors"
                  },
                  "label": {
                    "en_US": "age",
                    "pt_BR": "age",
                    "zh_Hans": "年龄"
                  },
                  "llm_description": "clone Speaker's age:Children、 Youth、 Adults、 Seniors",
                  "max": null,
                  "min": null,
                  "name": "age",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get speaker ID",
                  "pt_BR": "Get speaker ID",
                  "zh_Hans": "获取发音人信息"
                },
                "llm": "Get speaker ID"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "dupdub-dify",
                "label": {
                  "en_US": "Get speaker ID",
                  "pt_BR": "Get speaker ID",
                  "zh_Hans": "获取发音人信息"
                },
                "name": "GetspeakerID"
              },
              "output_schema": null,
              "parameters": null
            },
            {
              "description": {
                "human": {
                  "en_US": "Speech Synthesis",
                  "pt_BR": "Speech Synthesis",
                  "zh_Hans": "语音合成"
                },
                "llm": "Speech Synthesis"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "dupdub-dify",
                "label": {
                  "en_US": "Speech Synthesis",
                  "pt_BR": "Speech Synthesis",
                  "zh_Hans": "语音合成"
                },
                "name": "SpeechSynthesis"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Speaker Name",
                    "pt_BR": "Speaker Name",
                    "zh_Hans": "克隆名称"
                  },
                  "label": {
                    "en_US": "Speaker Name",
                    "pt_BR": "Speaker Name",
                    "zh_Hans": "克隆名称"
                  },
                  "llm_description": "Speaker Name",
                  "max": null,
                  "min": null,
                  "name": "name",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Identifier for the speaker whose voice will be used.",
                    "pt_BR": "Identifier for the speaker whose voice will be used.",
                    "zh_Hans": "将使用其语音的说话者的标识符。"
                  },
                  "label": {
                    "en_US": "speaker",
                    "pt_BR": "speaker",
                    "zh_Hans": "发音人"
                  },
                  "llm_description": "Identifier for the speaker whose voice will be used.",
                  "max": null,
                  "min": null,
                  "name": "speaker",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Speed of the speech. Default is normal speed (1.0)",
                    "pt_BR": "Speed of the speech. Default is normal speed (1.0)",
                    "zh_Hans": "说话的速度。默认为正常速度1.0"
                  },
                  "label": {
                    "en_US": "speed",
                    "pt_BR": "speed",
                    "zh_Hans": "语速"
                  },
                  "llm_description": "Speed of the speech. Default is normal speed (1.0)",
                  "max": null,
                  "min": null,
                  "name": "speed",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Pitch of the speech. Default is standard pitch (0)",
                    "pt_BR": "Pitch of the speech. Default is standard pitch (0)",
                    "zh_Hans": "演讲的音高。默认值为标准间距0"
                  },
                  "label": {
                    "en_US": "pitch",
                    "pt_BR": "pitch",
                    "zh_Hans": "语调"
                  },
                  "llm_description": "Pitch of the speech. Default is standard pitch (0)",
                  "max": null,
                  "min": null,
                  "name": "pitch",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "text segments to be dubbed",
                    "pt_BR": "text segments to be dubbed",
                    "zh_Hans": "要配音的文本段"
                  },
                  "label": {
                    "en_US": "text",
                    "pt_BR": "text",
                    "zh_Hans": "文本"
                  },
                  "llm_description": "text segments to be dubbed",
                  "max": null,
                  "min": null,
                  "name": "textList",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-03T02:15:08Z",
        "version_updated_at": "2025-03-03T02:15:08Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Translate text using Baidu",
          "zh_Hans": "使用百度进行翻译"
        },
        "category": "tool",
        "created_at": "2024-12-02T05:31:27Z",
        "endpoint": {},
        "icon": "langgenius/packages/baidu_translate/_assets/icon.png",
        "index_id": "langgenius___baidu_translate",
        "install_count": 682,
        "introduction": "# Overview\nThe Baidu Translate plugin provides powerful language translation capabilities by leveraging Baidu's robust translation API. This plugin includes three tools: **Field Translate**, **Baidu Language**, and **Translate** designed to handle various translation tasks such as text translation, language detection, and field-specific translations.\n\n# Configure\n1. Go to the Dify Marketplace.\n2. Search for the Baidu Translate Plugin.\n3. Click \"Install\" to add the plugin to your workspace.\n![](./_assets/baidu-translate_install.PNG)\nBefore using the tools, you need to authorize the plugin with your Baidu Translate API credentials:\n1. Go to [Baidu Translate](https://api.fanyi.baidu.com/register), and register as a developer.\n2. Add any of the Baidu Translate tools (Field Translate, Baidu Language, or Translate) to your workflow.\n3. Click on the \"To authorize\" button in the tool configuration panel.\n4. Enter your Baidu Translate credentials:\n  - AppID: Obtain it from [Baidu Translate API](https://api.fanyi.baidu.com/).\n  - Secret: Generate it from [Baidu Translate API](https://api.fanyi.baidu.com/).\n5. Save your credentials to complete the authorization process.\n6. Fill in the required parameters for each tool, such as the text to translate, source and destination languages, and any other relevant information.\n![](./_assets/baidu-translate_field_language.png)\n![](./_assets/baidu-translate_baidu_language.png)\n![](./_assets/baidu-translate_translate.png)",
        "label": {
          "en_US": "Baidu Translate",
          "zh_Hans": "百度翻译"
        },
        "latest_package_identifier": "langgenius/baidu_translate:0.0.2@93f7766111af3d2494f35de4efe473e60a349090f4b497a0f54f2f48b75a9002",
        "latest_version": "0.0.2",
        "model": {},
        "name": "baidu_translate",
        "org": "langgenius",
        "plugin_id": "langgenius/baidu_translate",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/baidu_translate.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "utilities"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "Baidu translate appid",
                "zh_Hans": "Baidu translate appid"
              },
              "name": "appid",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Baidu translate appid",
                "zh_Hans": "请输入你的百度翻译 appid"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://api.fanyi.baidu.com"
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "Baidu translate secret",
                "zh_Hans": "Baidu translate secret"
              },
              "name": "secret",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Baidu translate secret",
                "zh_Hans": "请输入你的百度翻译 secret"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://api.fanyi.baidu.com"
            }
          ],
          "identity": {
            "author": "Xiao Ley",
            "description": {
              "en_US": "Translate text using Baidu",
              "zh_Hans": "使用百度进行翻译"
            },
            "icon": "icon.png",
            "label": {
              "en_US": "Baidu Translate",
              "zh_Hans": "百度翻译"
            },
            "name": "baidu_translate",
            "tags": [
              "utilities"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool for Baidu Language, support Chinese, English, Japanese, Korean, Thai, Vietnamese and Russian",
                  "zh_Hans": "使用百度进行语种识别，支持的语种：中文、英语、日语、韩语、泰语、越南语和俄语"
                },
                "llm": "A tool for Baidu Language"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Xiao Ley",
                "label": {
                  "en_US": "Baidu Language",
                  "zh_Hans": "百度语种识别"
                },
                "name": "language"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Text content to be recognized",
                    "zh_Hans": "需要识别语言的文本内容"
                  },
                  "label": {
                    "en_US": "Text content",
                    "zh_Hans": "文本内容"
                  },
                  "llm_description": "Text content to be recognized",
                  "max": null,
                  "min": null,
                  "name": "q",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "Chinese",
                  "form": "form",
                  "human_description": {
                    "en_US": "Describe the language used to identify the results",
                    "zh_Hans": "描述识别结果所用的语言"
                  },
                  "label": {
                    "en_US": "Description language",
                    "zh_Hans": "描述语言"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "description_language",
                  "options": [
                    {
                      "label": {
                        "en_US": "Chinese",
                        "zh_Hans": "中文"
                      },
                      "value": "Chinese"
                    },
                    {
                      "label": {
                        "en_US": "English",
                        "zh_Hans": "英语"
                      },
                      "value": "English"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for Baidu Translate",
                  "zh_Hans": "百度翻译"
                },
                "llm": "A tool for Baidu Translate"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Xiao Ley",
                "label": {
                  "en_US": "Translate",
                  "zh_Hans": "百度翻译"
                },
                "name": "translate"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Text content to be translated",
                    "zh_Hans": "需要翻译的文本内容"
                  },
                  "label": {
                    "en_US": "Text content",
                    "zh_Hans": "文本内容"
                  },
                  "llm_description": "Text content to be translated",
                  "max": null,
                  "min": null,
                  "name": "q",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "auto",
                  "form": "form",
                  "human_description": {
                    "en_US": "The source language of the input text",
                    "zh_Hans": "输入的文本的源语言"
                  },
                  "label": {
                    "en_US": "source language",
                    "zh_Hans": "源语言"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "from",
                  "options": [
                    {
                      "label": {
                        "en_US": "auto",
                        "zh_Hans": "自动检测"
                      },
                      "value": "auto"
                    },
                    {
                      "label": {
                        "en_US": "Chinese",
                        "zh_Hans": "中文"
                      },
                      "value": "zh"
                    },
                    {
                      "label": {
                        "en_US": "English",
                        "zh_Hans": "英语"
                      },
                      "value": "en"
                    },
                    {
                      "label": {
                        "en_US": "Traditional Chinese",
                        "zh_Hans": "繁体中文"
                      },
                      "value": "cht"
                    },
                    {
                      "label": {
                        "en_US": "Yue",
                        "zh_Hans": "粤语"
                      },
                      "value": "yue"
                    },
                    {
                      "label": {
                        "en_US": "Wyw",
                        "zh_Hans": "文言文"
                      },
                      "value": "wyw"
                    },
                    {
                      "label": {
                        "en_US": "Japanese",
                        "zh_Hans": "日语"
                      },
                      "value": "jp"
                    },
                    {
                      "label": {
                        "en_US": "Korean",
                        "zh_Hans": "韩语"
                      },
                      "value": "kor"
                    },
                    {
                      "label": {
                        "en_US": "French",
                        "zh_Hans": "法语"
                      },
                      "value": "fra"
                    },
                    {
                      "label": {
                        "en_US": "Spanish",
                        "zh_Hans": "西班牙语"
                      },
                      "value": "spa"
                    },
                    {
                      "label": {
                        "en_US": "Thai",
                        "zh_Hans": "泰语"
                      },
                      "value": "th"
                    },
                    {
                      "label": {
                        "en_US": "Arabic",
                        "zh_Hans": "阿拉伯语"
                      },
                      "value": "ara"
                    },
                    {
                      "label": {
                        "en_US": "Russian",
                        "zh_Hans": "俄语"
                      },
                      "value": "ru"
                    },
                    {
                      "label": {
                        "en_US": "Portuguese",
                        "zh_Hans": "葡萄牙语"
                      },
                      "value": "pt"
                    },
                    {
                      "label": {
                        "en_US": "German",
                        "zh_Hans": "德语"
                      },
                      "value": "de"
                    },
                    {
                      "label": {
                        "en_US": "Italian",
                        "zh_Hans": "意大利语"
                      },
                      "value": "it"
                    },
                    {
                      "label": {
                        "en_US": "Greek",
                        "zh_Hans": "希腊语"
                      },
                      "value": "el"
                    },
                    {
                      "label": {
                        "en_US": "Dutch",
                        "zh_Hans": "荷兰语"
                      },
                      "value": "nl"
                    },
                    {
                      "label": {
                        "en_US": "Polish",
                        "zh_Hans": "波兰语"
                      },
                      "value": "pl"
                    },
                    {
                      "label": {
                        "en_US": "Bulgarian",
                        "zh_Hans": "保加利亚语"
                      },
                      "value": "bul"
                    },
                    {
                      "label": {
                        "en_US": "Estonian",
                        "zh_Hans": "爱沙尼亚语"
                      },
                      "value": "est"
                    },
                    {
                      "label": {
                        "en_US": "Danish",
                        "zh_Hans": "丹麦语"
                      },
                      "value": "dan"
                    },
                    {
                      "label": {
                        "en_US": "Finnish",
                        "zh_Hans": "芬兰语"
                      },
                      "value": "fin"
                    },
                    {
                      "label": {
                        "en_US": "Czech",
                        "zh_Hans": "捷克语"
                      },
                      "value": "cs"
                    },
                    {
                      "label": {
                        "en_US": "Romanian",
                        "zh_Hans": "罗马尼亚语"
                      },
                      "value": "rom"
                    },
                    {
                      "label": {
                        "en_US": "Slovak",
                        "zh_Hans": "斯洛文尼亚语"
                      },
                      "value": "slo"
                    },
                    {
                      "label": {
                        "en_US": "Swedish",
                        "zh_Hans": "瑞典语"
                      },
                      "value": "swe"
                    },
                    {
                      "label": {
                        "en_US": "Hungarian",
                        "zh_Hans": "匈牙利语"
                      },
                      "value": "hu"
                    },
                    {
                      "label": {
                        "en_US": "Vietnamese",
                        "zh_Hans": "越南语"
                      },
                      "value": "vie"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "en",
                  "form": "form",
                  "human_description": {
                    "en_US": "The destination language of the input text",
                    "zh_Hans": "输入文本的目标语言"
                  },
                  "label": {
                    "en_US": "destination language",
                    "zh_Hans": "目标语言"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "to",
                  "options": [
                    {
                      "label": {
                        "en_US": "Chinese",
                        "zh_Hans": "中文"
                      },
                      "value": "zh"
                    },
                    {
                      "label": {
                        "en_US": "English",
                        "zh_Hans": "英语"
                      },
                      "value": "en"
                    },
                    {
                      "label": {
                        "en_US": "Traditional Chinese",
                        "zh_Hans": "繁体中文"
                      },
                      "value": "cht"
                    },
                    {
                      "label": {
                        "en_US": "Yue",
                        "zh_Hans": "粤语"
                      },
                      "value": "yue"
                    },
                    {
                      "label": {
                        "en_US": "Wyw",
                        "zh_Hans": "文言文"
                      },
                      "value": "wyw"
                    },
                    {
                      "label": {
                        "en_US": "Japanese",
                        "zh_Hans": "日语"
                      },
                      "value": "jp"
                    },
                    {
                      "label": {
                        "en_US": "Korean",
                        "zh_Hans": "韩语"
                      },
                      "value": "kor"
                    },
                    {
                      "label": {
                        "en_US": "French",
                        "zh_Hans": "法语"
                      },
                      "value": "fra"
                    },
                    {
                      "label": {
                        "en_US": "Spanish",
                        "zh_Hans": "西班牙语"
                      },
                      "value": "spa"
                    },
                    {
                      "label": {
                        "en_US": "Thai",
                        "zh_Hans": "泰语"
                      },
                      "value": "th"
                    },
                    {
                      "label": {
                        "en_US": "Arabic",
                        "zh_Hans": "阿拉伯语"
                      },
                      "value": "ara"
                    },
                    {
                      "label": {
                        "en_US": "Russian",
                        "zh_Hans": "俄语"
                      },
                      "value": "ru"
                    },
                    {
                      "label": {
                        "en_US": "Portuguese",
                        "zh_Hans": "葡萄牙语"
                      },
                      "value": "pt"
                    },
                    {
                      "label": {
                        "en_US": "German",
                        "zh_Hans": "德语"
                      },
                      "value": "de"
                    },
                    {
                      "label": {
                        "en_US": "Italian",
                        "zh_Hans": "意大利语"
                      },
                      "value": "it"
                    },
                    {
                      "label": {
                        "en_US": "Greek",
                        "zh_Hans": "希腊语"
                      },
                      "value": "el"
                    },
                    {
                      "label": {
                        "en_US": "Dutch",
                        "zh_Hans": "荷兰语"
                      },
                      "value": "nl"
                    },
                    {
                      "label": {
                        "en_US": "Polish",
                        "zh_Hans": "波兰语"
                      },
                      "value": "pl"
                    },
                    {
                      "label": {
                        "en_US": "Bulgarian",
                        "zh_Hans": "保加利亚语"
                      },
                      "value": "bul"
                    },
                    {
                      "label": {
                        "en_US": "Estonian",
                        "zh_Hans": "爱沙尼亚语"
                      },
                      "value": "est"
                    },
                    {
                      "label": {
                        "en_US": "Danish",
                        "zh_Hans": "丹麦语"
                      },
                      "value": "dan"
                    },
                    {
                      "label": {
                        "en_US": "Finnish",
                        "zh_Hans": "芬兰语"
                      },
                      "value": "fin"
                    },
                    {
                      "label": {
                        "en_US": "Czech",
                        "zh_Hans": "捷克语"
                      },
                      "value": "cs"
                    },
                    {
                      "label": {
                        "en_US": "Romanian",
                        "zh_Hans": "罗马尼亚语"
                      },
                      "value": "rom"
                    },
                    {
                      "label": {
                        "en_US": "Slovak",
                        "zh_Hans": "斯洛文尼亚语"
                      },
                      "value": "slo"
                    },
                    {
                      "label": {
                        "en_US": "Swedish",
                        "zh_Hans": "瑞典语"
                      },
                      "value": "swe"
                    },
                    {
                      "label": {
                        "en_US": "Hungarian",
                        "zh_Hans": "匈牙利语"
                      },
                      "value": "hu"
                    },
                    {
                      "label": {
                        "en_US": "Vietnamese",
                        "zh_Hans": "越南语"
                      },
                      "value": "vie"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for Baidu Field translate (Currently, the fields of \"novel\" and \"wiki\" only support Chinese to English translation. If the language direction is set to English to Chinese, the default output will be a universal translation result).",
                  "zh_Hans": "百度领域翻译，提供多种领域的文本翻译（目前“网络文学领域”和“人文社科领域”仅支持中到英，如设置语言方向为英到中，则默认输出通用翻译结果）"
                },
                "llm": "A tool for Baidu Field translate"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Xiao Ley",
                "label": {
                  "en_US": "Field translate",
                  "zh_Hans": "百度领域翻译"
                },
                "name": "field_translate"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Text content to be translated",
                    "zh_Hans": "需要翻译的文本内容"
                  },
                  "label": {
                    "en_US": "Text content",
                    "zh_Hans": "文本内容"
                  },
                  "llm_description": "Text content to be translated",
                  "max": null,
                  "min": null,
                  "name": "q",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "auto",
                  "form": "form",
                  "human_description": {
                    "en_US": "The source language of the input text",
                    "zh_Hans": "输入的文本的源语言"
                  },
                  "label": {
                    "en_US": "source language",
                    "zh_Hans": "源语言"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "from",
                  "options": [
                    {
                      "label": {
                        "en_US": "auto",
                        "zh_Hans": "自动检测"
                      },
                      "value": "auto"
                    },
                    {
                      "label": {
                        "en_US": "Chinese",
                        "zh_Hans": "中文"
                      },
                      "value": "zh"
                    },
                    {
                      "label": {
                        "en_US": "English",
                        "zh_Hans": "英语"
                      },
                      "value": "en"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "en",
                  "form": "form",
                  "human_description": {
                    "en_US": "The destination language of the input text",
                    "zh_Hans": "输入文本的目标语言"
                  },
                  "label": {
                    "en_US": "destination language",
                    "zh_Hans": "目标语言"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "to",
                  "options": [
                    {
                      "label": {
                        "en_US": "Chinese",
                        "zh_Hans": "中文"
                      },
                      "value": "zh"
                    },
                    {
                      "label": {
                        "en_US": "English",
                        "zh_Hans": "英语"
                      },
                      "value": "en"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "novel",
                  "form": "form",
                  "human_description": {
                    "en_US": "The domain of the input text",
                    "zh_Hans": "输入文本的领域"
                  },
                  "label": {
                    "en_US": "domain",
                    "zh_Hans": "领域"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "domain",
                  "options": [
                    {
                      "label": {
                        "en_US": "it",
                        "zh_Hans": "信息技术领域"
                      },
                      "value": "it"
                    },
                    {
                      "label": {
                        "en_US": "finance",
                        "zh_Hans": "金融财经领域"
                      },
                      "value": "finance"
                    },
                    {
                      "label": {
                        "en_US": "machinery",
                        "zh_Hans": "机械制造领域"
                      },
                      "value": "machinery"
                    },
                    {
                      "label": {
                        "en_US": "senimed",
                        "zh_Hans": "生物医药领域"
                      },
                      "value": "senimed"
                    },
                    {
                      "label": {
                        "en_US": "novel (only support Chinese to English translation)",
                        "zh_Hans": "网络文学领域（仅支持中到英）"
                      },
                      "value": "novel"
                    },
                    {
                      "label": {
                        "en_US": "academic",
                        "zh_Hans": "学术论文领域"
                      },
                      "value": "academic"
                    },
                    {
                      "label": {
                        "en_US": "aerospace",
                        "zh_Hans": "航空航天领域"
                      },
                      "value": "aerospace"
                    },
                    {
                      "label": {
                        "en_US": "wiki (only support Chinese to English translation)",
                        "zh_Hans": "人文社科领域（仅支持中到英）"
                      },
                      "value": "wiki"
                    },
                    {
                      "label": {
                        "en_US": "news",
                        "zh_Hans": "新闻咨询领域"
                      },
                      "value": "news"
                    },
                    {
                      "label": {
                        "en_US": "law",
                        "zh_Hans": "法律法规领域"
                      },
                      "value": "law"
                    },
                    {
                      "label": {
                        "en_US": "contract",
                        "zh_Hans": "合同领域"
                      },
                      "value": "contract"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:09:57Z",
        "version_updated_at": "2025-02-17T07:09:57Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Nomic"
        },
        "category": "model",
        "created_at": "2025-02-17T06:57:32Z",
        "endpoint": {},
        "icon": "langgenius/packages/nomic/_assets/icon_s_en.png",
        "index_id": "langgenius___nomic",
        "install_count": 678,
        "introduction": "",
        "label": {
          "en_US": "nomic"
        },
        "latest_package_identifier": "langgenius/nomic:0.0.3@c14290d2a4a3b752127ba8496fe5cfa9eb8ebbfa6bac17be00ddb66c95b2b6ce",
        "latest_version": "0.0.3",
        "model": {
          "background": "#EFF1FE",
          "configurate_methods": [
            "predefined-model"
          ],
          "description": {
            "en_US": "Nomic"
          },
          "help": {
            "title": {
              "en_US": "Get your API key from Nomic Atlas",
              "zh_Hans": "从Nomic Atlas获取 API Key"
            },
            "url": {
              "en_US": "https://atlas.nomic.ai/data"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.svg"
          },
          "icon_small": {
            "en_US": "icon_s_en.png"
          },
          "label": {
            "en_US": "Nomic Atlas",
            "zh_Hans": "Nomic Atlas"
          },
          "model_credential_schema": null,
          "models": [
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "nomic-embed-text-v1.5"
              },
              "model": "nomic-embed-text-v1.5",
              "model_properties": {
                "context_size": 8192
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.1",
                "output": null,
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "nomic-embed-text-v1"
              },
              "model": "nomic-embed-text-v1",
              "model_properties": {
                "context_size": 8192
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.1",
                "output": null,
                "unit": "0.000001"
              }
            }
          ],
          "position": {},
          "provider": "nomic",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "nomic_api_key"
              }
            ]
          },
          "supported_model_types": [
            "text-embedding"
          ]
        },
        "name": "nomic",
        "org": "langgenius",
        "plugin_id": "langgenius/nomic",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/nomic.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": false,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-02-28T04:09:51Z",
        "version_updated_at": "2025-02-28T04:09:51Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "rookie rss 多平台新闻聚合插件",
          "ja_JP": "rookie rss 多平台新闻聚合插件",
          "pt_BR": "rookie rss 多平台新闻聚合插件",
          "zh_Hans": "rookie rss 多平台新闻聚合插件"
        },
        "category": "tool",
        "created_at": "2025-03-19T18:39:10Z",
        "endpoint": {},
        "icon": "jaguarliuu/packages/rookie_rss/_assets/rss.svg",
        "index_id": "jaguarliuu___rookie_rss",
        "install_count": 673,
        "introduction": "## rookie_rss\n\n> 一款多平台新闻聚合插件\n\n**Author:** jaguarliuu\n**Version:** 0.0.1\n**Type:** tool\n\n### Description\n本插件信息来源基于开源项目[DailyHotApi](https://github.com/imsyy/DailyHotApi)\n方便用户无代码的方式获取多平台热搜与热点新闻。\n\n\n### Steps\n1. 下载/安装插件\n2. 配置DailyHotApi地址，默认为`https://api-hot.imsyy.top/`\n![](./_assets/1.png)\n    > DailyHotApi 的手动部署请参考[DailyHotApi](https://github.com/imsyy/DailyHotApi)\n    >\n\n3. 在工作流中引入，并完成选择平台和数量即可\n![](./_assets/2.png)\n\n\n\n",
        "label": {
          "en_US": "rookie_rss",
          "ja_JP": "rookie_rss",
          "pt_BR": "rookie_rss",
          "zh_Hans": "rookie_rss"
        },
        "latest_package_identifier": "jaguarliuu/rookie_rss:0.0.1@952c543edd18220f33741a1f3f5625efbd5a5149032226ea8984843601da6fea",
        "latest_version": "0.0.1",
        "model": {},
        "name": "rookie_rss",
        "org": "jaguarliuu",
        "plugin_id": "jaguarliuu/rookie_rss",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/rookie_rss.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": "https://api-hot.imsyy.top/",
              "help": {
                "en_US": "Get your Daily Hot URL from https://github.com/imsyy/DailyHotApi",
                "zh_Hans": "从 https://github.com/imsyy/DailyHotApi 获取你的每日热榜 URL"
              },
              "label": {
                "en_US": "Daily Hot URL",
                "zh_Hans": "每日热榜 URL"
              },
              "name": "daily_hot_url",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Daily Hot URL",
                "zh_Hans": "请配置你的每日热榜 URL"
              },
              "required": false,
              "scope": null,
              "type": "text-input",
              "url": "https://github.com/imsyy/DailyHotApi"
            }
          ],
          "identity": {
            "author": "jaguarliuu",
            "description": {
              "en_US": "rookie rss 多平台新闻聚合插件",
              "pt_BR": "rookie rss 多平台新闻聚合插件",
              "zh_Hans": "rookie rss 多平台新闻聚合插件"
            },
            "icon": "rss.svg",
            "label": {
              "en_US": "rookie_rss",
              "pt_BR": "rookie_rss",
              "zh_Hans": "rookie_rss"
            },
            "name": "rookie_rss",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "rookie rss 多平台新闻聚合插件",
                  "pt_BR": "rookie rss 多平台新闻聚合插件",
                  "zh_Hans": "rookie rss 多平台新闻聚合插件"
                },
                "llm": "rookie rss 多平台新闻聚合插件"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "jaguarliuu",
                "label": {
                  "en_US": "rookie_rss",
                  "pt_BR": "rookie_rss",
                  "zh_Hans": "rookie_rss"
                },
                "name": "rookie_rss"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "platform name",
                    "zh_Hans": "平台名称"
                  },
                  "label": {
                    "en_US": "platform",
                    "zh_Hans": "平台名称"
                  },
                  "llm_description": "平台名称",
                  "max": null,
                  "min": null,
                  "name": "platform",
                  "options": [
                    {
                      "label": {
                        "en_US": "zhihu",
                        "zh_Hans": "知乎"
                      },
                      "value": "zhihu"
                    },
                    {
                      "label": {
                        "en_US": "juejin",
                        "zh_Hans": "掘金"
                      },
                      "value": "juejin"
                    },
                    {
                      "label": {
                        "en_US": "bilibili",
                        "zh_Hans": "bilibili"
                      },
                      "value": "bilibili"
                    },
                    {
                      "label": {
                        "en_US": "ac_fun",
                        "zh_Hans": "ac_fun"
                      },
                      "value": "acfun"
                    },
                    {
                      "label": {
                        "en_US": "weibo",
                        "zh_Hans": "微博"
                      },
                      "value": "weibo"
                    },
                    {
                      "label": {
                        "en_US": "toutiao",
                        "zh_Hans": "今日头条"
                      },
                      "value": "toutiao"
                    },
                    {
                      "label": {
                        "en_US": "36kr",
                        "zh_Hans": "36kr"
                      },
                      "value": "36kr"
                    },
                    {
                      "label": {
                        "en_US": "huxiu",
                        "zh_Hans": "虎嗅"
                      },
                      "value": "huxiu"
                    },
                    {
                      "label": {
                        "en_US": "hellogithub",
                        "zh_Hans": "hellogithub"
                      },
                      "value": "hellogithub"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "result number",
                    "zh_Hans": "返回结果数量"
                  },
                  "label": {
                    "en_US": "result number",
                    "zh_Hans": "返回结果数量"
                  },
                  "llm_description": "返回结果数量",
                  "max": 10,
                  "min": 1,
                  "name": "result_num",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-19T18:39:22Z",
        "version_updated_at": "2025-03-19T18:39:22Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "search information by OpenSearch",
          "ja_JP": "search information by OpenSearch",
          "pt_BR": "search information by OpenSearch",
          "zh_Hans": "使用 OpenSearch 检索信息"
        },
        "category": "tool",
        "created_at": "2025-03-21T08:50:01Z",
        "endpoint": {},
        "icon": "mark/packages/opensearch/_assets/icon.svg",
        "index_id": "mark___opensearch",
        "install_count": 669,
        "introduction": "## OpenSearch plugin for Dify\n\n\n**Author:** [mark](https://github.com/exitNA)  \n**Version:** 0.0.2  \n**Type:** tool  \n**Github Repo:** [https://github.com/exitNA/opensearch](https://github.com/exitNA/opensearch)  \n**Github Issues:** [issues](https://github.com/exitNA/opensearch/issues)  \n\n\n---\n\n### Description\nThis plugin is used to search data in OpenSearch.\n\n![opensearch_plugin](_assets/home.png)\n\n## Usage\n1. setup your credential\n2. use tool in workflow\n\n### credential\n![credential](_assets/credential.png)\n\n- endpoint: The endpoint of OpenSearch, such as localhost:9200\n- user: The user of OpenSearch, such as xiaoming\n- password: The password of OpenSearch user\n\n### Query\n![query](_assets/query.png)\n\n- index: The index of OpenSearch\n- query: The OpenSearch query dsl\n- from: The start index of OpenSearch\n- size: The size of OpenSearch\n\n**output**\n![output variable](_assets/output-variable.png)\n- total: number of total matched docs\n- message: inner status message for debug\n- result: the result document list\n\n> More information about OpenSearch query dsl and paginate\n> https://opensearch.org/docs/latest/query-dsl/\n> https://opensearch.org/docs/latest/search-plugins/searching-data/paginate/#the-from-and-size-parameters\n",
        "label": {
          "en_US": "OpenSearch",
          "ja_JP": "OpenSearch",
          "pt_BR": "OpenSearch",
          "zh_Hans": "OpenSearch"
        },
        "latest_package_identifier": "mark/opensearch:0.0.2@e7b6e9785598034c8ddf132f8a51c02471afd48580cf3faae103756d44b23e3f",
        "latest_version": "0.0.2",
        "model": {},
        "name": "opensearch",
        "org": "mark",
        "plugin_id": "mark/opensearch",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/opensearch.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Get your OpenSearch endpoint from your provider",
                "pt_BR": "Get your OpenSearch endpoint from your provider",
                "zh_Hans": "从您的OpenSearch服务商那里获取您的endpoint"
              },
              "label": {
                "en_US": "Endpoint",
                "pt_BR": "Endpoint",
                "zh_Hans": "服务地址"
              },
              "name": "endpoint",
              "options": null,
              "placeholder": {
                "en_US": "host:port,...",
                "pt_BR": "host:port,...",
                "zh_Hans": "host:port,..."
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": "https://opensearch-project.github.io/opensearch-py/api-ref/clients/opensearch_client.html"
            },
            {
              "default": null,
              "help": {
                "en_US": "Get your user name",
                "pt_BR": "Get your user name",
                "zh_Hans": "您在OpenSearch服务商那里设置的账号名称"
              },
              "label": {
                "en_US": "User",
                "pt_BR": "User",
                "zh_Hans": "用户名"
              },
              "name": "user",
              "options": null,
              "placeholder": {
                "en_US": "Please input your user name",
                "pt_BR": "Please input your user name",
                "zh_Hans": "请输入你的用户名"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": "https://opensearch-project.github.io/opensearch-py/api-ref/clients/opensearch_client.html"
            },
            {
              "default": null,
              "help": {
                "en_US": "Get your password",
                "pt_BR": "Get your password",
                "zh_Hans": "您在OpenSearch服务商那里设置的密码"
              },
              "label": {
                "en_US": "password",
                "pt_BR": "password",
                "zh_Hans": "密码"
              },
              "name": "password",
              "options": null,
              "placeholder": {
                "en_US": "Please input your password",
                "pt_BR": "Please input your password",
                "zh_Hans": "请输入你的密码"
              },
              "required": false,
              "scope": null,
              "type": "secret-input",
              "url": "https://opensearch-project.github.io/opensearch-py/api-ref/clients/opensearch_client.html"
            }
          ],
          "identity": {
            "author": "mark",
            "description": {
              "en_US": "search information by OpenSearch",
              "pt_BR": "search information by OpenSearch",
              "zh_Hans": "search information by OpenSearch"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "OpenSearch",
              "pt_BR": "OpenSearch",
              "zh_Hans": "OpenSearch"
            },
            "name": "opensearch",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "search information by OpenSearch",
                  "pt_BR": "search information by OpenSearch",
                  "zh_Hans": "使用 OpenSearch 检索信息"
                },
                "llm": "search information by OpenSearch"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "mark",
                "label": {
                  "en_US": "OpenSearch Query",
                  "pt_BR": "OpenSearch Query",
                  "zh_Hans": "OpenSearch查询"
                },
                "name": "opensearch"
              },
              "output_schema": {
                "properties": {
                  "message": {
                    "type": "string"
                  },
                  "result": {
                    "items": {
                      "type": "object"
                    },
                    "type": "array"
                  },
                  "total": {
                    "type": "number"
                  }
                },
                "type": "object"
              },
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Index Name",
                    "pt_BR": "Index Name",
                    "zh_Hans": "索引名称"
                  },
                  "label": {
                    "en_US": "Index Name",
                    "pt_BR": "Index Name",
                    "zh_Hans": "索引名称"
                  },
                  "llm_description": "index name",
                  "max": null,
                  "min": null,
                  "name": "index",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "DSL Query",
                    "pt_BR": "DSL Query",
                    "zh_Hans": "查询DSL"
                  },
                  "label": {
                    "en_US": "DSL Query",
                    "pt_BR": "DSL Query",
                    "zh_Hans": "查询DSL"
                  },
                  "llm_description": "DSL Query",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 0,
                  "form": "llm",
                  "human_description": {
                    "en_US": "From",
                    "pt_BR": "From",
                    "zh_Hans": "查询的起始位置(用于分页)"
                  },
                  "label": {
                    "en_US": "From",
                    "zh_Hans": "查询的起始位置(用于分页)"
                  },
                  "llm_description": "OpenSearch Query from",
                  "max": null,
                  "min": null,
                  "name": "from",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 10,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Size",
                    "pt_BR": "Size",
                    "zh_Hans": "最大返回文档数量"
                  },
                  "label": {
                    "en_US": "Size",
                    "pt_BR": "Size",
                    "zh_Hans": "最大返回文档数量"
                  },
                  "llm_description": "OpenSearch Query Size",
                  "max": null,
                  "min": null,
                  "name": "size",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-21T08:50:13Z",
        "version_updated_at": "2025-03-21T08:50:13Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "together.ai"
        },
        "category": "model",
        "created_at": "2024-12-05T06:40:56Z",
        "endpoint": {},
        "icon": "langgenius/packages/togetherai/_assets/togetherai_square.svg",
        "index_id": "langgenius___togetherai",
        "install_count": 660,
        "introduction": "## Overview\n[Together.ai](http://together.ai/) provides a cloud-based platform for building, training, and deploying AI models, with a focus on open-source LLMs and the ability to fine-tune existing models or build custom ones from scratch. This plugin provides access to [together.ai's](http://together.ai/) LLMs via model names and API keys.\n\n## Configure\nTo configure [together.ai](http://together.ai/), specify the Model (Type and Name), your API Key (from [together.ai](http://together.ai/)), and the desired completion and size parameters. Save your settings.\n\n<img src=\"./_assets/togetherai-01.png\" width=\"400\" />\n",
        "label": {
          "en_US": "Together.AI"
        },
        "latest_package_identifier": "langgenius/togetherai:0.0.2@93e8572b8180c0285ef630820931773c65fd54b1174d5e5fc6ea77b57dc93849",
        "latest_version": "0.0.2",
        "model": {
          "background": "#F1EFED",
          "configurate_methods": [
            "customizable-model"
          ],
          "description": {
            "en_US": "together.ai"
          },
          "help": {
            "title": {
              "en_US": "Get your API key from together.ai",
              "zh_Hans": "从 together.ai 获取 API Key"
            },
            "url": {
              "en_US": "https://api.together.xyz/"
            }
          },
          "icon_large": {
            "en_US": "togetherai.svg"
          },
          "icon_small": {
            "en_US": "togetherai_square.svg"
          },
          "label": {
            "en_US": "together.ai"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              },
              {
                "default": "chat",
                "label": {
                  "en_US": "Completion mode"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Completion",
                      "zh_Hans": "补全"
                    },
                    "show_on": [],
                    "value": "completion"
                  },
                  {
                    "label": {
                      "en_US": "Chat",
                      "zh_Hans": "对话"
                    },
                    "show_on": [],
                    "value": "chat"
                  }
                ],
                "placeholder": {
                  "en_US": "Select completion mode",
                  "zh_Hans": "选择对话类型"
                },
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "select",
                "variable": "mode"
              },
              {
                "default": "4096",
                "label": {
                  "en_US": "Model context size",
                  "zh_Hans": "模型上下文长度"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Model context size",
                  "zh_Hans": "在此输入您的模型上下文长度"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "context_size"
              },
              {
                "default": "4096",
                "label": {
                  "en_US": "Upper bound for max tokens",
                  "zh_Hans": "最大 token 上限"
                },
                "max_length": 0,
                "options": [],
                "placeholder": null,
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "text-input",
                "variable": "max_tokens_to_sample"
              }
            ],
            "model": {
              "label": {
                "en_US": "Model Name",
                "zh_Hans": "模型名称"
              },
              "placeholder": {
                "en_US": "Enter full model name",
                "zh_Hans": "输入模型全称"
              }
            }
          },
          "models": [],
          "provider": "togetherai",
          "provider_credential_schema": null,
          "supported_model_types": [
            "llm"
          ]
        },
        "name": "togetherai",
        "org": "langgenius",
        "plugin_id": "langgenius/togetherai",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/togetherai.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-02-17T06:55:06Z",
        "version_updated_at": "2025-02-17T06:55:06Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Models provided by 360 AI.",
          "zh_Hans": "360 智脑提供的模型。"
        },
        "category": "model",
        "created_at": "2024-12-06T11:12:55Z",
        "endpoint": {},
        "icon": "langgenius/packages/zhinao/_assets/icon_s_en.svg",
        "index_id": "langgenius___zhinao",
        "install_count": 653,
        "introduction": "",
        "label": {
          "en_US": "360 AI",
          "zh_Hans": "360 智脑"
        },
        "latest_package_identifier": "langgenius/zhinao:0.0.2@722bda8d2e769d5f68f924f77e0c0c185b525c8dff78aa5185ababa4507b549d",
        "latest_version": "0.0.2",
        "model": {
          "background": "#e3f0ff",
          "configurate_methods": [
            "predefined-model"
          ],
          "description": {
            "en_US": "Models provided by 360 AI.",
            "zh_Hans": "360 智脑提供的模型。"
          },
          "help": {
            "title": {
              "en_US": "Get your API Key from 360 AI.",
              "zh_Hans": "从360 智脑获取 API Key"
            },
            "url": {
              "en_US": "https://ai.360.com/platform/keys"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.svg"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "360 AI",
            "zh_Hans": "360 智脑"
          },
          "model_credential_schema": null,
          "models": [
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "360gpt-turbo-responsibility-8k",
                "zh_Hans": "360gpt-turbo-responsibility-8k"
              },
              "model": "360gpt-turbo-responsibility-8k",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "360gpt-turbo",
                "zh_Hans": "360gpt-turbo"
              },
              "model": "360gpt-turbo",
              "model_properties": {
                "context_size": 2048,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "360gpt2-pro",
                "zh_Hans": "360gpt2-pro"
              },
              "model": "360gpt2-pro",
              "model_properties": {
                "context_size": 2048,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": null
            }
          ],
          "position": {
            "llm": [
              "360gpt2-pro",
              "360gpt-turbo",
              "360gpt-turbo-responsibility-8k"
            ]
          },
          "provider": "zhinao",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              }
            ]
          },
          "supported_model_types": [
            "llm"
          ]
        },
        "name": "zhinao",
        "org": "langgenius",
        "plugin_id": "langgenius/zhinao",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/zhinao.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-02-17T06:58:13Z",
        "version_updated_at": "2025-02-17T06:58:13Z"
      },
      {
        "agent_strategy": {},
        "badges": [
          "partner"
        ],
        "brief": {
          "en_US": "Tool for integration with e2b.dev.",
          "zh_Hans": "用于集成 e2b.dev 的工具插件。"
        },
        "category": "tool",
        "created_at": "2025-02-12T08:00:34Z",
        "endpoint": {},
        "icon": "langgenius/packages/e2b/_assets/icon.png",
        "index_id": "langgenius___e2b",
        "install_count": 639,
        "introduction": "## e2b\n\n### Description\n\nThis is a plugin for Dify to integrate with e2b.dev. It allows you to run code in a sandboxed environment.\n\n### Features\n\n- Run code in a sandboxed environment.\n- Run command in a sandboxed environment.\n- Upload file to a sandboxed environment.\n- Download file from a sandboxed environment.\n\n### Usage\n\nLogin to [e2b.dev](https://e2b.dev), get your API key from `Keys` page.\n\n![image](./_assets/e2b_01.png)\n\nInstall this plugin in Dify, click on `To Authorize` button, paste your API key, and click on `Authorize` button.\n\n![image](./_assets/e2b_02.png)\n\n![image](./_assets/e2b_03.png)\n\nThen you can use the tool in your workflow or other apps.\n\n![image](./_assets/e2b_04.png)\n\n#### Run Code\n\nCurrently supports Python and JavaScript code.\n\n![image](./_assets/e2b_05.png)\n\n![image](./_assets/e2b_06.png)\n\n#### Run Command\n\nRun a Linux command in a sandboxed environment.\n\n![image](./_assets/e2b_07.png)\n\n#### Upload/Download File\n\nUpload a file to a sandboxed environment.\n\n![image](./_assets/e2b_08.png)\n\nDownload a file from a sandboxed environment.\n\n![image](./_assets/e2b_09.png)\n\nNote that these two file operations require an existing sandbox.\n",
        "label": {
          "en_US": "E2B",
          "ja_JP": "E2B",
          "pt_BR": "E2B",
          "zh_Hans": "E2B"
        },
        "latest_package_identifier": "langgenius/e2b:0.0.1@c1cbd8c9e8c0e6aea1bd3d3dcf161dc24fe46b79646d62719e84b5adb60a462b",
        "latest_version": "0.0.1",
        "model": {},
        "name": "e2b",
        "org": "langgenius",
        "plugin_id": "langgenius/e2b",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/e2b.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {}
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "API Key",
                "zh_Hans": "API 密钥"
              },
              "name": "api_key",
              "options": null,
              "placeholder": null,
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://e2b.dev/dashboard?tab=keys"
            }
          ],
          "identity": {
            "author": "langgenius",
            "description": {
              "en_US": "Tool for integrate with e2b.dev.",
              "pt_BR": "Tool for integrate with e2b.dev.",
              "zh_Hans": "Tool for integrate with e2b.dev."
            },
            "icon": "icon.png",
            "label": {
              "en_US": "E2B",
              "pt_BR": "E2B",
              "zh_Hans": "E2B"
            },
            "name": "e2b",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Run a snippet of Python code in a sandboxed environment.",
                  "pt_BR": "Executar um trecho de Python código em um ambiente sandboxed.",
                  "zh_Hans": "在沙盒环境中运行一段 Python 代码。"
                },
                "llm": "Run a snippet of Python code in a sandboxed environment."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Run Code",
                  "pt_BR": "Executar código",
                  "zh_Hans": "运行代码"
                },
                "name": "run_code"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The code to execute in the sandbox environment, it can be Python or JavaScript.",
                    "pt_BR": "O código a ser executado no ambiente sandbox, pode ser Python ou JavaScript.",
                    "zh_Hans": "要在沙盒环境中执行的代码，可以是 Python 或 JavaScript。"
                  },
                  "label": {
                    "en_US": "Code",
                    "pt_BR": "Código",
                    "zh_Hans": "代码"
                  },
                  "llm_description": "The code to execute in the sandbox environment",
                  "max": null,
                  "min": null,
                  "name": "code",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "python",
                  "form": "llm",
                  "human_description": {
                    "en_US": "The language of the code, Python or JavaScript.",
                    "pt_BR": "O idioma do código, Python ou JavaScript.",
                    "zh_Hans": "代码的语言，Python 或 JavaScript。"
                  },
                  "label": {
                    "en_US": "Language",
                    "pt_BR": "Idioma",
                    "zh_Hans": "语言"
                  },
                  "llm_description": "The language of the code, Python or JavaScript.",
                  "max": null,
                  "min": null,
                  "name": "language",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "",
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of an existing sandbox, if not provided, a new sandbox will be created.",
                    "pt_BR": "O ID de um sandbox existente, se não fornecido, um novo sandbox será criado.",
                    "zh_Hans": "一个现有沙盒的 ID, 如果未提供, 将创建一个新的沙盒。"
                  },
                  "label": {
                    "en_US": "Sandbox ID",
                    "pt_BR": "ID do Sandbox",
                    "zh_Hans": "沙盒 ID"
                  },
                  "llm_description": "The ID of an existing sandbox, if not provided, a new sandbox will be created.",
                  "max": null,
                  "min": null,
                  "name": "sandbox_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 120,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The lifetime of the sandbox in seconds, 120 seconds by default.",
                    "pt_BR": "O tempo de vida do sandbox em segundos, 120 segundos por padrão.",
                    "zh_Hans": "沙盒的生命周期（秒），默认 120 秒。"
                  },
                  "label": {
                    "en_US": "Timeout",
                    "pt_BR": "Tempo limite",
                    "zh_Hans": "超时"
                  },
                  "llm_description": "The lifetime of the sandbox in seconds.",
                  "max": null,
                  "min": null,
                  "name": "timeout",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Run a command in a sandboxed environment.",
                  "pt_BR": "Executar um comando em um ambiente sandboxed.",
                  "zh_Hans": "在沙盒环境中运行一个命令。"
                },
                "llm": "Run a command in a sandboxed environment."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Run Command",
                  "pt_BR": "Executar comando",
                  "zh_Hans": "运行命令"
                },
                "name": "run_command"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The command to execute in the sandbox environment.",
                    "pt_BR": "O comando a ser executado no ambiente sandbox.",
                    "zh_Hans": "要在沙盒环境中执行的命令。"
                  },
                  "label": {
                    "en_US": "Command",
                    "pt_BR": "Comando",
                    "zh_Hans": "命令"
                  },
                  "llm_description": "The command to execute in the sandbox environment.",
                  "max": null,
                  "min": null,
                  "name": "command",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "",
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of an existing sandbox, if not provided, a new sandbox will be created.",
                    "pt_BR": "O ID de um sandbox existente, se não fornecido, um novo sandbox será criado.",
                    "zh_Hans": "一个现有沙盒的 ID, 如果未提供, 将创建一个新的沙盒。"
                  },
                  "label": {
                    "en_US": "Sandbox ID",
                    "pt_BR": "ID do Sandbox",
                    "zh_Hans": "沙盒 ID"
                  },
                  "llm_description": "The ID of an existing sandbox, if not provided, a new sandbox will be created.",
                  "max": null,
                  "min": null,
                  "name": "sandbox_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 120,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The lifetime of the sandbox in seconds, 120 seconds by default.",
                    "pt_BR": "O tempo de vida do sandbox em segundos, 120 segundos por padrão.",
                    "zh_Hans": "沙盒的生命周期（秒），默认 120 秒。"
                  },
                  "label": {
                    "en_US": "Timeout",
                    "pt_BR": "Tempo limite",
                    "zh_Hans": "超时"
                  },
                  "llm_description": "The lifetime of the sandbox in seconds.",
                  "max": null,
                  "min": null,
                  "name": "timeout",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Upload a file to a sandboxed environment.",
                  "pt_BR": "Carregar um arquivo para um ambiente sandboxed.",
                  "zh_Hans": "上传一个文件到沙盒环境中。"
                },
                "llm": "Upload a file to a sandboxed environment."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Upload File",
                  "pt_BR": "Carregar Arquivo",
                  "zh_Hans": "上传文件"
                },
                "name": "upload_file"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The file to upload",
                    "pt_BR": "O arquivo a ser carregado",
                    "zh_Hans": "要上传的文件"
                  },
                  "label": {
                    "en_US": "File",
                    "pt_BR": "Arquivo",
                    "zh_Hans": "文件"
                  },
                  "llm_description": "The file to upload",
                  "max": null,
                  "min": null,
                  "name": "file",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "file"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The path of the file to upload",
                    "pt_BR": "O caminho do arquivo a ser carregado",
                    "zh_Hans": "要上传的文件路径"
                  },
                  "label": {
                    "en_US": "File Path",
                    "pt_BR": "Caminho do Arquivo",
                    "zh_Hans": "文件路径"
                  },
                  "llm_description": "The path of the file to upload",
                  "max": null,
                  "min": null,
                  "name": "file_path",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of an existing sandbox.",
                    "pt_BR": "O ID de um sandbox existente.",
                    "zh_Hans": "一个现有沙盒的 ID。"
                  },
                  "label": {
                    "en_US": "Sandbox ID",
                    "pt_BR": "ID do Sandbox",
                    "zh_Hans": "沙盒 ID"
                  },
                  "llm_description": "The ID of an existing sandbox.",
                  "max": null,
                  "min": null,
                  "name": "sandbox_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Download a file from a sandboxed environment.",
                  "pt_BR": "Baixar um arquivo de um ambiente sandboxed.",
                  "zh_Hans": "从沙盒环境中下载一个文件。"
                },
                "llm": "Download a file from a sandboxed environment."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Download File",
                  "pt_BR": "Baixar Arquivo",
                  "zh_Hans": "下载文件"
                },
                "name": "download_file"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The path of the file to download",
                    "pt_BR": "O caminho do arquivo a ser baixado",
                    "zh_Hans": "要下载的文件路径"
                  },
                  "label": {
                    "en_US": "File Path",
                    "pt_BR": "Caminho do Arquivo",
                    "zh_Hans": "文件路径"
                  },
                  "llm_description": "The path of the file to download",
                  "max": null,
                  "min": null,
                  "name": "file_path",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of an existing sandbox.",
                    "pt_BR": "O ID de um sandbox existente.",
                    "zh_Hans": "一个现有沙盒的 ID。"
                  },
                  "label": {
                    "en_US": "Sandbox ID",
                    "pt_BR": "ID do Sandbox",
                    "zh_Hans": "沙盒 ID"
                  },
                  "llm_description": "The ID of an existing sandbox.",
                  "max": null,
                  "min": null,
                  "name": "sandbox_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-27T07:17:31Z",
        "version_updated_at": "2025-02-27T07:17:31Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "This Slack Bot supports receiving messages from Slack as input to Chatflow/Chatbot/Agent in Dify, and sending messages back to Slack.",
          "ja_JP": "このSlack Botは、SlackからのメッセージをDifyのChatflow/Chatbot/Agentへの入力として受け取り、Slackにメッセージを送信することをサポートします。",
          "pt_BR": "Este Slack Bot suporta receber mensagens do Slack como entrada para Chatflow/Chatbot/Agent no Dify e enviar mensagens de volta para o Slack.",
          "zh_Hans": "这个Slack Bot支持接收来自Slack的消息作为Dify中Chatflow/Chatbot/Agent的输入，并将消息发送回Slack。"
        },
        "category": "extension",
        "created_at": "2024-12-18T15:39:33Z",
        "endpoint": {
          "endpoints": [
            {
              "hidden": false,
              "method": "POST",
              "path": "/"
            }
          ],
          "settings": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "Bot Token",
                "ja_JP": "Bot Token",
                "pt_BR": "Token do Bot",
                "zh_Hans": "Bot Token"
              },
              "name": "bot_token",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Bot Token",
                "ja_JP": "ボットトークンを入力してください",
                "pt_BR": "Por favor, insira seu Token do Bot",
                "zh_Hans": "请输入你的 Bot Token"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": false,
              "helper": null,
              "label": {
                "en_US": "Allow Retry",
                "ja_JP": "再試行を許可",
                "pt_BR": "Permitir Retentativas",
                "zh_Hans": "允许重试"
              },
              "name": "allow_retry",
              "options": null,
              "placeholder": null,
              "required": false,
              "scope": null,
              "type": "boolean",
              "url": null
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "App",
                "ja_JP": "アプリ",
                "pt_BR": "App",
                "zh_Hans": "应用"
              },
              "name": "app",
              "options": null,
              "placeholder": {
                "en_US": "the app you want to use to answer Slack messages",
                "ja_JP": "あなたが Slack メッセージに回答するために使用するアプリ",
                "pt_BR": "o app que você deseja usar para responder mensagens do Slack",
                "zh_Hans": "你想要用来回答 Slack 消息的应用"
              },
              "required": true,
              "scope": null,
              "type": "app-selector",
              "url": null
            }
          ]
        },
        "icon": "langgenius/packages/slack-bot/_assets/icon.svg",
        "index_id": "langgenius___slack-bot",
        "install_count": 632,
        "introduction": "## Slack Bot\n\n**Author:** Langgenius  \n**Version:** 0.0.1\n**Type:** extension\n\n### Description\n\nFollow these steps to integrate the Slack plugin:\n\n1. **Create a Slack App**\n\n   - Either create an app from a manifest or from scratch\n   - Name your app and select your target workspace\n     <img src=\"./_assets/step1.png\" width=\"600\" />\n     <img src=\"./_assets/step2.png\" width=\"600\" />\n\n2. **Configure App Settings**\n\n   - Enable Incoming Webhooks\n   - Install the app to your workspace\n   - Choose a channel for message delivery\n   - Locate your \"Bot User OAuth Token\" in settings\n     <img src=\"./_assets/step3.png\" width=\"600\" />\n     <img src=\"./_assets/step4.png\" width=\"600\" />\n     <img src=\"./_assets/step5.png\" width=\"600\" />\n\n3. **Set Up Dify Endpoint**\n\n   - Create a new endpoint with a custom name\n   - Input your Bot User OAuth Token\n   - Set \"Allow Retry\" to false (recommended to prevent duplicate messages)\n   - Link to your Dify chatflow/chatbot/agent\n   - Save and copy the generated endpoint URL\n\n    <div style=\"display: flex; gap: 10px;\">\n      <img src=\"./_assets/step6.png\" width=\"400\" />\n      <img src=\"./_assets/step7.png\" width=\"400\" />\n    </div>\n\n4. **Complete Slack App Configuration**\n\n   - Enable Event Subscriptions\n   - Paste the Dify endpoint URL as the Request URL\n   - Add required OAuth scopes for Event Subscriptions\n   - Configure App's OAuth & Permissions with necessary scopes\n     <img src=\"./_assets/step8.png\" width=\"600\" />\n     <img src=\"./_assets/step9.png\" width=\"600\" />\n\n     <img src=\"./_assets/step10.png\" width=\"400\" />\n\n5. **Final Steps**\n   - Reinstall the app to your workspace if you made changes\n   - Add the bot to your chosen channel\n   - Start interacting by @mentioning the bot in messages\n     <img src=\"./_assets/step11.png\" width=\"600\" />\n     <img src=\"./_assets/step12.png\" width=\"600\" />\n",
        "label": {
          "en_US": "Slack Bot",
          "ja_JP": "Slack Bot",
          "pt_BR": "Slack Bot",
          "zh_Hans": "Slack Bot"
        },
        "latest_package_identifier": "langgenius/slack-bot:0.0.3@019d1acf6599977dde981c9d783e12a98f6c02791a45a158bc1958a69f417c5b",
        "latest_version": "0.0.3",
        "model": {},
        "name": "slack-bot",
        "org": "langgenius",
        "plugin_id": "langgenius/slack-bot",
        "plugins": {
          "agent_strategies": null,
          "endpoints": [
            "group/slack.yaml"
          ],
          "models": null,
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-02-17T07:19:57Z",
        "version_updated_at": "2025-02-17T07:19:57Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "AlphaVantage is an online platform that provides financial market data and APIs, making it convenient for individual investors and developers to access stock quotes, technical indicators, and stock analysis.",
          "pt_BR": "AlphaVantage is an online platform that provides financial market data and APIs, making it convenient for individual investors and developers to access stock quotes, technical indicators, and stock analysis.",
          "zh_Hans": "AlphaVantage是一个在线平台，它提供金融市场数据和API，便于个人投资者和开发者获取股票报价、技术指标和股票分析。"
        },
        "category": "tool",
        "created_at": "2024-12-03T09:34:46Z",
        "endpoint": {},
        "icon": "langgenius/packages/alphavantage/_assets/icon.svg",
        "index_id": "langgenius___alphavantage",
        "install_count": 630,
        "introduction": "# Alpha Vantage API Tool\n\n## Overview\n\nAlpha Vantage provides an API service offering access to a wide range of financial market data. It allows developers to retrieve real-time and historical stock prices, forex rates, cryptocurrency data, and technical indicators. An API key grants access to these data endpoints, enabling integration into applications, analysis tools, and research projects.\n\n## Configuration\n\n### 1. Apply for AlphaVantage API Key\nPlease apply for an API Key on the [AlphaVantage](https://www.alphavantage.co/support/#api-key) homepage.\n\n### 2. Get AlphaVantage tools from Plugin Marketplace\nThe AlphaVantage tools could be found at the Plugin Marketplace, please install it first.\n\n### 3. On the Dify navigation page, click `Tools > AlphaVantage > Authorize` and fill in the API key.\n\n![](./_assets/alpha_1.PNG)\n\n### 4. You can use the AlphaVantage tool in the following application types.\n\n![](./_assets/alpha_2.png)\n\n#### Chatflow / Workflow applications\n\nBoth Chatflow and Workflow applications support the AlphaVantage tool node.\n\n#### Agent applications\n\nAdd the AlphaVantage tool in the Agent application, then enter the stock code to call this tool.",
        "label": {
          "en_US": "AlphaVantage",
          "pt_BR": "AlphaVantage",
          "zh_Hans": "AlphaVantage"
        },
        "latest_package_identifier": "langgenius/alphavantage:0.0.2@abfae4f295632d2ee8a99775072e4c2e012e13bc6220d745d41da4baa9073b7a",
        "latest_version": "0.0.2",
        "model": {},
        "name": "alphavantage",
        "org": "langgenius",
        "plugin_id": "langgenius/alphavantage",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/alphavantage.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "finance"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "AlphaVantage API key",
                "pt_BR": "AlphaVantage API key",
                "zh_Hans": "AlphaVantage API key"
              },
              "name": "api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your AlphaVantage API key",
                "pt_BR": "Please input your AlphaVantage API key",
                "zh_Hans": "请输入你的 AlphaVantage API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://www.alphavantage.co/support/#api-key"
            }
          ],
          "identity": {
            "author": "zhuhao",
            "description": {
              "en_US": "AlphaVantage is an online platform that provides financial market data and APIs, making it convenient for individual investors and developers to access stock quotes, technical indicators, and stock analysis.",
              "pt_BR": "AlphaVantage is an online platform that provides financial market data and APIs, making it convenient for individual investors and developers to access stock quotes, technical indicators, and stock analysis.",
              "zh_Hans": "AlphaVantage是一个在线平台，它提供金融市场数据和API，便于个人投资者和开发者获取股票报价、技术指标和股票分析。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "AlphaVantage",
              "pt_BR": "AlphaVantage",
              "zh_Hans": "AlphaVantage"
            },
            "name": "alphavantage",
            "tags": [
              "finance"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Retrieve information such as daily opening price, daily highest price, daily lowest price, daily closing price, and daily trading volume for a specified stock symbol.",
                  "pt_BR": "Retrieve information such as daily opening price, daily highest price, daily lowest price, daily closing price, and daily trading volume for a specified stock symbol",
                  "zh_Hans": "获取指定股票代码的每日开盘价、每日最高价、每日最低价、每日收盘价和每日交易量等信息。"
                },
                "llm": "Retrieve information such as daily opening price, daily highest price, daily lowest price, daily closing price, and daily trading volume for a specified stock symbol"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "zhuhao",
                "label": {
                  "en_US": "query_stock",
                  "pt_BR": "query_stock",
                  "zh_Hans": "query_stock"
                },
                "name": "query_stock"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "stock code",
                    "pt_BR": "stock code",
                    "zh_Hans": "股票代码"
                  },
                  "label": {
                    "en_US": "stock code",
                    "pt_BR": "stock code",
                    "zh_Hans": "股票代码"
                  },
                  "llm_description": "stock code for query from alphavantage",
                  "max": null,
                  "min": null,
                  "name": "code",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:03:54Z",
        "version_updated_at": "2025-02-17T07:03:54Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Redis tools plugin for Dify, provide Redis SET and GET functions, Redis Cluster mode is supported too.",
          "ja_JP": "Redis tools plugin for Dify, provide Redis SET and GET functions, Redis Cluster mode is supported too.",
          "pt_BR": "Redis tools plugin for Dify, provide Redis SET and GET functions, Redis Cluster mode is supported too.",
          "zh_Hans": "适用于 Dify 的 Redis 工具插件，提供 Redis SET 与 GET 功能，同时支持 Redis 单节点与集群模式。"
        },
        "category": "tool",
        "created_at": "2025-04-13T17:27:35Z",
        "endpoint": {},
        "icon": "eft/packages/redis/_assets/icon.svg",
        "index_id": "eft___redis",
        "install_count": 627,
        "introduction": "# Dify Redis Plugin\r\n\r\n**Author:** [EFT](https://github.com/ztistic)\r\n**Repo:** [dify-plugin-redis](https://github.com/ztistic/dify-plugin-redis)\r\n**Version:** 1.0.0\r\n**Type:** tool\r\n\r\n## Description\r\n\r\nThis Dify Redis plugin provides Redis SET and GET functionalities,\r\nallowing the caching of model-generated data in Redis to reduce server load.\r\n\r\n### Examples\r\n\r\n- Cache the output of LLM into Redis.\r\n\r\n![Cache the output of LLM](./_assets/example_1.png)\r\n\r\n- Read cache from Redis if exists.\r\n\r\n![Read cache](./_assets/example_2.png)\r\n\r\n### Authorize\r\n\r\nSet up authorization, witch actually connects to the Redis server provided by the user.\r\n![Set up authorization](./_assets/set_up.png)\r\n\r\n#### Features\r\n\r\n- Connect to Redis Server, Redis Cluster is supported too.\r\n\r\n#### Parameters\r\n\r\n| Parameter  | Type     | Required | Description                             |\r\n|------------|----------|----------|-----------------------------------------|\r\n| `host`     | `string` | `No`     | redis server host, default `127.0.0.1`. |\r\n| `port`     | `number` | `No`     | redis server port, default `6379`.      |\r\n| `password` | `string` | `No`     | redis server password, default `None`.  |\r\n| `cluster`  | `bool`   | `No`     | redis cluster or not, default `False`.  |\r\n\r\n### Redis SET\r\n\r\nThe Redis SET tool allows users write data into Redis.\r\n![Redis SET example](./_assets/redis_set.png)\r\n\r\n#### Features\r\n\r\n- Write data into Redis, the input string value is returned if success, or standard error is thrown.\r\n\r\n#### Parameters\r\n\r\n| Parameter | Type     | Required | Description                                                |\r\n|-----------|----------|----------|------------------------------------------------------------|\r\n| `name`    | `string` | `Yes`    | name of a redis record, part of the final redis key.       |\r\n| `key`     | `string` | `Yes`    | key of a redis record, part of the final redis key.        |\r\n| `value`   | `string` | `Yes`    | value of a redis record.                                   |\r\n| `ttl`     | `number` | `No`     | value of a redis record, default `60`s, `-1` is supported. |\r\n\r\n### Redis GET\r\n\r\nThe Redis GET tool allows users to read data from Redis.\r\n![Redis GET example](./_assets/redis_get.png)\r\n\r\n#### Features\r\n\r\n- Read data from Redis and returns standard output and standard error\r\n\r\n#### Parameters\r\n\r\n| Parameter | Type     | Required | Description                                          |\r\n|-----------|----------|----------|------------------------------------------------------|\r\n| `name`    | `string` | `Yes`    | name of a redis record, part of the final redis key. |\r\n| `key`     | `string` | `Yes`    | key of a redis record, part of the final redis key.  |\r\n\r\n## Security Considerations\r\n\r\n- Ensure you have permission to access the target redis server\r\n- Sensitive information such as password should be kept secure\r\n- Follow the principle of least privilege, granting only necessary execution permissions\r\n\r\n## License\r\n\r\n[MIT](./LICENSE)\r\n\r\n\r\n\r\n",
        "label": {
          "en_US": "Redis",
          "ja_JP": "Redis",
          "pt_BR": "Redis",
          "zh_Hans": "Redis"
        },
        "latest_package_identifier": "eft/redis:1.0.0@12bbbd0672fe8d058d9608555daeea34ac560c978792a1f961a7c03e62601a77",
        "latest_version": "1.0.0",
        "model": {},
        "name": "redis",
        "org": "eft",
        "plugin_id": "eft/redis",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/redis-provider.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Host",
                "zh_Hans": "Host"
              },
              "name": "host",
              "options": null,
              "placeholder": {
                "en_US": "default: 127.0.0.1",
                "zh_Hans": "默认: 127.0.0.1"
              },
              "required": false,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Port",
                "zh_Hans": "Port"
              },
              "name": "port",
              "options": null,
              "placeholder": {
                "en_US": "default: 6379",
                "zh_Hans": "默认: 6379"
              },
              "required": false,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Password",
                "zh_Hans": "Password"
              },
              "name": "password",
              "options": null,
              "placeholder": {
                "en_US": "default: None",
                "zh_Hans": "默认: None"
              },
              "required": false,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Cluster",
                "zh_Hans": "是否集群"
              },
              "name": "cluster",
              "options": null,
              "placeholder": {
                "en_US": "default: false",
                "zh_Hans": "默认: false"
              },
              "required": false,
              "scope": null,
              "type": "boolean",
              "url": null
            }
          ],
          "identity": {
            "author": "eft",
            "description": {
              "en_US": "Redis tools plugin for Dify, provide Redis SET and GET functions, Redis Cluster mode is supported too.",
              "pt_BR": "Redis tools plugin for Dify, provide Redis SET and GET functions, Redis Cluster mode is supported too.",
              "zh_Hans": "适用于 Dify 的 Redis 工具插件，提供 Redis SET 与 GET 功能，同时支持 Redis 单节点与集群模式。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Redis",
              "pt_BR": "Redis",
              "zh_Hans": "Redis"
            },
            "name": "redis",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Redis SET",
                  "pt_BR": "Redis SET",
                  "zh_Hans": "Redis SET"
                },
                "llm": "Redis SET"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "eft",
                "label": {
                  "en_US": "Redis SET",
                  "pt_BR": "Redis SET",
                  "zh_Hans": "Redis SET"
                },
                "name": "redis-set"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Redis Name",
                    "pt_BR": "Redis Name",
                    "zh_Hans": "Redis Name"
                  },
                  "label": {
                    "en_US": "Name",
                    "pt_BR": "Name",
                    "zh_Hans": "Name"
                  },
                  "llm_description": "Redis Name",
                  "max": null,
                  "min": null,
                  "name": "name",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Redis Key",
                    "pt_BR": "Redis Key",
                    "zh_Hans": "Redis Key"
                  },
                  "label": {
                    "en_US": "Key",
                    "pt_BR": "Key",
                    "zh_Hans": "Key"
                  },
                  "llm_description": "Redis Key",
                  "max": null,
                  "min": null,
                  "name": "key",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Redis Value",
                    "pt_BR": "Redis Value",
                    "zh_Hans": "Redis Value"
                  },
                  "label": {
                    "en_US": "Value",
                    "pt_BR": "Value",
                    "zh_Hans": "Value"
                  },
                  "llm_description": "Redis Value",
                  "max": null,
                  "min": null,
                  "name": "value",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "TTL, default 60s",
                    "pt_BR": "TTL, default 60s",
                    "zh_Hans": "TTL, 默认 60 秒"
                  },
                  "label": {
                    "en_US": "TTL",
                    "pt_BR": "TTL",
                    "zh_Hans": "TTL"
                  },
                  "llm_description": "TTL",
                  "max": null,
                  "min": null,
                  "name": "ttl",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Redis GET",
                  "pt_BR": "Redis GET",
                  "zh_Hans": "Redis GET"
                },
                "llm": "Redis GET"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "eft",
                "label": {
                  "en_US": "Redis GET",
                  "pt_BR": "Redis GET",
                  "zh_Hans": "Redis GET"
                },
                "name": "redis-get"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Redis Name",
                    "pt_BR": "Redis Name",
                    "zh_Hans": "Redis Name"
                  },
                  "label": {
                    "en_US": "Name",
                    "pt_BR": "Name",
                    "zh_Hans": "Name"
                  },
                  "llm_description": "Redis Name",
                  "max": null,
                  "min": null,
                  "name": "name",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Redis Key",
                    "pt_BR": "Redis Key",
                    "zh_Hans": "Redis Key"
                  },
                  "label": {
                    "en_US": "Key",
                    "pt_BR": "Key",
                    "zh_Hans": "Key"
                  },
                  "llm_description": "Redis Key",
                  "max": null,
                  "min": null,
                  "name": "key",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-13T17:27:52Z",
        "version_updated_at": "2025-04-13T17:27:52Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "The Alibaba Cloud Toolkit is an integrated set of development capabilities from Alibaba Cloud, aimed at helping users utilize cloud resources more easily and efficiently.",
          "pt_BR": "The Alibaba Cloud Toolkit is an integrated set of development capabilities from Alibaba Cloud, aimed at helping users utilize cloud resources more easily and efficiently.",
          "zh_Hans": "集成了阿里云的一系列开放能力，旨在帮助用户更简单、更高效使用云端能力。"
        },
        "category": "tool",
        "created_at": "2025-04-09T13:57:43Z",
        "endpoint": {},
        "icon": "liujicheng/packages/aliyun_tool/_assets/icon.png",
        "index_id": "liujicheng___aliyun_tool",
        "install_count": 622,
        "introduction": "# Alibaba Cloud Tool README\n# Overview\nIntegrates the open capabilities of Alibaba Cloud\n# 1、Alibaba Cloud OCR TOOL\n**Alibaba Cloud OCR**: Alibaba Cloud OCR enables you to seamlessly extract text from a variety of image formats, including scanned documents, photographs, and more. This tool is ideal for businesses and individuals looking to digitize and manage their data effectively.\n## 1.1、Configuration\nTo integrate the OCR tool into your application, follow these steps:\n1. Open the **Plugin Marketplace**.\n2. Search for the **Alibaba Cloud OCR** tool.\n3. Install the tool to complete the integration.\n## 1.2、Tool Features\nThe **Alibaba Cloud OCR** plugin includes several customizable actions to cater to your text extraction needs:\n### Text Recognition\nExtract text from images based on various parameters and configurations.\n**Input Variables:**\n- **Image File (Required):** Upload the image file from which you want to extract text.\n- **Output:** Returns the extracted text along with its formatting information, if applicable.\nThis action offers flexibility for extracting text tailored to your specific needs, ensuring reliable and accurate decoding of image data.\n## 1.3、Usage\nAlibaba Cloud OCR can be seamlessly integrated with **Chatflow / Workflow Apps** and **Agent Apps**.\n### Chatflow / Workflow Apps\n1. Add the **Alibaba Cloud OCR** node to your Chatflow or Workflow pipeline.\n2. Configure the \"Text Recognition\" action by uploading the image file and specifying any additional parameters.\n3. Run the pipeline to extract text from the image and utilize it in your workflow.\n### Agent Apps\n1. Add the **Alibaba Cloud OCR** tool to your Agent application.\n2. Upload the image containing text via the chat interface.\n3. The tool processes your input and returns the extracted text.\n## 1.4、Use Cases\n- **Document Digitization:** Convert paper-based documents into editable digital text.\n- **Data Entry Automation:** Automate data extraction from forms and invoices to reduce manual entry errors.\n- **Accessibility Improvements:** Enhance accessibility by converting visual text into digital formats for screen readers.\n- **Research and Analysis:** Extract and process large volumes of text data for academic or business research purposes.\nWith **Alibaba Cloud OCR**, you can easily convert images into text data, making the extraction and manipulation of information straightforward and efficient.",
        "label": {
          "en_US": "AliYun Tool",
          "pt_BR": "AliYun Tool",
          "zh_Hans": "阿里云工具集"
        },
        "latest_package_identifier": "liujicheng/aliyun_tool:0.0.1@cfac4caa162add082d9ef4a776486c21fa3818a5306604106acf87c57ef88873",
        "latest_version": "0.0.1",
        "model": {},
        "name": "aliyun_tool",
        "org": "liujicheng",
        "plugin_id": "liujicheng/aliyun_tool",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/aliyun.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Access Key ID",
                "pt_BR": "Access Key ID",
                "zh_Hans": "Access Key ID"
              },
              "name": "access_key_id",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Access Key ID",
                "pt_BR": "Please input your Access Key ID",
                "zh_Hans": "请输入你的 Access Key ID"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Access Key Secret",
                "pt_BR": "Access Key Secret",
                "zh_Hans": "Access Key Secret"
              },
              "name": "access_key_secret",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Access Key Secret",
                "pt_BR": "Please input your Access Key Secret",
                "zh_Hans": "请输入你的 Access Key Secret"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            }
          ],
          "identity": {
            "author": "liujicheng",
            "description": {
              "en_US": "aliyun, https://www.aliyun.com.",
              "pt_BR": "aliyun, https://www.aliyun.com.",
              "zh_Hans": "集成了阿里云（https://www.aliyun.com）的强大开放能力,为开发者提供一站式的开发工具."
            },
            "icon": "icon.png",
            "label": {
              "en_US": "aliyun",
              "pt_BR": "aliyun",
              "zh_Hans": "阿里云"
            },
            "name": "aliyun",
            "tags": [
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "An OCR tool used to recognize textual information contained in images, documents, cards, and other files.",
                  "pt_BR": "An OCR tool used to recognize textual information contained in images, documents, cards, and other files.",
                  "zh_Hans": "一个OCR工具，用于识别图片、文档、卡证等文件所包含的文字信息。"
                },
                "llm": "An OCR tool used to recognize textual information contained in images, documents, cards, and other files."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "liujicheng",
                "label": {
                  "en_US": "DuGuang OCR",
                  "pt_BR": "DuGuang OCR",
                  "zh_Hans": "读光OCR"
                },
                "name": "读光OCR"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "image url to be recognize textual information",
                    "pt_BR": "image url to be recognize textual information",
                    "zh_Hans": "图片地址"
                  },
                  "label": {
                    "en_US": "image url to be recognize textual information",
                    "pt_BR": "image url to be recognize textual information",
                    "zh_Hans": "图片地址"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "image_url",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-09T13:57:47Z",
        "version_updated_at": "2025-04-09T13:57:47Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "A plugin for the Dify platform that provides image processing capabilities, including text-to-image generation.",
          "ja_JP": "A plugin for the Dify platform that provides image processing capabilities, including text-to-image generation.",
          "pt_BR": "A plugin for the Dify platform that provides image processing capabilities, including text-to-image generation.",
          "zh_Hans": "Dify平台的插件，提供图像处理功能，包括文本到图像的生成。"
        },
        "category": "tool",
        "created_at": "2025-04-18T19:23:06Z",
        "endpoint": {},
        "icon": "caffbyte/packages/imagetool/_assets/icon.svg",
        "index_id": "caffbyte___imagetool",
        "install_count": 621,
        "introduction": "## dify-plugin-imagetool\n\n### Overview\n\nGenerates images based on text prompts using the Tonyi API.\n\n### Setup\n\n1. **Apply for a Tonyi API Key**  \n   Visit the [AliCloud Bailian Console](https://bailian.console.aliyun.com/?apiKey=1#/api-key) to apply for an API key.\n\n2. **Install ImageTool from the Plugin Marketplace**  \n   Search for “ImageTool” in the Plugin Marketplace and install it.\n\n3. **Configure in Dify**  \n   In the Dify navigation panel, go to **Tools > ImageTool > Authorize**, and enter your API key.\n\n4. **Start Using the Tool**  \n   Once configured, you can start generating images via text prompts.\n\n   ![](_assets/text2image.png)\n\n---\n\n**Feature Requests and Issues**  \nSubmit feature requests or report issues via [GitHub Issues](https://github.com/caffbyte/dify-plugin-imagetool/issues).\n",
        "label": {
          "en_US": "Image tool",
          "ja_JP": "Image tool",
          "pt_BR": "Image tool",
          "zh_Hans": "图像工具"
        },
        "latest_package_identifier": "caffbyte/imagetool:0.0.1@ea34c6f28f5b7d2d1489f0e750c731746e98901307f74005d69ed4eb82cf1dca",
        "latest_version": "0.0.1",
        "model": {},
        "name": "imagetool",
        "org": "caffbyte",
        "plugin_id": "caffbyte/imagetool",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/imagetool.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "storage": {
              "enabled": true,
              "size": 1048576
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Get your API key from AliCloud",
                "zh_Hans": "从阿里云百炼获取 API Key"
              },
              "label": {
                "en_US": "Tonyi API key",
                "zh_Hans": "Tonyi API key"
              },
              "name": "tonyi_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Tonyi API key",
                "zh_Hans": "请输入你的 Tonyi API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://bailian.console.aliyun.com/?apiKey=1#/api-key"
            }
          ],
          "identity": {
            "author": "caffbyte",
            "description": {
              "en_US": "A plugin for the Dify platform that provides image processing capabilities, including text-to-image generation.",
              "pt_BR": "A plugin for the Dify platform that provides image processing capabilities, including text-to-image generation.",
              "zh_Hans": "Dify平台的插件，提供图像处理功能，包括文本到图像的生成。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Image tool",
              "pt_BR": "Image tool",
              "zh_Hans": "图像工具"
            },
            "name": "imagetool",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Generate an image based on a text prompt.",
                  "pt_BR": "Generate an image based on a text prompt.",
                  "zh_Hans": "根据文本提示生成图像。"
                },
                "llm": "Generate an image based on a text prompt."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "caffbyte",
                "label": {
                  "en_US": "Text to image",
                  "pt_BR": "Text to image",
                  "zh_Hans": "文生图"
                },
                "name": "imagetool"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The model name, example value: wanx2.1-T2-turbo.",
                    "pt_BR": "The model name, example value: wanx2.1-T2-turbo.",
                    "zh_Hans": "模型名称，示例值：wanx2.1-t2i-turbo。"
                  },
                  "label": {
                    "en_US": "Model name",
                    "pt_BR": "Model name",
                    "zh_Hans": "模型名称"
                  },
                  "llm_description": "The model name, example value: wanx2.1-T2-turbo.",
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The forward prompt, used to describe the elements and visual characteristics you want in the generated image.",
                    "pt_BR": "The forward prompt, used to describe the elements and visual characteristics you want in the generated image.",
                    "zh_Hans": "正向提示词，用来描述生成图像中期望包含的元素和视觉特点。"
                  },
                  "label": {
                    "en_US": "Prompt",
                    "pt_BR": "Prompt",
                    "zh_Hans": "提示词"
                  },
                  "llm_description": "The forward prompt, used to describe the elements and visual characteristics you want in the generated image.",
                  "max": null,
                  "min": null,
                  "name": "prompt",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "1024*1024",
                  "form": "form",
                  "human_description": {
                    "en_US": "Choose the image size from the options below.",
                    "pt_BR": "Choose the image size from the options below.",
                    "zh_Hans": "从以下选项中选择图像尺寸。"
                  },
                  "label": {
                    "en_US": "Image size",
                    "pt_BR": "Image size",
                    "zh_Hans": "图像尺寸"
                  },
                  "llm_description": "Choose the image size from the options below.",
                  "max": null,
                  "min": null,
                  "name": "size",
                  "options": [
                    {
                      "label": {
                        "en_US": "1024*1024",
                        "pt_BR": "1024*1024",
                        "zh_Hans": "1024*1024"
                      },
                      "value": "1024*1024"
                    },
                    {
                      "label": {
                        "en_US": "1280*720",
                        "pt_BR": "1280*720",
                        "zh_Hans": "1280*720"
                      },
                      "value": "1280*720"
                    },
                    {
                      "label": {
                        "en_US": "720*1280",
                        "pt_BR": "720*1280",
                        "zh_Hans": "720*1280"
                      },
                      "value": "720*1280"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 1,
                  "form": "form",
                  "human_description": {
                    "en_US": "Select how many images you want to generate (1~4).",
                    "pt_BR": "Select how many images you want to generate (1~4).",
                    "zh_Hans": "选择要生成的图片数量（1~4）。"
                  },
                  "label": {
                    "en_US": "Number of images generated",
                    "pt_BR": "Number of images generated",
                    "zh_Hans": "生成的图像数量"
                  },
                  "llm_description": "Select how many images you want to generate (1~4).",
                  "max": 4,
                  "min": 1,
                  "name": "count",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "Enable smart rewriting of the input prompt. Recommended for short prompts.",
                    "pt_BR": "Enable smart rewriting of the input prompt. Recommended for short prompts.",
                    "zh_Hans": "开启输入提示词的智能改写功能。适用于较短的提示词，能显著提升生成效果，但会增加 3-4 秒的耗时。"
                  },
                  "label": {
                    "en_US": "Enable smart prompt rewriting",
                    "pt_BR": "Enable smart prompt rewriting",
                    "zh_Hans": "开启智能改写"
                  },
                  "llm_description": "Enable smart rewriting of the input prompt. Recommended for short prompts.",
                  "max": null,
                  "min": null,
                  "name": "prompt_extend",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to add a watermark to the image. The watermark will appear at the bottom-right corner with the text “AI Generated”.",
                    "pt_BR": "Whether to add a watermark to the image. The watermark will appear at the bottom-right corner with the text “AI Generated”.",
                    "zh_Hans": "是否添加水印标识，水印位于图片右下角，文案为“AI生成”。"
                  },
                  "label": {
                    "en_US": "Add watermark",
                    "pt_BR": "Add watermark",
                    "zh_Hans": "添加水印"
                  },
                  "llm_description": "Whether to add a watermark to the image. The watermark will appear at the bottom-right corner with the text “AI Generated”.",
                  "max": null,
                  "min": null,
                  "name": "watermark",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-18T19:23:14Z",
        "version_updated_at": "2025-04-18T19:23:14Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Voyage"
        },
        "category": "model",
        "created_at": "2025-02-17T07:01:17Z",
        "endpoint": {},
        "icon": "langgenius/packages/voyage/_assets/icon_s_en.svg",
        "index_id": "langgenius___voyage",
        "install_count": 617,
        "introduction": "",
        "label": {
          "en_US": "Voyage"
        },
        "latest_package_identifier": "langgenius/voyage:0.0.4@84dbd567848d1b47c91f72d6526916c560c235770f8b1b56479d9a315f5dff38",
        "latest_version": "0.0.4",
        "model": {
          "background": "#EFFDFD",
          "configurate_methods": [
            "predefined-model"
          ],
          "description": {
            "en_US": "Embedding and Rerank Model Supported"
          },
          "help": {
            "title": {
              "en_US": "Get your API key from Voyage AI",
              "zh_Hans": "从 Voyage 获取 API Key"
            },
            "url": {
              "en_US": "https://dash.voyageai.com/"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.svg"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "Voyage"
          },
          "model_credential_schema": null,
          "models": [
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "rerank-1"
              },
              "model": "rerank-1",
              "model_properties": {
                "context_size": 8000
              },
              "model_type": "rerank",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "rerank-2"
              },
              "model": "rerank-2",
              "model_properties": {
                "context_size": 16000
              },
              "model_type": "rerank",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "rerank-lite-1"
              },
              "model": "rerank-lite-1",
              "model_properties": {
                "context_size": 4000
              },
              "model_type": "rerank",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "rerank-lite-2"
              },
              "model": "rerank-lite-2",
              "model_properties": {
                "context_size": 8000
              },
              "model_type": "rerank",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "voyage-3-lite"
              },
              "model": "voyage-3-lite",
              "model_properties": {
                "context_size": 32000
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.00002",
                "output": null,
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "voyage-3"
              },
              "model": "voyage-3",
              "model_properties": {
                "context_size": 32000
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.00006",
                "output": null,
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "voyage-code-2"
              },
              "model": "voyage-code-2",
              "model_properties": {
                "context_size": 16000
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.00012",
                "output": null,
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "voyage-finance-2"
              },
              "model": "voyage-finance-2",
              "model_properties": {
                "context_size": 32000
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.00012",
                "output": null,
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "voyage-law-2"
              },
              "model": "voyage-law-2",
              "model_properties": {
                "context_size": 16000
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.00012",
                "output": null,
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "voyage-multilingual-2"
              },
              "model": "voyage-multilingual-2",
              "model_properties": {
                "context_size": 32000
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.00012",
                "output": null,
                "unit": "0.001"
              }
            }
          ],
          "position": {
            "rerank": [
              "rerank-2",
              "rerank-lite-2",
              "rerank-1",
              "rerank-lite-1"
            ],
            "text_embedding": [
              "voyage-3",
              "voyage-3-lite",
              "voyage-finance-2",
              "voyage-multilingual-2",
              "voyage-law-2",
              "voyage-code-2"
            ]
          },
          "provider": "voyage",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              }
            ]
          },
          "supported_model_types": [
            "text-embedding",
            "rerank"
          ]
        },
        "name": "voyage",
        "org": "langgenius",
        "plugin_id": "langgenius/voyage",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/voyage.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": false,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-03-21T09:19:29Z",
        "version_updated_at": "2025-03-21T09:19:29Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Get RSS feeds from RSSHub, a flexible and extensible RSS feed aggregator",
          "ja_JP": "RSSHubからRSSフィードを取得する",
          "zh_Hans": "从RSSHub获取RSS订阅源，RSSHub是一个灵活可扩展的RSS聚合器"
        },
        "category": "tool",
        "created_at": "2025-03-11T16:56:45Z",
        "endpoint": {},
        "icon": "stvlynn/packages/rsshub/_assets/icon.svg",
        "index_id": "stvlynn___rsshub",
        "install_count": 608,
        "introduction": "# RSSHub Dify Plugin\n\n> **Note**: For comprehensive information about available routes and parameters, please refer to the official [RSSHub Documentation](https://docs.rsshub.app/).\n\nThis is a RSSHub plugin for Dify that allows you to access RSS feeds from RSSHub through Dify.\n\n# Installation\n\nRead more in [Release](https://github.com/stvlynn/RSSHub-Dify-Plugin/releases)\n\n## Features\n\n- Get RSS feeds from RSSHub\n- Support for custom RSSHub instances\n- Limit the number of returned items\n- Convenient access to specific services (such as X/Twitter, LinkedIn)\n\n## Usage\n\n1. Install this plugin in Dify\n2. Use the plugin in your prompts, for example:\n\n```\nUse RSSHub to get the latest articles from sspai\n```\n\n## Available Tools\n\n### Custom Route\n\nGet RSS feeds from RSSHub using a custom route.\n\n**Parameters:**\n- `base_url`: The base URL of the RSSHub instance, default is `https://rsshub.app`\n- `route`: The RSSHub route path, e.g. `/zhihu/hot`\n- `limit`: Maximum number of items to return, default is 10\n\n### X (Twitter)\n\nGet RSS feeds from X (Twitter) via RSSHub.\n\n![](./_assets/X.png)\n\n**Parameters:**\n- `route_type`: Twitter route type, with the following options:\n  - User Timeline\n  - Keyword Search\n  - List Timeline\n  - Home Timeline\n  - Latest Home Timeline\n  - User Likes\n  - User Media\n- `base_url`: The base URL of the RSSHub instance, default is `https://rsshub.app`\n- `username`: Twitter username without @ (e.g., elonmusk). Required for user timeline, user likes, and user media route types\n- `keyword`: The keyword to search for. Required for keyword search route type\n- `list_id`: Twitter list ID. Required for list timeline route type\n- `exclude_replies`: Whether to exclude replies, default is false. Only applies to user timeline route type\n- `exclude_rts`: Whether to exclude retweets, default is false. Only applies to user timeline route type\n- `limit`: Maximum number of items to return, default is 10\n\n### LinkedIn\n\nGet RSS feeds from LinkedIn via RSSHub.\n\n![](./_assets/linkedin.png)\n\n**Parameters:**\n- `route_type`: LinkedIn route type, with the following options:\n  - Jobs\n- `base_url`: The base URL of the RSSHub instance, default is `https://rsshub.app`\n- `keywords`: Job search keywords\n- `job_types`: Job types, available options:\n  - Full Time\n  - Part Time\n  - Contractor\n  - All\n- `exp_levels`: Experience levels, available options:\n  - Internship\n  - Entry Level\n  - Associate\n  - Mid-Senior Level\n  - Director\n  - All\n- `work_type`: Work type, available options:\n  - Onsite\n  - Remote\n  - Hybrid\n  - Any\n- `time_posted`: Filter by when the job was posted, available options:\n  - Past 24 hours\n  - Past week\n  - Past month\n  - Any time\n- `geo_id`: Geographic location ID (e.g., 91000012 for East Asia)\n- `limit`: Maximum number of items to return, default is 10\n\n### Threads\n\nGet RSS feeds from Threads via RSSHub.\n\n![](./_assets/threads.png)\n\n**Parameters:**\n- `route_type`: Threads route type, with the following options:\n  - User\n- `base_url`: The base URL of the RSSHub instance, default is `https://rsshub.app`\n- `username`: Threads username without @ symbol\n- `show_author_in_title`: Show author name in title, default is true\n- `show_author_in_desc`: Show author name in description (RSS body), default is true\n- `show_quoted_in_title`: Show quoted thread in title, default is true\n- `show_emoji_for_quotes_and_reply`: Use 🔁 instead of QT, ↩️ instead of Re, default is true\n- `replies`: Include replies, default is true\n- `show_author_avatar_in_desc`: Show author avatar in description, default is false (not recommended if your RSS reader extracts images from description)\n- `show_quoted_author_avatar_in_desc`: Show quoted author avatar in description, default is false (not recommended if your RSS reader extracts images from description)\n- `limit`: Maximum number of items to return, default is 10\n\n### Discord\n\nGet RSS feeds from Discord via RSSHub.\n\n![](./_assets/discord.png)\n\n**Parameters:**\n- `route_type`: Discord route type, with the following options:\n  - Channel Messages\n  - Guild Search\n- `base_url`: The base URL of the RSSHub instance, default is `https://rsshub.app`\n- `channel_id`: Discord channel ID, required for Channel Messages route type\n- `guild_id`: Discord server ID, required for Guild Search route type\n- `search_params`: Search parameters for Guild Search route type (e.g., content=friendly&has=image,video). Supports content, author_id, mentions, has, min_id, max_id, channel_id, pinned, etc.\n- `discord_authorization`: Discord authorization header from the browser (required for both route types)\n- `limit`: Maximum number of items to return, default is 10\n\n### Google News\n\nGet RSS feeds from Google News via RSSHub.\n\n![](./_assets/google_news.png)\n\n**Parameters:**\n- `base_url`: The base URL of the RSSHub instance, default is `https://rsshub.app`\n- `category`: Category title of Google News, e.g. 'Top stories', 'World', 'Business'\n- `language_code`: Language code for Google News content, e.g. 'en-US', 'zh-CN', 'ja-JP'\n- `country_code`: Country or region code for Google News content, e.g. 'US', 'CN', 'JP'\n- `country_edition`: Country edition for Google News, usually in format 'COUNTRY:LANGUAGE', e.g. 'US:en', 'CN:zh'\n- `limit`: Maximum number of items to return, default is 10\n\n## Supported Routes\n\nRSSHub supports a large number of routes. You can view all supported routes in the [RSSHub Documentation](https://docs.rsshub.app/).\n\nHere are some commonly used route examples:\n\n- `/zhihu/hot` - Zhihu Hot List\n- `/sspai/matrix` - Sspai Matrix\n- `/36kr/hot-list` - 36Kr Hot List\n- `/weibo/search/hot` - Weibo Hot Search\n\n## Developer\n\n- [Steven Lynn](https://github.com/stvlynn)\n\n## License\n\n[MIT](./LICENSE)\n\n## rsshub\n\n**Author:** stvlynn\n**Version:** 0.0.1\n**Type:** tool\n\n### Description\n\n\n\n",
        "label": {
          "en_US": "RSSHub",
          "ja_JP": "RSSHub",
          "zh_Hans": "RSSHub订阅"
        },
        "latest_package_identifier": "stvlynn/rsshub:0.0.2@553500946c623490081cd63e54504f53a48c44ad792678fd566acb381c16f244",
        "latest_version": "0.0.2",
        "model": {},
        "name": "rsshub",
        "org": "stvlynn",
        "plugin_id": "stvlynn/rsshub",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/rsshub.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {}
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "stvlynn",
            "description": {
              "en_US": "Get RSS feeds from RSSHub",
              "ja_JP": "RSSHubからRSSフィードを取得",
              "zh_Hans": "获取RSSHub的RSS订阅源"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "RSSHub",
              "ja_JP": "RSSHub",
              "zh_Hans": "RSSHub订阅"
            },
            "name": "rsshub",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Get RSS feeds from RSSHub using a custom route",
                  "ja_JP": "カスタムルートを使用してRSSHubからRSSフィードを取得",
                  "zh_Hans": "使用自定义路由从RSSHub获取RSS订阅源"
                },
                "llm": "A tool to fetch RSS feeds from RSSHub using any custom route path."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "stvlynn",
                "label": {
                  "en_US": "Custom Route",
                  "ja_JP": "カスタムルート",
                  "zh_Hans": "自定义路由"
                },
                "name": "custom_route"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": "https://rsshub.app",
                  "form": "form",
                  "human_description": {
                    "en_US": "The base URL of RSSHub instance (default is https://rsshub.app)",
                    "ja_JP": "RSSHubインスタンスのベースURL（デフォルトはhttps://rsshub.app）",
                    "zh_Hans": "RSSHub实例的基础URL（默认为https://rsshub.app）"
                  },
                  "label": {
                    "en_US": "RSSHub Base URL",
                    "ja_JP": "RSSHubベースURL",
                    "zh_Hans": "RSSHub基础URL"
                  },
                  "llm_description": "The base URL of RSSHub instance (default is https://rsshub.app)",
                  "max": null,
                  "min": null,
                  "name": "base_url",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Access key for RSSHub routes (e.g. ILoveRSSHub). Leave empty if not needed.",
                    "ja_JP": "RSSHubルートのアクセスキー（例：ILoveRSSHub）。必要ない場合は空のままにしてください。",
                    "zh_Hans": "RSSHub路由的访问密钥（例如：ILoveRSSHub）。如不需要请留空。"
                  },
                  "label": {
                    "en_US": "RSSHub Access Key",
                    "ja_JP": "RSSHubアクセスキー",
                    "zh_Hans": "RSSHub访问密钥"
                  },
                  "llm_description": "Access key for RSSHub routes (e.g. ILoveRSSHub). Leave empty if not needed.",
                  "max": null,
                  "min": null,
                  "name": "access_key",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The RSSHub route path (e.g. /zhihu/hot, /sspai/matrix)",
                    "ja_JP": "RSSHubのルートパス（例：/zhihu/hot, /sspai/matrix）",
                    "zh_Hans": "RSSHub的路由路径（例如：/zhihu/hot, /sspai/matrix）"
                  },
                  "label": {
                    "en_US": "RSSHub Route",
                    "ja_JP": "RSSHubルート",
                    "zh_Hans": "RSSHub路由"
                  },
                  "llm_description": "The RSSHub route path without the base URL (e.g. /zhihu/hot, /sspai/matrix)",
                  "max": null,
                  "min": null,
                  "name": "route",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Maximum number of items to return (default: 10)",
                    "ja_JP": "返される最大アイテム数（デフォルト：10）",
                    "zh_Hans": "返回的最大条目数量（默认：10）"
                  },
                  "label": {
                    "en_US": "Item Limit",
                    "ja_JP": "アイテム数制限",
                    "zh_Hans": "条目数量限制"
                  },
                  "llm_description": "Maximum number of items to return (default: 10)",
                  "max": null,
                  "min": null,
                  "name": "limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get RSS feeds from X (Twitter) via RSSHub",
                  "ja_JP": "RSSHubを通じてX (Twitter)のRSSフィードを取得",
                  "zh_Hans": "通过RSSHub获取X (Twitter)的RSS订阅源"
                },
                "llm": "A tool to fetch RSS feeds from X (Twitter) using RSSHub as a proxy."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "stvlynn",
                "label": {
                  "en_US": "X (Twitter)",
                  "ja_JP": "X (Twitter)",
                  "zh_Hans": "X (Twitter)"
                },
                "name": "twitter"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": "user",
                  "form": "form",
                  "human_description": {
                    "en_US": "The type of Twitter route to use",
                    "ja_JP": "使用するTwitterルートのタイプ",
                    "zh_Hans": "要使用的Twitter路由类型"
                  },
                  "label": {
                    "en_US": "Route Type",
                    "ja_JP": "ルートタイプ",
                    "zh_Hans": "路由类型"
                  },
                  "llm_description": "The type of Twitter route to use",
                  "max": null,
                  "min": null,
                  "name": "route_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "User Timeline",
                        "ja_JP": "ユーザータイムライン",
                        "zh_Hans": "用户时间线"
                      },
                      "value": "user"
                    },
                    {
                      "label": {
                        "en_US": "Keyword Search",
                        "ja_JP": "キーワード検索",
                        "zh_Hans": "关键词搜索"
                      },
                      "value": "keyword"
                    },
                    {
                      "label": {
                        "en_US": "List Timeline",
                        "ja_JP": "リストタイムライン",
                        "zh_Hans": "列表时间线"
                      },
                      "value": "list"
                    },
                    {
                      "label": {
                        "en_US": "Home Timeline",
                        "ja_JP": "ホームタイムライン",
                        "zh_Hans": "主页时间线"
                      },
                      "value": "home"
                    },
                    {
                      "label": {
                        "en_US": "Latest Home Timeline",
                        "ja_JP": "最新ホームタイムライン",
                        "zh_Hans": "最新主页时间线"
                      },
                      "value": "home_latest"
                    },
                    {
                      "label": {
                        "en_US": "User Likes",
                        "ja_JP": "ユーザーのいいね",
                        "zh_Hans": "用户喜欢的推文"
                      },
                      "value": "likes"
                    },
                    {
                      "label": {
                        "en_US": "User Media",
                        "ja_JP": "ユーザーメディア",
                        "zh_Hans": "用户媒体推文"
                      },
                      "value": "media"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "https://rsshub.app",
                  "form": "form",
                  "human_description": {
                    "en_US": "The base URL of RSSHub instance (default is https://rsshub.app)",
                    "ja_JP": "RSSHubインスタンスのベースURL（デフォルトはhttps://rsshub.app）",
                    "zh_Hans": "RSSHub实例的基础URL（默认为https://rsshub.app）"
                  },
                  "label": {
                    "en_US": "RSSHub Base URL",
                    "ja_JP": "RSSHubベースURL",
                    "zh_Hans": "RSSHub基础URL"
                  },
                  "llm_description": "The base URL of RSSHub instance (default is https://rsshub.app)",
                  "max": null,
                  "min": null,
                  "name": "base_url",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Access key for RSSHub routes (e.g. ILoveRSSHub). Leave empty if not needed.",
                    "ja_JP": "RSSHubルートのアクセスキー（例：ILoveRSSHub）。必要ない場合は空のままにしてください。",
                    "zh_Hans": "RSSHub路由的访问密钥（例如：ILoveRSSHub）。如不需要请留空。"
                  },
                  "label": {
                    "en_US": "RSSHub Access Key",
                    "ja_JP": "RSSHubアクセスキー",
                    "zh_Hans": "RSSHub访问密钥"
                  },
                  "llm_description": "Access key for RSSHub routes (e.g. ILoveRSSHub). Leave empty if not needed.",
                  "max": null,
                  "min": null,
                  "name": "access_key",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The Twitter username without @ (e.g. elonmusk). Required for user, likes, and media routes.",
                    "ja_JP": "@なしのTwitterユーザー名（例：elonmusk）。ユーザー、いいね、メディアルートに必要。",
                    "zh_Hans": "Twitter用户名，不包含@符号（例如：elonmusk）。用于用户、喜欢和媒体路由。"
                  },
                  "label": {
                    "en_US": "Twitter Username",
                    "ja_JP": "Twitterユーザー名",
                    "zh_Hans": "Twitter用户名"
                  },
                  "llm_description": "The Twitter username without @ (e.g. elonmusk). Required for user, likes, and media routes.",
                  "max": null,
                  "min": null,
                  "name": "username",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The keyword to search for. Required for keyword route.",
                    "ja_JP": "検索するキーワード。キーワードルートに必要。",
                    "zh_Hans": "要搜索的关键词。关键词路由必填。"
                  },
                  "label": {
                    "en_US": "Keyword",
                    "ja_JP": "キーワード",
                    "zh_Hans": "关键词"
                  },
                  "llm_description": "The keyword to search for. Required for keyword route.",
                  "max": null,
                  "min": null,
                  "name": "keyword",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The Twitter list ID. Required for list route.",
                    "ja_JP": "TwitterリストID。リストルートに必要。",
                    "zh_Hans": "Twitter列表ID。列表路由必填。"
                  },
                  "label": {
                    "en_US": "List ID",
                    "ja_JP": "リストID",
                    "zh_Hans": "列表ID"
                  },
                  "llm_description": "The Twitter list ID. Required for list route.",
                  "max": null,
                  "min": null,
                  "name": "list_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to exclude replies from the timeline",
                    "ja_JP": "タイムラインから返信を除外するかどうか",
                    "zh_Hans": "是否从时间线中排除回复"
                  },
                  "label": {
                    "en_US": "Exclude Replies",
                    "ja_JP": "返信を除外",
                    "zh_Hans": "排除回复"
                  },
                  "llm_description": "Whether to exclude replies from the timeline",
                  "max": null,
                  "min": null,
                  "name": "exclude_replies",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to exclude retweets from the timeline",
                    "ja_JP": "タイムラインからリツイートを除外するかどうか",
                    "zh_Hans": "是否从时间线中排除转发"
                  },
                  "label": {
                    "en_US": "Exclude Retweets",
                    "ja_JP": "リツイートを除外",
                    "zh_Hans": "排除转发"
                  },
                  "llm_description": "Whether to exclude retweets from the timeline",
                  "max": null,
                  "min": null,
                  "name": "exclude_rts",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Maximum number of items to return (default: 10)",
                    "ja_JP": "返される最大アイテム数（デフォルト：10）",
                    "zh_Hans": "返回的最大条目数量（默认：10）"
                  },
                  "label": {
                    "en_US": "Item Limit",
                    "ja_JP": "アイテム数制限",
                    "zh_Hans": "条目数量限制"
                  },
                  "llm_description": "Maximum number of items to return (default: 10)",
                  "max": null,
                  "min": null,
                  "name": "limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get RSS feeds from LinkedIn via RSSHub",
                  "ja_JP": "RSSHubを通じてLinkedInのRSSフィードを取得",
                  "zh_Hans": "通过RSSHub获取LinkedIn的RSS订阅源"
                },
                "llm": "A tool to fetch RSS feeds from LinkedIn using RSSHub as a proxy."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "stvlynn",
                "label": {
                  "en_US": "LinkedIn",
                  "ja_JP": "LinkedIn",
                  "zh_Hans": "LinkedIn"
                },
                "name": "linkedin"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": "jobs",
                  "form": "form",
                  "human_description": {
                    "en_US": "The type of LinkedIn route to use",
                    "ja_JP": "使用するLinkedInルートのタイプ",
                    "zh_Hans": "要使用的LinkedIn路由类型"
                  },
                  "label": {
                    "en_US": "Route Type",
                    "ja_JP": "ルートタイプ",
                    "zh_Hans": "路由类型"
                  },
                  "llm_description": "The type of LinkedIn route to use",
                  "max": null,
                  "min": null,
                  "name": "route_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "Jobs",
                        "ja_JP": "求人検索",
                        "zh_Hans": "职位搜索"
                      },
                      "value": "jobs"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "https://rsshub.app",
                  "form": "form",
                  "human_description": {
                    "en_US": "The base URL of RSSHub instance (default is https://rsshub.app)",
                    "ja_JP": "RSSHubインスタンスのベースURL（デフォルトはhttps://rsshub.app）",
                    "zh_Hans": "RSSHub实例的基础URL（默认为https://rsshub.app）"
                  },
                  "label": {
                    "en_US": "RSSHub Base URL",
                    "ja_JP": "RSSHubベースURL",
                    "zh_Hans": "RSSHub基础URL"
                  },
                  "llm_description": "The base URL of RSSHub instance (default is https://rsshub.app)",
                  "max": null,
                  "min": null,
                  "name": "base_url",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Access key for RSSHub routes (e.g. ILoveRSSHub). Leave empty if not needed.",
                    "ja_JP": "RSSHubルートのアクセスキー（例：ILoveRSSHub）。必要ない場合は空のままにしてください。",
                    "zh_Hans": "RSSHub路由的访问密钥（例如：ILoveRSSHub）。如不需要请留空。"
                  },
                  "label": {
                    "en_US": "RSSHub Access Key",
                    "ja_JP": "RSSHubアクセスキー",
                    "zh_Hans": "RSSHub访问密钥"
                  },
                  "llm_description": "Access key for RSSHub routes (e.g. ILoveRSSHub). Leave empty if not needed.",
                  "max": null,
                  "min": null,
                  "name": "access_key",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Search keywords for jobs",
                    "ja_JP": "求人検索キーワード",
                    "zh_Hans": "职位搜索关键词"
                  },
                  "label": {
                    "en_US": "Keywords",
                    "ja_JP": "キーワード",
                    "zh_Hans": "关键词"
                  },
                  "llm_description": "Search keywords for jobs",
                  "max": null,
                  "min": null,
                  "name": "keywords",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "all",
                  "form": "form",
                  "human_description": {
                    "en_US": "The type of jobs to search for",
                    "ja_JP": "検索する雇用形態",
                    "zh_Hans": "要搜索的职位类型"
                  },
                  "label": {
                    "en_US": "Job Types",
                    "ja_JP": "雇用形態",
                    "zh_Hans": "职位类型"
                  },
                  "llm_description": "The type of jobs to search for",
                  "max": null,
                  "min": null,
                  "name": "job_types",
                  "options": [
                    {
                      "label": {
                        "en_US": "Full Time",
                        "ja_JP": "フルタイム",
                        "zh_Hans": "全职"
                      },
                      "value": "F"
                    },
                    {
                      "label": {
                        "en_US": "Part Time",
                        "ja_JP": "パートタイム",
                        "zh_Hans": "兼职"
                      },
                      "value": "P"
                    },
                    {
                      "label": {
                        "en_US": "Contractor",
                        "ja_JP": "契約社員",
                        "zh_Hans": "合同工"
                      },
                      "value": "C"
                    },
                    {
                      "label": {
                        "en_US": "All",
                        "ja_JP": "すべて",
                        "zh_Hans": "全部"
                      },
                      "value": "all"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "all",
                  "form": "form",
                  "human_description": {
                    "en_US": "The experience level required for the jobs",
                    "ja_JP": "求人に必要な経験レベル",
                    "zh_Hans": "职位所需的经验等级"
                  },
                  "label": {
                    "en_US": "Experience Levels",
                    "ja_JP": "経験レベル",
                    "zh_Hans": "经验等级"
                  },
                  "llm_description": "The experience level required for the jobs",
                  "max": null,
                  "min": null,
                  "name": "exp_levels",
                  "options": [
                    {
                      "label": {
                        "en_US": "Internship",
                        "ja_JP": "インターンシップ",
                        "zh_Hans": "实习"
                      },
                      "value": "1"
                    },
                    {
                      "label": {
                        "en_US": "Entry Level",
                        "ja_JP": "新卒・第二新卒",
                        "zh_Hans": "入门级"
                      },
                      "value": "2"
                    },
                    {
                      "label": {
                        "en_US": "Associate",
                        "ja_JP": "アソシエイト",
                        "zh_Hans": "助理级"
                      },
                      "value": "3"
                    },
                    {
                      "label": {
                        "en_US": "Mid-Senior Level",
                        "ja_JP": "中堅・管理職",
                        "zh_Hans": "中高级"
                      },
                      "value": "4"
                    },
                    {
                      "label": {
                        "en_US": "Director",
                        "ja_JP": "ディレクター",
                        "zh_Hans": "总监级"
                      },
                      "value": "5"
                    },
                    {
                      "label": {
                        "en_US": "All",
                        "ja_JP": "すべて",
                        "zh_Hans": "全部"
                      },
                      "value": "all"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "0",
                  "form": "form",
                  "human_description": {
                    "en_US": "The work type of the jobs",
                    "ja_JP": "求人の勤務形態",
                    "zh_Hans": "职位的工作方式"
                  },
                  "label": {
                    "en_US": "Work Type",
                    "ja_JP": "勤務形態",
                    "zh_Hans": "工作方式"
                  },
                  "llm_description": "The work type of the jobs",
                  "max": null,
                  "min": null,
                  "name": "work_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "Onsite",
                        "ja_JP": "オンサイト",
                        "zh_Hans": "现场办公"
                      },
                      "value": "1"
                    },
                    {
                      "label": {
                        "en_US": "Remote",
                        "ja_JP": "リモート",
                        "zh_Hans": "远程办公"
                      },
                      "value": "2"
                    },
                    {
                      "label": {
                        "en_US": "Hybrid",
                        "ja_JP": "ハイブリッド",
                        "zh_Hans": "混合办公"
                      },
                      "value": "3"
                    },
                    {
                      "label": {
                        "en_US": "Any",
                        "ja_JP": "指定なし",
                        "zh_Hans": "任意"
                      },
                      "value": "0"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "0",
                  "form": "form",
                  "human_description": {
                    "en_US": "Filter by when the job was posted",
                    "ja_JP": "求人の投稿時間でフィルタリング",
                    "zh_Hans": "按职位发布时间筛选"
                  },
                  "label": {
                    "en_US": "Time Posted",
                    "ja_JP": "投稿時間",
                    "zh_Hans": "发布时间"
                  },
                  "llm_description": "Filter by when the job was posted",
                  "max": null,
                  "min": null,
                  "name": "time_posted",
                  "options": [
                    {
                      "label": {
                        "en_US": "Past 24 hours",
                        "ja_JP": "過去24時間",
                        "zh_Hans": "过去24小时"
                      },
                      "value": "r86400"
                    },
                    {
                      "label": {
                        "en_US": "Past week",
                        "ja_JP": "過去1週間",
                        "zh_Hans": "过去一周"
                      },
                      "value": "r604800"
                    },
                    {
                      "label": {
                        "en_US": "Past month",
                        "ja_JP": "過去1ヶ月",
                        "zh_Hans": "过去一个月"
                      },
                      "value": "r2592000"
                    },
                    {
                      "label": {
                        "en_US": "Any time",
                        "ja_JP": "指定なし",
                        "zh_Hans": "任意时间"
                      },
                      "value": "0"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Geographic location ID (e.g. 91000012 for East Asia)",
                    "ja_JP": "地理的位置ID（例：91000012は東アジアを表す）",
                    "zh_Hans": "地理位置ID（如91000012代表东亚）"
                  },
                  "label": {
                    "en_US": "Geographic Location ID",
                    "ja_JP": "地理的位置ID",
                    "zh_Hans": "地理位置ID"
                  },
                  "llm_description": "Geographic location ID (e.g. 91000012 for East Asia)",
                  "max": null,
                  "min": null,
                  "name": "geo_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Maximum number of items to return (default: 10)",
                    "ja_JP": "返される最大アイテム数（デフォルト：10）",
                    "zh_Hans": "返回的最大条目数量（默认：10）"
                  },
                  "label": {
                    "en_US": "Item Limit",
                    "ja_JP": "アイテム数制限",
                    "zh_Hans": "条目数量限制"
                  },
                  "llm_description": "Maximum number of items to return (default: 10)",
                  "max": null,
                  "min": null,
                  "name": "limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get RSS feeds from Threads via RSSHub",
                  "ja_JP": "RSSHubを通じてThreadsのRSSフィードを取得",
                  "zh_Hans": "通过RSSHub获取Threads的RSS订阅源"
                },
                "llm": "A tool to fetch RSS feeds from Threads using RSSHub as a proxy."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "stvlynn",
                "label": {
                  "en_US": "Threads",
                  "ja_JP": "Threads",
                  "zh_Hans": "Threads"
                },
                "name": "threads"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": "user",
                  "form": "form",
                  "human_description": {
                    "en_US": "The type of Threads route to use",
                    "ja_JP": "使用するThreadsルートのタイプ",
                    "zh_Hans": "要使用的Threads路由类型"
                  },
                  "label": {
                    "en_US": "Route Type",
                    "ja_JP": "ルートタイプ",
                    "zh_Hans": "路由类型"
                  },
                  "llm_description": "The type of Threads route to use",
                  "max": null,
                  "min": null,
                  "name": "route_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "User Timeline",
                        "ja_JP": "ユーザータイムライン",
                        "zh_Hans": "用户时间线"
                      },
                      "value": "user"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "https://rsshub.app",
                  "form": "form",
                  "human_description": {
                    "en_US": "The base URL of RSSHub instance (default is https://rsshub.app)",
                    "ja_JP": "RSSHubインスタンスのベースURL（デフォルトはhttps://rsshub.app）",
                    "zh_Hans": "RSSHub实例的基础URL（默认为https://rsshub.app）"
                  },
                  "label": {
                    "en_US": "RSSHub Base URL",
                    "ja_JP": "RSSHubベースURL",
                    "zh_Hans": "RSSHub基础URL"
                  },
                  "llm_description": "The base URL of RSSHub instance (default is https://rsshub.app)",
                  "max": null,
                  "min": null,
                  "name": "base_url",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Access key for RSSHub routes (e.g. ILoveRSSHub). Leave empty if not needed.",
                    "ja_JP": "RSSHubルートのアクセスキー（例：ILoveRSSHub）。必要ない場合は空のままにしてください。",
                    "zh_Hans": "RSSHub路由的访问密钥（例如：ILoveRSSHub）。如不需要请留空。"
                  },
                  "label": {
                    "en_US": "RSSHub Access Key",
                    "ja_JP": "RSSHubアクセスキー",
                    "zh_Hans": "RSSHub访问密钥"
                  },
                  "llm_description": "Access key for RSSHub routes (e.g. ILoveRSSHub). Leave empty if not needed.",
                  "max": null,
                  "min": null,
                  "name": "access_key",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The username of Threads account",
                    "ja_JP": "Threadsアカウントのユーザー名",
                    "zh_Hans": "Threads账户的用户名"
                  },
                  "label": {
                    "en_US": "Threads Username",
                    "ja_JP": "Threadsユーザー名",
                    "zh_Hans": "Threads用户名"
                  },
                  "llm_description": "The username of Threads account",
                  "max": null,
                  "min": null,
                  "name": "username",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "Show author name in title",
                    "ja_JP": "タイトルに作者名を表示する",
                    "zh_Hans": "在标题中显示作者名"
                  },
                  "label": {
                    "en_US": "Show Author in Title",
                    "ja_JP": "タイトルに作者を表示",
                    "zh_Hans": "在标题中显示作者"
                  },
                  "llm_description": "Show author name in title",
                  "max": null,
                  "min": null,
                  "name": "show_author_in_title",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "Show author name in description (RSS body)",
                    "ja_JP": "説明（RSSの本文）に作者名を表示する",
                    "zh_Hans": "在描述中显示作者名（RSS正文）"
                  },
                  "label": {
                    "en_US": "Show Author in Description",
                    "ja_JP": "説明に作者を表示",
                    "zh_Hans": "在描述中显示作者"
                  },
                  "llm_description": "Show author name in description (RSS body)",
                  "max": null,
                  "min": null,
                  "name": "show_author_in_desc",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "Show quoted thread in title",
                    "ja_JP": "タイトルに引用されたスレッドを表示する",
                    "zh_Hans": "在标题中显示引用的帖子"
                  },
                  "label": {
                    "en_US": "Show Quoted in Title",
                    "ja_JP": "タイトルに引用を表示",
                    "zh_Hans": "在标题中显示引用"
                  },
                  "llm_description": "Show quoted thread in title",
                  "max": null,
                  "min": null,
                  "name": "show_quoted_in_title",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "Use 🔁 instead of QT, ↩️ instead of Re",
                    "ja_JP": "QTの代わりに🔁、Reの代わりに↩️を使用する",
                    "zh_Hans": "使用🔁代替QT，↩️代替Re"
                  },
                  "label": {
                    "en_US": "Use Emoji for Quotes and Replies",
                    "ja_JP": "引用と返信に絵文字を使用",
                    "zh_Hans": "使用表情符号表示引用和回复"
                  },
                  "llm_description": "Use 🔁 instead of QT, ↩️ instead of Re",
                  "max": null,
                  "min": null,
                  "name": "show_emoji_for_quotes_and_reply",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "Show replies",
                    "ja_JP": "返信を表示する",
                    "zh_Hans": "显示回复"
                  },
                  "label": {
                    "en_US": "Show Replies",
                    "ja_JP": "返信を表示",
                    "zh_Hans": "显示回复"
                  },
                  "llm_description": "Show replies",
                  "max": null,
                  "min": null,
                  "name": "replies",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Show avatar of author in description (Not recommended if your RSS reader extracts images from description)",
                    "ja_JP": "説明に作者のアバターを表示する（RSSリーダーが説明から画像を抽出する場合は推奨されません）",
                    "zh_Hans": "在描述中显示作者头像（如果您的RSS阅读器从描述中提取图片，不推荐使用）"
                  },
                  "label": {
                    "en_US": "Show Author Avatar in Description",
                    "ja_JP": "説明に作者のアバターを表示",
                    "zh_Hans": "在描述中显示作者头像"
                  },
                  "llm_description": "Show avatar of author in description (Not recommended if your RSS reader extracts images from description)",
                  "max": null,
                  "min": null,
                  "name": "show_author_avatar_in_desc",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Show avatar of quoted author in description (Not recommended if your RSS reader extracts images from description)",
                    "ja_JP": "説明に引用された作者のアバターを表示する（RSSリーダーが説明から画像を抽出する場合は推奨されません）",
                    "zh_Hans": "在描述中显示被引用作者头像（如果您的RSS阅读器从描述中提取图片，不推荐使用）"
                  },
                  "label": {
                    "en_US": "Show Quoted Author Avatar in Description",
                    "ja_JP": "説明に引用された作者のアバターを表示",
                    "zh_Hans": "在描述中显示被引用作者头像"
                  },
                  "llm_description": "Show avatar of quoted author in description (Not recommended if your RSS reader extracts images from description)",
                  "max": null,
                  "min": null,
                  "name": "show_quoted_author_avatar_in_desc",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": 10,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Maximum number of items to return (default: 10)",
                    "ja_JP": "返される最大アイテム数（デフォルト：10）",
                    "zh_Hans": "返回的最大条目数量（默认：10）"
                  },
                  "label": {
                    "en_US": "Item Limit",
                    "ja_JP": "アイテム数制限",
                    "zh_Hans": "条目数量限制"
                  },
                  "llm_description": "Maximum number of items to return (default: 10)",
                  "max": null,
                  "min": null,
                  "name": "limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get RSS feeds from Discord via RSSHub",
                  "ja_JP": "RSSHubを通じてDiscordのRSSフィードを取得",
                  "zh_Hans": "通过RSSHub获取Discord的RSS订阅源"
                },
                "llm": "A tool to fetch RSS feeds from Discord using RSSHub as a proxy."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "stvlynn",
                "label": {
                  "en_US": "Discord",
                  "ja_JP": "Discord",
                  "zh_Hans": "Discord"
                },
                "name": "discord"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": "channel",
                  "form": "form",
                  "human_description": {
                    "en_US": "The type of Discord route to use",
                    "ja_JP": "使用するDiscordルートのタイプ",
                    "zh_Hans": "要使用的Discord路由类型"
                  },
                  "label": {
                    "en_US": "Route Type",
                    "ja_JP": "ルートタイプ",
                    "zh_Hans": "路由类型"
                  },
                  "llm_description": "The type of Discord route to use",
                  "max": null,
                  "min": null,
                  "name": "route_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "Channel Messages",
                        "ja_JP": "チャンネルメッセージ",
                        "zh_Hans": "频道消息"
                      },
                      "value": "channel"
                    },
                    {
                      "label": {
                        "en_US": "Guild Search",
                        "ja_JP": "サーバー検索",
                        "zh_Hans": "服务器搜索"
                      },
                      "value": "search"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "https://rsshub.app",
                  "form": "form",
                  "human_description": {
                    "en_US": "The base URL of RSSHub instance (default is https://rsshub.app)",
                    "ja_JP": "RSSHubインスタンスのベースURL（デフォルトはhttps://rsshub.app）",
                    "zh_Hans": "RSSHub实例的基础URL（默认为https://rsshub.app）"
                  },
                  "label": {
                    "en_US": "RSSHub Base URL",
                    "ja_JP": "RSSHubベースURL",
                    "zh_Hans": "RSSHub基础URL"
                  },
                  "llm_description": "The base URL of RSSHub instance (default is https://rsshub.app)",
                  "max": null,
                  "min": null,
                  "name": "base_url",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Access key for RSSHub routes (e.g. ILoveRSSHub). Leave empty if not needed.",
                    "ja_JP": "RSSHubルートのアクセスキー（例：ILoveRSSHub）。必要ない場合は空のままにしてください。",
                    "zh_Hans": "RSSHub路由的访问密钥（例如：ILoveRSSHub）。如不需要请留空。"
                  },
                  "label": {
                    "en_US": "RSSHub Access Key",
                    "ja_JP": "RSSHubアクセスキー",
                    "zh_Hans": "RSSHub访问密钥"
                  },
                  "llm_description": "Access key for RSSHub routes (e.g. ILoveRSSHub). Leave empty if not needed.",
                  "max": null,
                  "min": null,
                  "name": "access_key",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of Discord channel (required for Channel Messages route type)",
                    "ja_JP": "DiscordチャンネルのID（チャンネルメッセージルートタイプに必要）",
                    "zh_Hans": "Discord频道的ID（频道消息路由类型必填）"
                  },
                  "label": {
                    "en_US": "Channel ID",
                    "ja_JP": "チャンネルID",
                    "zh_Hans": "频道ID"
                  },
                  "llm_description": "The ID of Discord channel (required for Channel Messages route type)",
                  "max": null,
                  "min": null,
                  "name": "channel_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of Discord guild/server (required for Guild Search route type)",
                    "ja_JP": "Discordサーバーの ID（サーバー検索ルートタイプに必要）",
                    "zh_Hans": "Discord服务器的ID（服务器搜索路由类型必填）"
                  },
                  "label": {
                    "en_US": "Guild ID",
                    "ja_JP": "サーバーID",
                    "zh_Hans": "服务器ID"
                  },
                  "llm_description": "The ID of Discord guild/server (required for Guild Search route type)",
                  "max": null,
                  "min": null,
                  "name": "guild_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Search parameters for Guild Search route type (e.g. content=friendly&has=image,video)",
                    "ja_JP": "サーバー検索ルートタイプの検索パラメータ（例：content=friendly&has=image,video）",
                    "zh_Hans": "服务器搜索路由类型的搜索参数（例如：content=friendly&has=image,video）"
                  },
                  "label": {
                    "en_US": "Search Parameters",
                    "ja_JP": "検索パラメータ",
                    "zh_Hans": "搜索参数"
                  },
                  "llm_description": "Search parameters for Guild Search route type (e.g. content=friendly&has=image,video). Supports content, author_id, mentions, has, min_id, max_id, channel_id, pinned.",
                  "max": null,
                  "min": null,
                  "name": "search_params",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Discord authorization header from the browser (required for both route types)",
                    "ja_JP": "ブラウザから取得したDiscord認証ヘッダー（両方のルートタイプに必要）",
                    "zh_Hans": "从浏览器获取的Discord授权头（两种路由类型都需要）"
                  },
                  "label": {
                    "en_US": "Discord Authorization",
                    "ja_JP": "Discord認証トークン",
                    "zh_Hans": "Discord授权令牌"
                  },
                  "llm_description": "Discord authorization header from the browser (required for both route types)",
                  "max": null,
                  "min": null,
                  "name": "discord_authorization",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 10,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Maximum number of items to return (default: 10)",
                    "ja_JP": "返される最大アイテム数（デフォルト：10）",
                    "zh_Hans": "返回的最大条目数量（默认：10）"
                  },
                  "label": {
                    "en_US": "Item Limit",
                    "ja_JP": "アイテム数制限",
                    "zh_Hans": "条目数量限制"
                  },
                  "llm_description": "Maximum number of items to return (default: 10)",
                  "max": null,
                  "min": null,
                  "name": "limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get RSS feeds from Google News via RSSHub",
                  "ja_JP": "RSSHubを通じてGoogleニュースのRSSフィードを取得",
                  "zh_Hans": "通过RSSHub获取Google新闻的RSS源"
                },
                "llm": "A tool to fetch RSS feeds from Google News using RSSHub as a proxy."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "stvlynn",
                "label": {
                  "en_US": "Google News",
                  "ja_JP": "Google ニュース",
                  "zh_Hans": "Google 新闻"
                },
                "name": "google_news"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": "https://rsshub.app",
                  "form": "form",
                  "human_description": {
                    "en_US": "The base URL of RSSHub instance",
                    "ja_JP": "RSSHubインスタンスのベースURL",
                    "zh_Hans": "RSSHub实例的基础URL"
                  },
                  "label": {
                    "en_US": "RSSHub Base URL",
                    "ja_JP": "RSSHubベースURL",
                    "zh_Hans": "RSSHub基础URL"
                  },
                  "llm_description": "The base URL of the RSSHub instance to use",
                  "max": null,
                  "min": null,
                  "name": "base_url",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Access key for RSSHub routes (e.g. ILoveRSSHub). Leave empty if not needed.",
                    "ja_JP": "RSSHubルートのアクセスキー（例：ILoveRSSHub）。必要ない場合は空のままにしてください。",
                    "zh_Hans": "RSSHub路由的访问密钥（例如：ILoveRSSHub）。如不需要请留空。"
                  },
                  "label": {
                    "en_US": "RSSHub Access Key",
                    "ja_JP": "RSSHubアクセスキー",
                    "zh_Hans": "RSSHub访问密钥"
                  },
                  "llm_description": "Access key for RSSHub routes (e.g. ILoveRSSHub). Leave empty if not needed.",
                  "max": null,
                  "min": null,
                  "name": "access_key",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The category title of Google News, e.g. 'Top stories', 'World', 'Business'",
                    "ja_JP": "Googleニュースのカテゴリタイトル、例：'Top stories'、'World'、'Business'",
                    "zh_Hans": "Google新闻的分类标题，例如'Top stories'、'World'、'Business'"
                  },
                  "label": {
                    "en_US": "Category Title",
                    "ja_JP": "カテゴリタイトル",
                    "zh_Hans": "分类标题"
                  },
                  "llm_description": "The category title of Google News, such as 'Top stories', 'World', 'Business'",
                  "max": null,
                  "min": null,
                  "name": "category",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "en-US",
                  "form": "form",
                  "human_description": {
                    "en_US": "The language code for Google News content",
                    "ja_JP": "Googleニュースコンテンツの言語コード",
                    "zh_Hans": "Google新闻内容的语言代码"
                  },
                  "label": {
                    "en_US": "Language",
                    "ja_JP": "言語",
                    "zh_Hans": "语言"
                  },
                  "llm_description": "The language code for Google News content (hl parameter)",
                  "max": null,
                  "min": null,
                  "name": "language_code",
                  "options": [
                    {
                      "label": {
                        "en_US": "English (US)",
                        "ja_JP": "英語（米国）",
                        "zh_Hans": "英语（美国）"
                      },
                      "value": "en-US"
                    },
                    {
                      "label": {
                        "en_US": "Chinese (Simplified)",
                        "ja_JP": "中国語（簡体字）",
                        "zh_Hans": "中文（简体）"
                      },
                      "value": "zh-CN"
                    },
                    {
                      "label": {
                        "en_US": "Japanese",
                        "ja_JP": "日本語",
                        "zh_Hans": "日语"
                      },
                      "value": "ja-JP"
                    },
                    {
                      "label": {
                        "en_US": "French",
                        "ja_JP": "フランス語",
                        "zh_Hans": "法语"
                      },
                      "value": "fr-FR"
                    },
                    {
                      "label": {
                        "en_US": "German",
                        "ja_JP": "ドイツ語",
                        "zh_Hans": "德语"
                      },
                      "value": "de-DE"
                    },
                    {
                      "label": {
                        "en_US": "Spanish",
                        "ja_JP": "スペイン語",
                        "zh_Hans": "西班牙语"
                      },
                      "value": "es-ES"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "US",
                  "form": "form",
                  "human_description": {
                    "en_US": "The country or region code for Google News content",
                    "ja_JP": "Googleニュースコンテンツの国または地域コード",
                    "zh_Hans": "Google新闻内容的国家或地区代码"
                  },
                  "label": {
                    "en_US": "Country/Region",
                    "ja_JP": "国/地域",
                    "zh_Hans": "国家/地区"
                  },
                  "llm_description": "The country or region code for Google News content (gl parameter)",
                  "max": null,
                  "min": null,
                  "name": "country_code",
                  "options": [
                    {
                      "label": {
                        "en_US": "United States",
                        "ja_JP": "アメリカ合衆国",
                        "zh_Hans": "美国"
                      },
                      "value": "US"
                    },
                    {
                      "label": {
                        "en_US": "China",
                        "ja_JP": "中国",
                        "zh_Hans": "中国"
                      },
                      "value": "CN"
                    },
                    {
                      "label": {
                        "en_US": "Japan",
                        "ja_JP": "日本",
                        "zh_Hans": "日本"
                      },
                      "value": "JP"
                    },
                    {
                      "label": {
                        "en_US": "France",
                        "ja_JP": "フランス",
                        "zh_Hans": "法国"
                      },
                      "value": "FR"
                    },
                    {
                      "label": {
                        "en_US": "Germany",
                        "ja_JP": "ドイツ",
                        "zh_Hans": "德国"
                      },
                      "value": "DE"
                    },
                    {
                      "label": {
                        "en_US": "United Kingdom",
                        "ja_JP": "イギリス",
                        "zh_Hans": "英国"
                      },
                      "value": "GB"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "US:en",
                  "form": "form",
                  "human_description": {
                    "en_US": "The country edition for Google News, usually in format 'COUNTRY:LANGUAGE', e.g. 'US:en', 'CN:zh'",
                    "ja_JP": "Googleニュースの国別エディション、通常'国:言語'の形式、例：'US:en'、'JP:ja'",
                    "zh_Hans": "Google新闻的国家版本，通常格式为'国家:语言'，例如'US:en'、'CN:zh'"
                  },
                  "label": {
                    "en_US": "Country Edition",
                    "ja_JP": "国別エディション",
                    "zh_Hans": "国家版本"
                  },
                  "llm_description": "The country edition for Google News (ceid parameter)",
                  "max": null,
                  "min": null,
                  "name": "country_edition",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 10,
                  "form": "form",
                  "human_description": {
                    "en_US": "Maximum number of items to return",
                    "ja_JP": "返回する最大アイテム数",
                    "zh_Hans": "返回的最大条目数"
                  },
                  "label": {
                    "en_US": "Item Limit",
                    "ja_JP": "アイテム数制限",
                    "zh_Hans": "条目数量限制"
                  },
                  "llm_description": "Maximum number of items to return in the RSS feed",
                  "max": null,
                  "min": null,
                  "name": "limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-12T12:34:21Z",
        "version_updated_at": "2025-03-12T12:34:21Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Tools for writing content to minio and reading from minio",
          "ja_JP": "Tools for writing content to minio and reading from minio",
          "pt_BR": "Tools for writing content to minio and reading from minio",
          "zh_Hans": "Tools for writing content to minio and reading from minio"
        },
        "category": "tool",
        "created_at": "2025-03-21T07:54:28Z",
        "endpoint": {},
        "icon": "aias00/packages/minio/_assets/minio.svg",
        "index_id": "aias00___minio",
        "install_count": 591,
        "introduction": "# Minio Plugin\n\n**Author:** [aias00](https://github.com/aias00)\n**Version:** 0.0.2\n**Type:** tool\n\n## Description\n\n### MinioWriter Plugin\n\nThe MinioWriter Plugin allows users to write data into Minio.\n![](./_assets/minio_writer.png)\n\n### Features\n\n- Write data into minio and returns standard output and standard error\n\n### Parameters\n\n| Parameter | Type | Required | Description |\n|-----------|------|----------|-------------|\n| access_key | string | Yes | access_key of the remote server |\n| secret_key | string | Yes | secret_key of the remote server |\n| endpoint | string | Yes | endpoint of the remote server |\n| bucket_name | string | Yes | bucket name in minio |\n| content | string | Yes | Content to write into minio |\n| object_name | string | Yes | object name to write into minio |\n\n\n### MinioReader Plugin\n\nThe MinioReader Plugin allows users to read data from Minio.\n![](./_assets/minio_reader.png)\n\n### Features\n\n- Read data from minio and returns standard output and standard error\n\n### Parameters\n\n| Parameter | Type | Required | Description |\n|-----------|------|----------|-------------|\n| access_key | string | Yes | access_key of the remote server |\n| secret_key | string | Yes | secret_key of the remote server |\n| endpoint | string | Yes | endpoint of the remote server |\n| bucket_name | string | Yes | bucket name in minio |\n| object_name | string | Yes | object name to read from minio |\n\n## Security Considerations\n\n- Ensure you have permission to access the target server\n- Sensitive information such as private keys and passwords should be kept secure\n- Follow the principle of least privilege, granting only necessary execution permissions\n\n## License\n\n[MIT](./LICENSE)\n\n\n\n",
        "label": {
          "en_US": "minio",
          "ja_JP": "minio",
          "pt_BR": "minio",
          "zh_Hans": "minio"
        },
        "latest_package_identifier": "aias00/minio:0.0.3@61cf1c04017eb311f5e18ebd26bb4e212b5af20465a79c8f89a40a32b085c49c",
        "latest_version": "0.0.3",
        "model": {},
        "name": "minio",
        "org": "aias00",
        "plugin_id": "aias00/minio",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/minio.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "aias00",
            "description": {
              "en_US": "Tools for writing content to minio and reading from minio",
              "pt_BR": "Tools for writing content to minio and reading from minio",
              "zh_Hans": "Tools for writing content to minio and reading from minio"
            },
            "icon": "minio.svg",
            "label": {
              "en_US": "minio",
              "pt_BR": "minio",
              "zh_Hans": "minio"
            },
            "name": "minio",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool to read content from a MinIO bucket.",
                  "pt_BR": "A tool to read content from a MinIO bucket.",
                  "zh_Hans": "从MinIO存储桶读取内容的工具。"
                },
                "llm": "A tool to read content from a MinIO bucket."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "aias00",
                "label": {
                  "en_US": "minio_reader",
                  "pt_BR": "minio_reader",
                  "zh_Hans": "MinIO读取工具"
                },
                "name": "minio_reader"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The access key for MinIO authentication.",
                    "zh_Hans": "用于MinIO身份验证的访问密钥。"
                  },
                  "label": {
                    "en_US": "MinIO Access Key",
                    "zh_Hans": "MinIO访问密钥"
                  },
                  "llm_description": "A tool to read content from a MinIO bucket.",
                  "max": null,
                  "min": null,
                  "name": "access_key",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The secret key for MinIO authentication.",
                    "zh_Hans": "用于MinIO身份验证的秘密密钥。"
                  },
                  "label": {
                    "en_US": "MinIO Secret Key",
                    "zh_Hans": "MinIO秘密密钥"
                  },
                  "llm_description": "A tool to read content from a MinIO bucket.",
                  "max": null,
                  "min": null,
                  "name": "secret_key",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The endpoint URL of the MinIO server (e.g., http://localhost:9000).",
                    "zh_Hans": "MinIO服务器的端点URL（例如 http://localhost:9000）。"
                  },
                  "label": {
                    "en_US": "MinIO Endpoint URL",
                    "zh_Hans": "MinIO端点URL"
                  },
                  "llm_description": "A tool to read content from a MinIO bucket.",
                  "max": null,
                  "min": null,
                  "name": "endpoint",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The name of the MinIO bucket to write to.",
                    "zh_Hans": "要写入的MinIO存储桶名称。"
                  },
                  "label": {
                    "en_US": "Bucket Name",
                    "zh_Hans": "存储桶名称"
                  },
                  "llm_description": "A tool to read content from a MinIO bucket.",
                  "max": null,
                  "min": null,
                  "name": "bucket_name",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The name of the object/file in the MinIO bucket.",
                    "zh_Hans": "MinIO存储桶中的对象/文件名。"
                  },
                  "label": {
                    "en_US": "Object Name",
                    "zh_Hans": "对象名称"
                  },
                  "llm_description": "A tool to read content from a MinIO bucket.",
                  "max": null,
                  "min": null,
                  "name": "object_name",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool to write generated content to a MinIO bucket.",
                  "pt_BR": "A tool to write generated content to a MinIO bucket.",
                  "zh_Hans": "将内容写入MinIO存储桶的工具。"
                },
                "llm": "A tool to write generated content to a MinIO bucket."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "aias00",
                "label": {
                  "en_US": "minio_writer",
                  "pt_BR": "minio_writer",
                  "zh_Hans": "MinIO写入工具"
                },
                "name": "minio_writer"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The access key for MinIO authentication.",
                    "zh_Hans": "用于MinIO身份验证的访问密钥。"
                  },
                  "label": {
                    "en_US": "MinIO Access Key",
                    "zh_Hans": "MinIO访问密钥"
                  },
                  "llm_description": "A tool to write generated content to a MinIO bucket.",
                  "max": null,
                  "min": null,
                  "name": "access_key",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The secret key for MinIO authentication.",
                    "zh_Hans": "用于MinIO身份验证的秘密密钥。"
                  },
                  "label": {
                    "en_US": "MinIO Secret Key",
                    "zh_Hans": "MinIO秘密密钥"
                  },
                  "llm_description": "A tool to write generated content to a MinIO bucket.",
                  "max": null,
                  "min": null,
                  "name": "secret_key",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The endpoint URL of the MinIO server (e.g., http://localhost:9000).",
                    "zh_Hans": "MinIO服务器的端点URL（例如 http://localhost:9000）。"
                  },
                  "label": {
                    "en_US": "MinIO Endpoint URL",
                    "zh_Hans": "MinIO端点URL"
                  },
                  "llm_description": "A tool to write generated content to a MinIO bucket.",
                  "max": null,
                  "min": null,
                  "name": "endpoint",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The name of the MinIO bucket to write to.",
                    "zh_Hans": "要写入的MinIO存储桶名称。"
                  },
                  "label": {
                    "en_US": "Bucket Name",
                    "zh_Hans": "存储桶名称"
                  },
                  "llm_description": "A tool to write generated content to a MinIO bucket.",
                  "max": null,
                  "min": null,
                  "name": "bucket_name",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The content to be written to MinIO.",
                    "zh_Hans": "要写入MinIO的内容。"
                  },
                  "label": {
                    "en_US": "Content",
                    "zh_Hans": "内容"
                  },
                  "llm_description": "A tool to write generated content to a MinIO bucket.",
                  "max": null,
                  "min": null,
                  "name": "content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The name of the object/file in the MinIO bucket.",
                    "zh_Hans": "MinIO存储桶中的对象/文件名。"
                  },
                  "label": {
                    "en_US": "Object Name",
                    "zh_Hans": "对象名称"
                  },
                  "llm_description": "A tool to write generated content to a MinIO bucket.",
                  "max": null,
                  "min": null,
                  "name": "object_name",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-02T01:34:14Z",
        "version_updated_at": "2025-04-02T01:34:14Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Quickly generate a set of mock data (name, address, email, credit card number, etc.).",
          "pt_BR": "Gere rapidamente um conjunto de dados fictícios (nome, endereço, e-mail, número de cartão de crédito, etc.).",
          "zh_Hans": "快速生成一组模拟数据（姓名、地址、邮件、信用卡号等）。"
        },
        "category": "tool",
        "created_at": "2025-04-02T01:48:44Z",
        "endpoint": {},
        "icon": "tavan/packages/faker/_assets/icon.jpg",
        "index_id": "tavan___faker",
        "install_count": 574,
        "introduction": "## README: Faker (Dify Plugin)\n\n### 📌 Overview\n\n**Faker** is a Dify plugin that generates fake data using the [Faker](https://faker.readthedocs.io/en/master/) library. It supports multiple data formats, including **text, JSON, and CSV**, and allows users to specify data types and locales.\n\n---\n\n### 🚀 Features\n\n- 📜 **Generate fake data** for various types (e.g., names, addresses, phone numbers, emails, etc.).\n- 🌍 **Supports multiple locales** (default: `en_US`).\n- 🔄 **Output formats**: Text, JSON, and CSV.\n- 📦 **Easily configurable** via tool parameters.\n\n---\n\n### 🛠️ Usage\n\nThe plugin can be integrated with **Dify** and used with the following parameters:\n\n| Parameter  | Type   | Default | Description |\n|------------|--------|---------|-------------|\n| `locale`   | string | `en_US` | Locale for fake data generation (e.g., `zh_CN`, `fr_FR`). |\n| `type`     | string | `name`  | Type of data to generate (`name`, `address`, `phone_number`, `email`, `credit_card_number`). |\n| `count`    | int    | `1`     | Number of fake records to generate (max: `1000`). |\n\n![Tool Configuration](./_assets/faker_config.png)\n\n### 🔄 Supported Data Types\n\nThe following **data types** are currently supported:\n\n- **name** → Generates a random name.\n- **address** → Generates a random address.\n- **phone_number** → Generates a fake phone number.\n- **email** → Generates a fake email address.\n- **credit_card_number** → Generates a fake credit card number.\n\nFor an extensive list of available Faker methods, check the [official Faker documentation](https://faker.readthedocs.io/en/master/).\n\n---\n\n### 🔥 Future Enhancements\n\n- ✅ Add more Faker data types (e.g., company names, job titles, etc.).\n- ✅ Allow users to define custom Faker methods.\n- ✅ Improve error handling and user input validation.\n\n---\n\n### 📝 License\n\nThis project is licensed under the [MIT License](./LICENSE).\n\n---",
        "label": {
          "en_US": "faker",
          "ja_JP": "faker",
          "pt_BR": "faker",
          "zh_Hans": "faker"
        },
        "latest_package_identifier": "tavan/faker:0.0.1@0117adf3d9db41aa0fb0614312ba8c61c463d716036e1641df8fbb9c7c3735a6",
        "latest_version": "0.0.1",
        "model": {},
        "name": "faker",
        "org": "tavan",
        "plugin_id": "tavan/faker",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/faker.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "endpoint": {
              "enabled": true
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "tavan",
            "description": {
              "en_US": "Quickly generate a set of mock data (name, address, email, credit card number, etc.).",
              "pt_BR": "Gere rapidamente um conjunto de dados fictícios (nome, endereço, e-mail, número de cartão de crédito, etc.).",
              "zh_Hans": "快速生成一组模拟数据（姓名、地址、邮件、信用卡号等）。"
            },
            "icon": "icon.jpg",
            "label": {
              "en_US": "faker",
              "pt_BR": "faker",
              "zh_Hans": "faker"
            },
            "name": "faker",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Quickly generate a set of mock data (name, address, email, credit card number, etc.).",
                  "pt_BR": "Gere rapidamente um conjunto de dados fictícios (nome, endereço, e-mail, número de cartão de crédito, etc.).",
                  "zh_Hans": "快速生成一组模拟数据（姓名、地址、邮件、信用卡号等）。"
                },
                "llm": "Quickly generate a set of mock data (name, address, email, credit card number, etc.)."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "tavan",
                "label": {
                  "en_US": "faker",
                  "pt_BR": "faker",
                  "zh_Hans": "faker"
                },
                "name": "faker"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The type of random data to generate.",
                    "pt_BR": "O tipo de dados aleatórios a serem gerados.",
                    "zh_Hans": "生成随机数据的类型。"
                  },
                  "label": {
                    "en_US": "Type",
                    "pt_BR": "Tipo",
                    "zh_Hans": "类型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "type",
                  "options": [
                    {
                      "label": {
                        "en_US": "Name",
                        "pt_BR": "Nome",
                        "zh_Hans": "姓名"
                      },
                      "value": "name"
                    },
                    {
                      "label": {
                        "en_US": "Address",
                        "pt_BR": "Endereço",
                        "zh_Hans": "地址"
                      },
                      "value": "address"
                    },
                    {
                      "label": {
                        "en_US": "Email",
                        "pt_BR": "Email",
                        "zh_Hans": "邮件"
                      },
                      "value": "email"
                    },
                    {
                      "label": {
                        "en_US": "Credit Card Number",
                        "pt_BR": "Número do Cartão de Crédito",
                        "zh_Hans": "信用卡号"
                      },
                      "value": "credit_card_number"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The number of random data to generate.",
                    "pt_BR": "O número de dados aleatórios a serem gerados.",
                    "zh_Hans": "生成随机数据的数量。"
                  },
                  "label": {
                    "en_US": "Count",
                    "pt_BR": "Contagem",
                    "zh_Hans": "生成数量"
                  },
                  "llm_description": "The number of random data to generate.",
                  "max": null,
                  "min": null,
                  "name": "count",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The language of the generated data.",
                    "pt_BR": "O idioma dos dados gerados.",
                    "zh_Hans": "生成随机数据的语言。"
                  },
                  "label": {
                    "en_US": "Language",
                    "pt_BR": "Idioma",
                    "zh_Hans": "语言"
                  },
                  "llm_description": "The language of the generated data.",
                  "max": null,
                  "min": null,
                  "name": "locale",
                  "options": [
                    {
                      "label": {
                        "en_US": "English",
                        "pt_BR": "Inglês",
                        "zh_Hans": "英语"
                      },
                      "value": "en_US"
                    },
                    {
                      "label": {
                        "en_US": "Chinese",
                        "pt_BR": "Chinês",
                        "zh_Hans": "中文"
                      },
                      "value": "zh_CN"
                    },
                    {
                      "label": {
                        "en_US": "Japanese",
                        "pt_BR": "Japonês",
                        "zh_Hans": "日语"
                      },
                      "value": "ja_JP"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-02T01:48:52Z",
        "version_updated_at": "2025-04-02T01:48:52Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Search designed for AI Business-grade search and crawling for any web data",
          "ja_JP": "Search designed for AI Business-grade search and crawling for any web data",
          "pt_BR": "Search designed for AI Business-grade search and crawling for any web data",
          "zh_Hans": "Search designed for AI Business-grade search and crawling for any web data"
        },
        "category": "tool",
        "created_at": "2025-03-21T09:13:13Z",
        "endpoint": {},
        "icon": "yevanchen/packages/exa/_assets/exa.jpg",
        "index_id": "yevanchen___exa",
        "install_count": 568,
        "introduction": "## exa\n\n**Author:** yevanchen\n**Version:** 0.0.1\n**Type:** tool\n\n\n### Contact\n![Exa Logo](./_assets/image%20copy.png)\n\n\n### Description\n\nExa is an AI-powered search tool that enables semantic search, content retrieval, similarity search, and answers generation using Exa's advanced API.\n\n![Exa Logo](./_assets/image.png)\n\n## Tools\n\n### 1. Exa Search (`exa_search`)\n\nThe search endpoint lets you intelligently search the web and extract contents from the results.\n\nBy default, it automatically chooses between traditional keyword search and Exa's embeddings-based model to find the most relevant results for your query.\n\n#### Parameters:\n\n- **query** (string, required): The search query to find relevant information on the web.\n- **search_type** (select, optional, default: \"neural\"): \n  - Options: \"neural\" (semantic), \"keyword\" (traditional), \"auto\"\n  - Neural uses advanced AI for semantic understanding, keyword uses traditional search techniques\n- **num_results** (number, optional, default: 10): Maximum number of search results (1-100)\n- **include_domains** (string, optional): Comma-separated list of domains to include in results\n- **exclude_domains** (string, optional): Comma-separated list of domains to exclude from results\n- **start_published_date** (string, optional): Only include results published after this date (YYYY-MM-DD)\n- **end_published_date** (string, optional): Only include results published before this date (YYYY-MM-DD)\n- **use_autoprompt** (boolean, optional, default: true): Whether to use Exa's prompt engineering to improve the query\n- **text_contents** (boolean, optional, default: false): Whether to include text contents from each result\n- **highlight_results** (boolean, optional, default: false): Whether to highlight relevant snippets\n- **category** (select, optional): Focus on specific data categories\n  - Options: \"company\", \"research paper\", \"news\", \"pdf\", \"github\", \"tweet\", \"personal site\", \"linkedin profile\", \"financial report\"\n- **includeText** (string, optional): Text that must be present in results (up to 5 words)\n- **excludeText** (string, optional): Text that must not be present in results (up to 5 words)\n\n### 2. Exa Answer (`exa_answer`)\n\nGet an LLM answer to a question informed by Exa search results. Fully compatible with OpenAI's chat completions endpoint.\n\n/answer performs an Exa search and uses an LLM (GPT-4o-mini) to generate either:\n- A direct answer for specific queries (i.e., \"What is the capital of France?\" would return \"Paris\")\n- A detailed summary with citations for open-ended queries (i.e., \"What is the state of AI in healthcare?\" would return a summary with citations to relevant sources)\n\n#### Parameters:\n\n- **query** (string, required): The question to be answered with supporting evidence from the web\n- **text** (boolean, optional, default: false): Include the full text content of each source in the results\n- **model** (select, optional, default: \"exa\"):\n  - Options: \"exa\", \"exa-pro\"\n  - Specify which model should process the query and generate the answer\n\n### 3. Exa Similar Links (`exa_similar`)\n\nFind similar links to the link provided and optionally return the contents of the pages.\n\n#### Parameters:\n\n- **url** (string, required): The source URL to find similar content for\n- **num_results** (number, optional, default: 10): Number of similar links to return (max 100)\n- **text** (boolean, optional, default: false): Include the full text content of each similar page\n\n### 4. Exa URL Contents (`exa_contents`)\n\nGet the full page contents, summaries, and metadata for a list of URLs.\n\nReturns instant results from Exa's cache, with automatic live crawling as fallback for uncached pages.\n\n#### Parameters:\n\n- **urls** (string, required): Comma-separated list of URLs to extract content from\n- **livecrawl** (select, optional, default: \"never\"):\n  - Options: \"never\", \"fallback\", \"always\", \"auto\"\n  - Choose the live crawling strategy for content retrieval\n- **full_page_text** (boolean, optional, default: false): Include the full text of each webpage, including subpages\n- **ai_page_summary** (boolean, optional, default: false): Generate a summary for each webpage using LLM\n- **number_of_subpages** (number, optional, default: 1): Number of subpages to include in content extraction\n- **return_links** (number, optional, default: 1): Number of links to return from each webpage\n\n## Acknowledgements\n\n\n\nSpecial thanks to [@ExaAILabs](https://x.com/ExaAILabs) for providing the powerful API that powers this plugin.\n\n\n\n",
        "label": {
          "en_US": "exa",
          "ja_JP": "exa",
          "pt_BR": "exa",
          "zh_Hans": "exa"
        },
        "latest_package_identifier": "yevanchen/exa:0.0.4@3b06260e9b7d9b864203d2302d07f19a4fa7459b9939d4fc1f30001ee1921b91",
        "latest_version": "0.0.4",
        "model": {},
        "name": "exa",
        "org": "yevanchen",
        "plugin_id": "yevanchen/exa",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/exa.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {}
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "search"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Please visit the Exa AI Dashboard to register an account and apply for an API key",
                "pt_BR": "Please visit the Exa AI Dashboard to register an account and apply for an API key",
                "zh_Hans": "请访问 Exa AI 仪表板注册账号并获取 API Key"
              },
              "label": {
                "en_US": "Exa API key",
                "pt_BR": "Exa API key",
                "zh_Hans": "Exa API Key"
              },
              "name": "exa_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Exa API key",
                "pt_BR": "Please input your Exa API key",
                "zh_Hans": "请输入你的 Exa API Key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://dashboard.exa.ai/playground"
            }
          ],
          "identity": {
            "author": "yevanchen",
            "description": {
              "en_US": "Search designed for AI Business-grade search and crawling for any web data",
              "pt_BR": "Search designed for AI Business-grade search and crawling for any web data",
              "zh_Hans": "Search designed for AI Business-grade search and crawling for any web data"
            },
            "icon": "exa.jpg",
            "label": {
              "en_US": "exa",
              "pt_BR": "exa",
              "zh_Hans": "exa"
            },
            "name": "exa",
            "tags": [
              "search",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Perform semantic search on the web using Exa's AI-powered search engine to find relevant web content and documents.",
                  "ja_JP": "Exaの AI 搜索エンジンを使用してウェブ上で意味検索を実行し、関連コンテンツやドキュメントを検索します。",
                  "pt_BR": "Realize pesquisas semânticas na web usando o mecanismo de busca com IA da Exa para encontrar conteúdo e documentos relevantes.",
                  "zh_Hans": "使用 Exa 的人工智能搜索引擎在网络上执行语义搜索，查找相关网页内容和文档。"
                },
                "llm": "A tool for performing semantic search on the web using Exa's AI-powered search engine to find relevant content, websites, and documents."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "yevanchen",
                "label": {
                  "en_US": "Exa Search",
                  "ja_JP": "Exa 検索",
                  "pt_BR": "Pesquisa Exa",
                  "zh_Hans": "Exa 搜索"
                },
                "name": "exa_search"
              },
              "output_schema": {
                "description": "The JSON response containing the search results, simplified to include only URLs and image URLs.",
                "properties": {
                  "images": {
                    "description": "An array of image URLs from the search results",
                    "items": {
                      "type": "string"
                    },
                    "type": "array"
                  },
                  "urls": {
                    "description": "An array of URLs from the search results",
                    "items": {
                      "type": "string"
                    },
                    "type": "array"
                  }
                },
                "type": "object"
              },
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The search query you want to perform using Exa's search engine.",
                    "ja_JP": "Exa の検索エンジンを使用して実行したい検索クエリ。",
                    "pt_BR": "A consulta de pesquisa que você deseja realizar usando o mecanismo de busca da Exa.",
                    "zh_Hans": "您想使用 Exa 搜索引擎执行的搜索查询。"
                  },
                  "label": {
                    "en_US": "Search query",
                    "ja_JP": "検索クエリ",
                    "pt_BR": "Consulta de pesquisa",
                    "zh_Hans": "搜索查询"
                  },
                  "llm_description": "The search query to find relevant information on the web.",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "neural",
                  "form": "form",
                  "human_description": {
                    "en_US": "The type of search to perform - neural (semantic), keyword (traditional), or auto.",
                    "ja_JP": "実行する検索のタイプ - ニューラル（意味的），キーワード（従来型），または自動。",
                    "pt_BR": "O tipo de pesquisa a ser realizada - neural (semântica), por palavra-chave (tradicional), ou auto.",
                    "zh_Hans": "要执行的搜索类型 - 神经（语义），关键词（传统），或自动。"
                  },
                  "label": {
                    "en_US": "Search Type",
                    "ja_JP": "検索タイプ",
                    "pt_BR": "Tipo de pesquisa",
                    "zh_Hans": "搜索类型"
                  },
                  "llm_description": "The type of search to perform - neural uses advanced AI for semantic understanding, keyword uses traditional search techniques, and auto dynamically selects the best approach.",
                  "max": null,
                  "min": null,
                  "name": "search_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "Neural",
                        "ja_JP": "ニューラル",
                        "pt_BR": "Neural",
                        "zh_Hans": "神经"
                      },
                      "value": "neural"
                    },
                    {
                      "label": {
                        "en_US": "Keyword",
                        "ja_JP": "キーワード",
                        "pt_BR": "Palavra-chave",
                        "zh_Hans": "关键词"
                      },
                      "value": "keyword"
                    },
                    {
                      "label": {
                        "en_US": "Auto",
                        "ja_JP": "自動",
                        "pt_BR": "Auto",
                        "zh_Hans": "自动"
                      },
                      "value": "auto"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 10,
                  "form": "form",
                  "human_description": {
                    "en_US": "The maximum number of search results to return (from 1 to 100).",
                    "ja_JP": "返す検索結果の最大数（1〜100）。",
                    "pt_BR": "O número máximo de resultados de pesquisa a serem retornados (de 1 a 100).",
                    "zh_Hans": "要返回的最大搜索结果数（从1到100）。"
                  },
                  "label": {
                    "en_US": "Number of Results",
                    "ja_JP": "結果数",
                    "pt_BR": "Número de resultados",
                    "zh_Hans": "结果数量"
                  },
                  "llm_description": "The maximum number of search results to return, ranging from 1 to 100.",
                  "max": 100,
                  "min": 1,
                  "name": "num_results",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "A comma-separated list of domains to specifically include in the search results.",
                    "ja_JP": "検索結果に特に含めるドメインのカンマ区切りリスト。",
                    "pt_BR": "Uma lista separada por vírgulas de domínios para incluir especificamente nos resultados da pesquisa.",
                    "zh_Hans": "要在搜索结果中特别包含的域名的逗号分隔列表。"
                  },
                  "label": {
                    "en_US": "Include Domains",
                    "ja_JP": "含めるドメイン",
                    "pt_BR": "Incluir domínios",
                    "zh_Hans": "包含域名"
                  },
                  "llm_description": "A comma-separated list of domains to specifically include in the search results.",
                  "max": null,
                  "min": null,
                  "name": "include_domains",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "A comma-separated list of domains to specifically exclude from the search results.",
                    "ja_JP": "検索結果から特に除外するドメインのカンマ区切りリスト。",
                    "pt_BR": "Uma lista separada por vírgulas de domínios para excluir especificamente dos resultados da pesquisa.",
                    "zh_Hans": "要从搜索结果中特别排除的域名的逗号分隔列表。"
                  },
                  "label": {
                    "en_US": "Exclude Domains",
                    "ja_JP": "除外するドメイン",
                    "pt_BR": "Excluir domínios",
                    "zh_Hans": "排除域名"
                  },
                  "llm_description": "A comma-separated list of domains to specifically exclude from the search results.",
                  "max": null,
                  "min": null,
                  "name": "exclude_domains",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Only include results published after this date (YYYY-MM-DD format).",
                    "ja_JP": "この日付以降に公開された結果のみを含める（YYYY-MM-DD形式）。",
                    "pt_BR": "Incluir apenas resultados publicados após esta data (formato AAAA-MM-DD).",
                    "zh_Hans": "仅包含在此日期之后发布的结果（YYYY-MM-DD 格式）。"
                  },
                  "label": {
                    "en_US": "Start Published Date",
                    "ja_JP": "公開開始日",
                    "pt_BR": "Data de publicação inicial",
                    "zh_Hans": "开始发布日期"
                  },
                  "llm_description": "Only include results published after this date in YYYY-MM-DD format.",
                  "max": null,
                  "min": null,
                  "name": "start_published_date",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Only include results published before this date (YYYY-MM-DD format).",
                    "ja_JP": "この日付以前に公開された結果のみを含める（YYYY-MM-DD形式）。",
                    "pt_BR": "Incluir apenas resultados publicados antes desta data (formato AAAA-MM-DD).",
                    "zh_Hans": "仅包含在此日期之前发布的结果（YYYY-MM-DD 格式）。"
                  },
                  "label": {
                    "en_US": "End Published Date",
                    "ja_JP": "公開終了日",
                    "pt_BR": "Data de publicação final",
                    "zh_Hans": "结束发布日期"
                  },
                  "llm_description": "Only include results published before this date in YYYY-MM-DD format.",
                  "max": null,
                  "min": null,
                  "name": "end_published_date",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to use Exa's prompt engineering to improve the query.",
                    "ja_JP": "Exaのプロンプトエンジニングを使用してクエリを改善するかどうか。",
                    "pt_BR": "Se deve usar a engenharia de prompt da Exa para melhorar a consulta.",
                    "zh_Hans": "是否使用 Exa 的提示工程来改进查询。"
                  },
                  "label": {
                    "en_US": "Use Autoprompt",
                    "ja_JP": "自動プロンプトを使用",
                    "pt_BR": "Usar Autoprompt",
                    "zh_Hans": "使用自动提示"
                  },
                  "llm_description": "Whether to use Exa's prompt engineering to improve the query. When true, Exa will automatically rewrite the query to improve search results.",
                  "max": null,
                  "min": null,
                  "name": "use_autoprompt",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to include the text contents from each search result.",
                    "ja_JP": "各検索結果からテキスト内容を含めるかどうか。",
                    "pt_BR": "Se deve incluir o conteúdo de texto de cada resultado da pesquisa.",
                    "zh_Hans": "是否包含每个搜索结果的文本内容。"
                  },
                  "label": {
                    "en_US": "Include Text Contents",
                    "ja_JP": "テキスト内容を含める",
                    "pt_BR": "Incluir conteúdo de texto",
                    "zh_Hans": "包含文本内容"
                  },
                  "llm_description": "Whether to include the text contents from each search result. When true, the response will include the text content of each webpage.",
                  "max": null,
                  "min": null,
                  "name": "text_contents",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to highlight relevant text snippets in the search results.",
                    "ja_JP": "検索結果内の関連テキスト部分をハイライトするかどうか。",
                    "pt_BR": "Se deve destacar trechos de texto relevantes nos resultados da pesquisa.",
                    "zh_Hans": "是否在搜索结果中高亮显示相关文本片段。"
                  },
                  "label": {
                    "en_US": "Highlight Results",
                    "ja_JP": "結果をハイライト",
                    "pt_BR": "Destacar resultados",
                    "zh_Hans": "高亮结果"
                  },
                  "llm_description": "Whether to highlight relevant text snippets in the search results. When true, relevant sections of text will be highlighted.",
                  "max": null,
                  "min": null,
                  "name": "highlight_results",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "A data category to focus on.",
                    "ja_JP": "集中するデータのカテゴリ。",
                    "pt_BR": "Uma categoria de dados para se concentrar.",
                    "zh_Hans": "要集中的数据类别。"
                  },
                  "label": {
                    "en_US": "Category",
                    "ja_JP": "カテゴリ",
                    "pt_BR": "Categoria",
                    "zh_Hans": "类别"
                  },
                  "llm_description": "A data category to focus on.",
                  "max": null,
                  "min": null,
                  "name": "category",
                  "options": [
                    {
                      "label": {
                        "en_US": "Company",
                        "ja_JP": "会社",
                        "pt_BR": "Empresa",
                        "zh_Hans": "公司"
                      },
                      "value": "company"
                    },
                    {
                      "label": {
                        "en_US": "Research Paper",
                        "ja_JP": "研究論文",
                        "pt_BR": "Artigo de Pesquisa",
                        "zh_Hans": "研究论文"
                      },
                      "value": "research paper"
                    },
                    {
                      "label": {
                        "en_US": "News",
                        "ja_JP": "ニュース",
                        "pt_BR": "Notícias",
                        "zh_Hans": "新闻"
                      },
                      "value": "news"
                    },
                    {
                      "label": {
                        "en_US": "PDF",
                        "ja_JP": "PDF",
                        "pt_BR": "PDF",
                        "zh_Hans": "PDF"
                      },
                      "value": "pdf"
                    },
                    {
                      "label": {
                        "en_US": "GitHub",
                        "ja_JP": "GitHub",
                        "pt_BR": "GitHub",
                        "zh_Hans": "GitHub"
                      },
                      "value": "github"
                    },
                    {
                      "label": {
                        "en_US": "Tweet",
                        "ja_JP": "ツイート",
                        "pt_BR": "Tuite",
                        "zh_Hans": "推文"
                      },
                      "value": "tweet"
                    },
                    {
                      "label": {
                        "en_US": "Personal Site",
                        "ja_JP": "個人サイト",
                        "pt_BR": "Site Pessoal",
                        "zh_Hans": "个人网站"
                      },
                      "value": "personal site"
                    },
                    {
                      "label": {
                        "en_US": "LinkedIn Profile",
                        "ja_JP": "LinkedInプロファイル",
                        "pt_BR": "Perfil do LinkedIn",
                        "zh_Hans": "LinkedIn 个人主页"
                      },
                      "value": "linkedin profile"
                    },
                    {
                      "label": {
                        "en_US": "Financial Report",
                        "ja_JP": "財務報告",
                        "pt_BR": "Relatório Financeiro",
                        "zh_Hans": "财务报告"
                      },
                      "value": "financial report"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "List of strings that must be present in webpage text of results. Currently, only 1 string is supported, of up to 5 words.",
                    "ja_JP": "結果のウェブページテキストに存在する必要がある文字列のリスト。現在、最大5単語の1つの文字列のみがサポートされています。",
                    "pt_BR": "Lista de strings que devem estar presentes no texto da página dos resultados. Atualmente, apenas 1 string é suportada, de até 5 palavras.",
                    "zh_Hans": "必须出现在结果的网页文本中的字符串列表。目前，只支持1个字符串，最多5个单词。"
                  },
                  "label": {
                    "en_US": "Include Text",
                    "ja_JP": "テキストを含める",
                    "pt_BR": "Incluir Texto",
                    "zh_Hans": "包含文本"
                  },
                  "llm_description": "List of strings that must be present in webpage text of results. Currently, only 1 string is supported, of up to 5 words.",
                  "max": null,
                  "min": null,
                  "name": "includeText",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "List of strings that must not be present in webpage text of results. Currently, only 1 string is supported, of up to 5 words.",
                    "ja_JP": "結果のウェブページテキストに存在してはならない文字列のリスト。現在、最大5単語の1つの文字列のみがサポートされています。",
                    "pt_BR": "Lista de strings que não devem estar presentes no texto da página dos resultados. Atualmente, apenas 1 string é suportada, de até 5 palavras.",
                    "zh_Hans": "不能出现在结果的网页文本中的字符串列表。目前，只支持1个字符串，最多5个单词。"
                  },
                  "label": {
                    "en_US": "Exclude Text",
                    "ja_JP": "テキストを除外",
                    "pt_BR": "Excluir Texto",
                    "zh_Hans": "排除文本"
                  },
                  "llm_description": "List of strings that must not be present in webpage text of results. Currently, only 1 string is supported, of up to 5 words.",
                  "max": null,
                  "min": null,
                  "name": "excludeText",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Retrieve the text content from specific URLs using Exa's web content extraction capabilities.",
                  "ja_JP": "Exaのウェブコンテンツ抽出機能を使用して、特定のURLからテキストコンテンツを取得します。",
                  "pt_BR": "Recupere o conteúdo de texto de URLs específicas usando as capacidades de extração de conteúdo web da Exa.",
                  "zh_Hans": "使用 Exa 的网页内容提取功能获取特定 URL 的文本内容。"
                },
                "llm": "A tool for retrieving the full text content from specific web pages or documents using Exa's content extraction API."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "yevanchen",
                "label": {
                  "en_US": "Exa URL Contents",
                  "ja_JP": "Exa URL コンテンツ",
                  "pt_BR": "Conteúdo Exa URL",
                  "zh_Hans": "Exa URL 内容获取"
                },
                "name": "exa_contents"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Comma-separated list of URLs to fetch content from.",
                    "ja_JP": "コンテンツを取得するためのカンマ区切りのURLリスト。",
                    "pt_BR": "Lista de URLs separadas por vírgulas para buscar conteúdo.",
                    "zh_Hans": "用逗号分隔的URL列表，用于获取内容。"
                  },
                  "label": {
                    "en_US": "URLs",
                    "ja_JP": "URL",
                    "pt_BR": "URLs",
                    "zh_Hans": "URL列表"
                  },
                  "llm_description": "A list of URLs to extract content from, separated by commas.",
                  "max": null,
                  "min": null,
                  "name": "urls",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "never",
                  "form": "form",
                  "human_description": {
                    "en_US": "Specify the live crawling behavior.",
                    "ja_JP": "実時間のクロールの動作を指定します。",
                    "pt_BR": "Especifique o comportamento de crawl em tempo real.",
                    "zh_Hans": "指定实时爬取行为。"
                  },
                  "label": {
                    "en_US": "Live Crawling",
                    "ja_JP": "リアルタイムクロール",
                    "pt_BR": "Crawl em Tempo Real",
                    "zh_Hans": "实时爬取"
                  },
                  "llm_description": "Choose the live crawling strategy for content retrieval.",
                  "max": null,
                  "min": null,
                  "name": "livecrawl",
                  "options": [
                    {
                      "label": {
                        "en_US": "Never",
                        "ja_JP": "なし",
                        "pt_BR": "Nunca",
                        "zh_Hans": "从不"
                      },
                      "value": "never"
                    },
                    {
                      "label": {
                        "en_US": "Fallback",
                        "ja_JP": "フォールバック",
                        "pt_BR": "Redundância",
                        "zh_Hans": "回退"
                      },
                      "value": "fallback"
                    },
                    {
                      "label": {
                        "en_US": "Always",
                        "ja_JP": "いつも",
                        "pt_BR": "Sempre",
                        "zh_Hans": "总是"
                      },
                      "value": "always"
                    },
                    {
                      "label": {
                        "en_US": "Auto",
                        "ja_JP": "自動",
                        "pt_BR": "Auto",
                        "zh_Hans": "自动"
                      },
                      "value": "auto"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Return full webpage text for every result, including for subpages.",
                    "ja_JP": "各結果の完全なウェブページテキストを返し、サブページも含む。",
                    "pt_BR": "Retorna o texto completo da página web para cada resultado, incluindo para subpáginas.",
                    "zh_Hans": "返回每个结果的完整网页文本，包括子页面。"
                  },
                  "label": {
                    "en_US": "Full Page Text",
                    "ja_JP": "完全ページテキスト",
                    "pt_BR": "Texto Completo da Página",
                    "zh_Hans": "完整页面文本"
                  },
                  "llm_description": "Include the full text of each webpage, including subpages.",
                  "max": null,
                  "min": null,
                  "name": "full_page_text",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Return an LLM-generated summary of each webpage.",
                    "ja_JP": "各ウェブページのLLM生成の要約を返します。",
                    "pt_BR": "Retorna um resumo gerado pelo LLM de cada página web.",
                    "zh_Hans": "返回每个网页的LLM生成的摘要。"
                  },
                  "label": {
                    "en_US": "AI Page Summary",
                    "ja_JP": "AIページ要約",
                    "pt_BR": "Resumo AI da Página",
                    "zh_Hans": "AI页面摘要"
                  },
                  "llm_description": "Generate a summary for each webpage using LLM.",
                  "max": null,
                  "min": null,
                  "name": "ai_page_summary",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": 1,
                  "form": "form",
                  "human_description": {
                    "en_US": "Number of subpages to include within each result.",
                    "ja_JP": "各結果中に含めるサブページの数。",
                    "pt_BR": "Número de subpáginas a incluir dentro de cada resultado.",
                    "zh_Hans": "每个结果中要包括的子页面数量。"
                  },
                  "label": {
                    "en_US": "Number of Subpages",
                    "ja_JP": "サブページ数",
                    "pt_BR": "Número de Subpáginas",
                    "zh_Hans": "子页面数量"
                  },
                  "llm_description": "Specify the number of subpages to include in the content extraction.",
                  "max": null,
                  "min": null,
                  "name": "number_of_subpages",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 1,
                  "form": "form",
                  "human_description": {
                    "en_US": "Number of links to return from each webpage.",
                    "ja_JP": "各ウェブページから返すリンクの数。",
                    "pt_BR": "Número de links a retornar de cada página web.",
                    "zh_Hans": "从每个网页返回的链接数量。"
                  },
                  "label": {
                    "en_US": "Return Links",
                    "ja_JP": "リンクを返す",
                    "pt_BR": "Retornar Links",
                    "zh_Hans": "返回链接"
                  },
                  "llm_description": "Include links found on each webpage.",
                  "max": null,
                  "min": null,
                  "name": "return_links",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Find similar links to a given URL using Exa's content similarity search.",
                  "ja_JP": "Exaのコンテンツ類似性検索を使用して、指定されたURLに類似したリンクを見つけます。",
                  "pt_BR": "Encontre links semelhantes a uma URL específica usando a pesquisa de similaridade de conteúdo da Exa.",
                  "zh_Hans": "使用 Exa 的内容相似度搜索功能查找与给定 URL 相似的链接。"
                },
                "llm": "A tool for finding web pages with similar content to a specified URL using Exa's content similarity search API."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "yevanchen",
                "label": {
                  "en_US": "Exa Similar Links",
                  "ja_JP": "Exa 類似リンク",
                  "pt_BR": "Links Similares Exa",
                  "zh_Hans": "Exa 相似链接"
                },
                "name": "exa_similar"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The URL for which you would like to find similar links.",
                    "ja_JP": "類似リンクを見つけたいURL。",
                    "pt_BR": "A URL para a qual você gostaria de encontrar links semelhantes.",
                    "zh_Hans": "您想要查找相似链接的URL。"
                  },
                  "label": {
                    "en_US": "URL",
                    "ja_JP": "URL",
                    "pt_BR": "URL",
                    "zh_Hans": "URL"
                  },
                  "llm_description": "The source URL to find similar content for.",
                  "max": null,
                  "min": null,
                  "name": "url",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 10,
                  "form": "form",
                  "human_description": {
                    "en_US": "Number of similar links to return (max 100).",
                    "ja_JP": "返す類似リンクの数（最大100）。",
                    "pt_BR": "Número de links semelhantes a retornar (máximo 100).",
                    "zh_Hans": "返回的相似链接数量（最多100个）。"
                  },
                  "label": {
                    "en_US": "Number of Results",
                    "ja_JP": "結果数",
                    "pt_BR": "Número de Resultados",
                    "zh_Hans": "结果数量"
                  },
                  "llm_description": "Specify how many similar pages to return (maximum 100).",
                  "max": null,
                  "min": null,
                  "name": "num_results",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to include full text of the results.",
                    "ja_JP": "結果の全文を含めるかどうか。",
                    "pt_BR": "Se deve incluir o texto completo dos resultados.",
                    "zh_Hans": "是否包含结果的完整文本。"
                  },
                  "label": {
                    "en_US": "Include Text",
                    "ja_JP": "テキストを含む",
                    "pt_BR": "Incluir Texto",
                    "zh_Hans": "包含文本"
                  },
                  "llm_description": "Include the full text content of each similar page in the results.",
                  "max": null,
                  "min": null,
                  "name": "text",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Generate answers to questions with cited sources using Exa AI.",
                  "ja_JP": "Exa AIを使用して、引用元付きの質問への回答を生成します。",
                  "pt_BR": "Gere respostas para perguntas com fontes citadas usando Exa AI.",
                  "zh_Hans": "使用 Exa AI 生成带有引用源的问题答案。"
                },
                "llm": "A tool for generating factual answers to user questions with cited sources using Exa's API and web information retrieval."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "yevanchen",
                "label": {
                  "en_US": "Exa Answer",
                  "ja_JP": "Exa 回答",
                  "pt_BR": "Resposta Exa",
                  "zh_Hans": "Exa 回答"
                },
                "name": "exa_answer"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The question you want answered with cited sources.",
                    "ja_JP": "引用元を含めて回答してほしい質問。",
                    "pt_BR": "A pergunta que você deseja respondida com fontes citadas.",
                    "zh_Hans": "您想要获得引用源的问题。"
                  },
                  "label": {
                    "en_US": "Query",
                    "ja_JP": "クエリ",
                    "pt_BR": "Consulta",
                    "zh_Hans": "查询"
                  },
                  "llm_description": "The question to be answered with supporting evidence from the web.",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to include full text of the source articles.",
                    "ja_JP": "ソース記事の全文を含めるかどうか。",
                    "pt_BR": "Se deve incluir o texto completo dos artigos de origem.",
                    "zh_Hans": "是否包含源文章的完整文本。"
                  },
                  "label": {
                    "en_US": "Include Source Text",
                    "ja_JP": "ソーステキストを含む",
                    "pt_BR": "Incluir Texto Fonte",
                    "zh_Hans": "包含源文本"
                  },
                  "llm_description": "Include the full text content of each source in the results.",
                  "max": null,
                  "min": null,
                  "name": "text",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": "exa",
                  "form": "form",
                  "human_description": {
                    "en_US": "The model to use for answering the question.",
                    "ja_JP": "質問に答えるために使用するモデル。",
                    "pt_BR": "O modelo a ser usado para responder à pergunta.",
                    "zh_Hans": "用于回答问题的模型。"
                  },
                  "label": {
                    "en_US": "Model",
                    "ja_JP": "モデル",
                    "pt_BR": "Modelo",
                    "zh_Hans": "模型"
                  },
                  "llm_description": "Specify which model should process the query and generate the answer.",
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": [
                    {
                      "label": {
                        "en_US": "Exa",
                        "ja_JP": "Exa",
                        "pt_BR": "Exa",
                        "zh_Hans": "Exa"
                      },
                      "value": "exa"
                    },
                    {
                      "label": {
                        "en_US": "Exa Pro",
                        "ja_JP": "Exa Pro",
                        "pt_BR": "Exa Pro",
                        "zh_Hans": "Exa Pro"
                      },
                      "value": "exa-pro"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-17T15:31:42Z",
        "version_updated_at": "2025-04-17T15:31:42Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Feishu Task, requires the following permissions: task:task:write、contact:user.id:readonly.\n",
          "zh_Hans": "飞书任务，需要开通以下权限: task:task:write、contact:user.id:readonly。\n"
        },
        "category": "tool",
        "created_at": "2025-02-26T10:44:24Z",
        "endpoint": {},
        "icon": "langgenius/packages/feishu_task/_assets/icon.png",
        "index_id": "langgenius___feishu_task",
        "install_count": 566,
        "introduction": "",
        "label": {
          "en_US": "Feishu Task",
          "zh_Hans": "飞书任务"
        },
        "latest_package_identifier": "langgenius/feishu_task:0.0.1@77a5361145bc0e37f3d8938934ac8f6358300288bf1f13cbce870f7157336f40",
        "latest_version": "0.0.1",
        "model": {},
        "name": "feishu_task",
        "org": "langgenius",
        "plugin_id": "langgenius/feishu_task",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/feishu_task.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "social"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "APP ID"
              },
              "name": "app_id",
              "options": null,
              "placeholder": {
                "en_US": "Please input your feishu app id",
                "zh_Hans": "请输入你的飞书 app id"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": "https://open.larkoffice.com/app"
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "APP Secret"
              },
              "name": "app_secret",
              "options": null,
              "placeholder": {
                "en_US": "Please input your app secret",
                "zh_Hans": "请输入你的飞书 app secret"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            }
          ],
          "identity": {
            "author": "Doug Lea",
            "description": {
              "en_US": "Feishu Task, requires the following permissions: task:task:write、contact:user.id:readonly.\n",
              "zh_Hans": "飞书任务，需要开通以下权限: task:task:write、contact:user.id:readonly。\n"
            },
            "icon": "icon.png",
            "label": {
              "en_US": "Feishu Task",
              "zh_Hans": "飞书任务"
            },
            "name": "feishu_task",
            "tags": [
              "social",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Delete Task",
                  "zh_Hans": "删除飞书任务"
                },
                "llm": "A tool for deleting tasks in Feishu.(删除飞书任务)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Delete Task",
                  "zh_Hans": "删除飞书任务"
                },
                "name": "delete_task"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The GUID of the task to be deleted, supports passing either the Task ID or the Task link URL. Example of Task ID: 8b5425ec-9f2a-43bd-a3ab-01912f50282b; Example of Task link URL: https://applink.feishu-pre.net/client/todo/detail?guid=8c6bf822-e4da-449a-b82a-dc44020f9be9&suite_entity_num=t21587362\n",
                    "zh_Hans": "要删除的任务的 GUID，支持传任务 ID 和任务链接 URL。任务 ID 示例：8b5425ec-9f2a-43bd-a3ab-01912f50282b；任务链接 URL 示例：https://applink.feishu-pre.net/client/todo/detail?guid=8c6bf822-e4da-449a-b82a-dc44020f9be9&suite_entity_num=t21587362"
                  },
                  "label": {
                    "en_US": "Task GUID",
                    "zh_Hans": "任务 GUID"
                  },
                  "llm_description": "要删除的任务的 GUID，支持传任务 ID 和任务链接 URL。任务 ID 示例：8b5425ec-9f2a-43bd-a3ab-01912f50282b；任务链接 URL 示例：https://applink.feishu-pre.net/client/todo/detail?guid=8c6bf822-e4da-449a-b82a-dc44020f9be9&suite_entity_num=t21587362",
                  "max": null,
                  "min": null,
                  "name": "task_guid",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Create Feishu Task",
                  "zh_Hans": "创建飞书任务"
                },
                "llm": "A tool for creating tasks in Feishu.(创建飞书任务)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Create Task",
                  "zh_Hans": "创建飞书任务"
                },
                "name": "create_task"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The title of the task.",
                    "zh_Hans": "任务标题"
                  },
                  "label": {
                    "en_US": "Task Title",
                    "zh_Hans": "任务标题"
                  },
                  "llm_description": "任务标题",
                  "max": null,
                  "min": null,
                  "name": "summary",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The description or notes for the task.",
                    "zh_Hans": "任务备注"
                  },
                  "label": {
                    "en_US": "Task Description",
                    "zh_Hans": "任务备注"
                  },
                  "llm_description": "任务备注",
                  "max": null,
                  "min": null,
                  "name": "description",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The start time of the task, in the format: 2006-01-02 15:04:05\n",
                    "zh_Hans": "任务开始时间，格式为：2006-01-02 15:04:05"
                  },
                  "label": {
                    "en_US": "Start Time",
                    "zh_Hans": "任务开始时间"
                  },
                  "llm_description": "任务开始时间，格式为：2006-01-02 15:04:05",
                  "max": null,
                  "min": null,
                  "name": "start_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The end time of the task, in the format: 2006-01-02 15:04:05\n",
                    "zh_Hans": "任务结束时间，格式为：2006-01-02 15:04:05"
                  },
                  "label": {
                    "en_US": "End Time",
                    "zh_Hans": "任务结束时间"
                  },
                  "llm_description": "任务结束时间，格式为：2006-01-02 15:04:05",
                  "max": null,
                  "min": null,
                  "name": "end_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The completion time of the task, in the format: 2006-01-02 15:04:05. Leave empty to create an incomplete task; fill in a specific time to create a completed task.\n",
                    "zh_Hans": "任务完成时间，格式为：2006-01-02 15:04:05，不填写表示创建一个未完成任务；填写一个具体的时间表示创建一个已完成任务。"
                  },
                  "label": {
                    "en_US": "Completed Time",
                    "zh_Hans": "任务完成时间"
                  },
                  "llm_description": "任务完成时间，格式为：2006-01-02 15:04:05，不填写表示创建一个未完成任务；填写一个具体的时间表示创建一个已完成任务。",
                  "max": null,
                  "min": null,
                  "name": "completed_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Update Feishu Task",
                  "zh_Hans": "更新飞书任务"
                },
                "llm": "A tool for updating tasks in Feishu.(更新飞书任务)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Update Task",
                  "zh_Hans": "更新飞书任务"
                },
                "name": "update_task"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The task ID, supports inputting either the Task ID or the Task link URL. Example of Task ID: 42cad8a0-f8c8-4344-9be2-d1d7e8e91b64; Example of Task link URL: https://applink.feishu-pre.net/client/todo/detail?guid=42cad8a0-f8c8-4344-9be2-d1d7e8e91b64&suite_entity_num=t21700217\n",
                    "zh_Hans": "任务ID，支持传入任务 ID 和任务链接 URL。任务 ID 示例: 42cad8a0-f8c8-4344-9be2-d1d7e8e91b64；任务链接 URL 示例: https://applink.feishu-pre.net/client/todo/detail?guid=42cad8a0-f8c8-4344-9be2-d1d7e8e91b64&suite_entity_num=t21700217\n"
                  },
                  "label": {
                    "en_US": "Task GUID",
                    "zh_Hans": "任务 GUID"
                  },
                  "llm_description": "任务ID，支持传入任务 ID 和任务链接 URL。任务 ID 示例: 42cad8a0-f8c8-4344-9be2-d1d7e8e91b64；任务链接 URL 示例: https://applink.feishu-pre.net/client/todo/detail?guid=42cad8a0-f8c8-4344-9be2-d1d7e8e91b64&suite_entity_num=t21700217\n",
                  "max": null,
                  "min": null,
                  "name": "task_guid",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The title of the task.",
                    "zh_Hans": "任务标题"
                  },
                  "label": {
                    "en_US": "Task Title",
                    "zh_Hans": "任务标题"
                  },
                  "llm_description": "任务标题",
                  "max": null,
                  "min": null,
                  "name": "summary",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The description or notes for the task.",
                    "zh_Hans": "任务备注"
                  },
                  "label": {
                    "en_US": "Task Description",
                    "zh_Hans": "任务备注"
                  },
                  "llm_description": "任务备注",
                  "max": null,
                  "min": null,
                  "name": "description",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The start time of the task, in the format: 2006-01-02 15:04:05\n",
                    "zh_Hans": "任务开始时间，格式为：2006-01-02 15:04:05"
                  },
                  "label": {
                    "en_US": "Start Time",
                    "zh_Hans": "任务开始时间"
                  },
                  "llm_description": "任务开始时间，格式为：2006-01-02 15:04:05",
                  "max": null,
                  "min": null,
                  "name": "start_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The end time of the task, in the format: 2006-01-02 15:04:05\n",
                    "zh_Hans": "任务结束时间，格式为：2006-01-02 15:04:05"
                  },
                  "label": {
                    "en_US": "End Time",
                    "zh_Hans": "任务结束时间"
                  },
                  "llm_description": "任务结束时间，格式为：2006-01-02 15:04:05",
                  "max": null,
                  "min": null,
                  "name": "end_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The completion time of the task, in the format: 2006-01-02 15:04:05\n",
                    "zh_Hans": "任务完成时间，格式为：2006-01-02 15:04:05"
                  },
                  "label": {
                    "en_US": "Completed Time",
                    "zh_Hans": "任务完成时间"
                  },
                  "llm_description": "任务完成时间，格式为：2006-01-02 15:04:05",
                  "max": null,
                  "min": null,
                  "name": "completed_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Add Members",
                  "zh_Hans": "添加任务成员"
                },
                "llm": "A tool for adding members to a Feishu task.(添加任务成员)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Add Members",
                  "zh_Hans": "添加任务成员"
                },
                "name": "add_members"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The GUID of the task to be added, supports passing either the Task ID or the Task link URL. Example of Task ID: 8b5425ec-9f2a-43bd-a3ab-01912f50282b; Example of Task link URL: https://applink.feishu-pre.net/client/todo/detail?guid=8c6bf822-e4da-449a-b82a-dc44020f9be9&suite_entity_num=t21587362\n",
                    "zh_Hans": "要添加的任务的 GUID，支持传任务 ID 和任务链接 URL。任务 ID 示例：8b5425ec-9f2a-43bd-a3ab-01912f50282b；任务链接 URL 示例：https://applink.feishu-pre.net/client/todo/detail?guid=8c6bf822-e4da-449a-b82a-dc44020f9be9&suite_entity_num=t21587362"
                  },
                  "label": {
                    "en_US": "Task GUID",
                    "zh_Hans": "任务 GUID"
                  },
                  "llm_description": "要添加的任务的 GUID，支持传任务 ID 和任务链接 URL。任务 ID 示例：8b5425ec-9f2a-43bd-a3ab-01912f50282b；任务链接 URL 示例：https://applink.feishu-pre.net/client/todo/detail?guid=8c6bf822-e4da-449a-b82a-dc44020f9be9&suite_entity_num=t21587362",
                  "max": null,
                  "min": null,
                  "name": "task_guid",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "A list of member emails or phone numbers, separated by commas.",
                    "zh_Hans": "任务成员邮箱或者手机号列表，使用逗号分隔。"
                  },
                  "label": {
                    "en_US": "Task Member Phone Or Email",
                    "zh_Hans": "任务成员的电话或邮箱"
                  },
                  "llm_description": "任务成员邮箱或者手机号列表，使用逗号分隔。",
                  "max": null,
                  "min": null,
                  "name": "member_phone_or_email",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "follower",
                  "form": "form",
                  "human_description": {
                    "en_US": "Member role, optional values are \"assignee\" (responsible person) and \"follower\" (observer), with a default value of \"assignee\".",
                    "zh_Hans": "成员的角色，可选值有 \"assignee\"（负责人）和 \"follower\"（关注人），默认值为 \"assignee\"。"
                  },
                  "label": {
                    "en_US": "member_role",
                    "zh_Hans": "成员的角色"
                  },
                  "llm_description": "成员的角色，可选值有 \"assignee\"（负责人）和 \"follower\"（关注人），默认值为 \"assignee\"。",
                  "max": null,
                  "min": null,
                  "name": "member_role",
                  "options": [
                    {
                      "label": {
                        "en_US": "assignee",
                        "zh_Hans": "负责人"
                      },
                      "value": "assignee"
                    },
                    {
                      "label": {
                        "en_US": "follower",
                        "zh_Hans": "关注人"
                      },
                      "value": "follower"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-26T10:44:29Z",
        "version_updated_at": "2025-02-26T10:44:29Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "InfiniAI provides high-performance APIs for accelerating large model inference, covering multiple modalities such as text, images, and videos. It supports the latest open-source LLM models like DeepSeek, as well as SOTA embedding and reranking models such as Jina/bge. Configuration can be done via model names, API keys, and other parameters.",
          "ja_JP": "InfiniAIは、テキスト、画像、動画などの多様なモダリティをカバーする大規模モデル推論高速化のための高性能APIを提供します。DeepSeekなどの最新オープンソースLLMモデルや、Jina/bgeなどのSOTA埋め込み・再ランキングモデルをサポートし、モデル名、APIキー、その他のパラメータで設定できます。",
          "pt_BR": "InfiniAI fornece APIs de alto desempenho para acelerar a inferência de modelos grandes, abrangendo várias modalidades, como texto, imagens e vídeos. Ele suporta os mais recentes modelos LLM de código aberto, como DeepSeek, bem como modelos SOTA de incorporação e reclassificação, como Jina/bge. A configuração pode ser feita por meio de nomes de modelos, chaves de API e outros parâmetros.",
          "zh_Hans": "无问芯穹提供大模型推理加速高性能API，涵盖文本、图像、视频等多种模态，支持最新开源DeepSeek等系列LLM模型，以及Jina/bge等sota嵌入重排模型，可通过模型名称、API密钥和其他参数进行配置。"
        },
        "category": "model",
        "created_at": "2025-03-24T01:48:41Z",
        "endpoint": {},
        "icon": "infiniai/packages/infiniai/_assets/icon.svg",
        "index_id": "infiniai___infiniai",
        "install_count": 563,
        "introduction": "\n\n### Overview\nInfiniAI(MaaS) provides high-performance APIs for accelerating large model inference, covering multiple modalities such as text, images, and videos. It supports the latest open-source LLM models like DeepSeek, as well as SOTA embedding and reranking models such as Jina/bge. Configuration can be done via model names, API keys, and other parameters.\n\n### Configure\nInstall the infiniai plugin, then configure it by entering your API Key. Get your API Key from [InfiniAI](https://cloud.infini-ai.com/login?redirect=/genstudio/model?deepsearch) and save.    \n<img src=\"./_assets/configure.png\" width=\"60%\" alt=\"配置界面\">\n\n### About InfiniAI \nWebsite | [InfiniAI](https://cloud.infini-ai.com/genstudio/model)\n\n### Contract\nyaozhuyu@infini-ai.com\n\n### Repository\nhttps://github.com/paxionfull/infiniai_dify_plugin\n",
        "label": {
          "en_US": "无问芯穹",
          "ja_JP": "无问芯穹",
          "pt_BR": "无问芯穹",
          "zh_Hans": "无问芯穹"
        },
        "latest_package_identifier": "infiniai/infiniai:0.0.2@fa05537b9be066ca640a9ab307fd6b294d31b7c5038dce9e105b87d6a641caa0",
        "latest_version": "0.0.2",
        "model": {
          "background": "#E5E7EB",
          "configurate_methods": [
            "predefined-model",
            "customizable-model"
          ],
          "description": {
            "en_US": "Models provided by InfiniAI.",
            "zh_Hans": "InfiniAI 提供的模型。"
          },
          "help": {
            "title": {
              "en_US": "Get your API Key from InfiniAI",
              "zh_Hans": "从 InfiniAI 获取 API Key"
            },
            "url": {
              "en_US": "https://cloud.infini-ai.com/genstudio/model?deepsearch"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.svg"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "InfiniAI"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "infiniai_api_key"
              }
            ],
            "model": {
              "label": {
                "en_US": "Model Name",
                "zh_Hans": "模型名称"
              },
              "placeholder": {
                "en_US": "Enter your model name",
                "zh_Hans": "输入模型名称"
              }
            }
          },
          "models": [
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "deepseek-r1",
                "zh_Hans": "deepseek-r1"
              },
              "model": "deepseek-r1",
              "model_properties": {
                "context_size": 64000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "deepseek-v3",
                "zh_Hans": "deepseek-v3"
              },
              "model": "deepseek-v3",
              "model_properties": {
                "context_size": 64000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen2.5-14b-instruct",
                "zh_Hans": "qwen2.5-14b-instruct"
              },
              "model": "qwen2.5-14b-instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen2.5-32b-instruct",
                "zh_Hans": "qwen2.5-32b-instruct"
              },
              "model": "qwen2.5-32b-instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen2.5-72b-instruct",
                "zh_Hans": "qwen2.5-72b-instruct"
              },
              "model": "qwen2.5-72b-instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen2.5-7b-instruct",
                "zh_Hans": "qwen2.5-7b-instruct"
              },
              "model": "qwen2.5-7b-instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0"
              }
            },
            {
              "deprecated": false,
              "features": [
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen2.5-vl-32b-instruct",
                "zh_Hans": "qwen2.5-vl-32b-instruct"
              },
              "model": "qwen2.5-vl-32b-instruct",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0"
              }
            },
            {
              "deprecated": false,
              "features": [
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen2.5-vl-72b-instruct",
                "zh_Hans": "qwen2.5-vl-72b-instruct"
              },
              "model": "qwen2.5-vl-72b-instruct",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0"
              }
            },
            {
              "deprecated": false,
              "features": [
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwen2.5-vl-7b-instruct",
                "zh_Hans": "qwen2.5-vl-7b-instruct"
              },
              "model": "qwen2.5-vl-7b-instruct",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 4096,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "qwq-32b",
                "zh_Hans": "qwq-32b"
              },
              "model": "qwq-32b",
              "model_properties": {
                "context_size": 64000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 2048,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "response_format"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "bge-reranker-v2-m3"
              },
              "model": "bge-reranker-v2-m3",
              "model_properties": {
                "context_size": 8192
              },
              "model_type": "rerank",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "bge-m3"
              },
              "model": "bge-m3",
              "model_properties": {
                "context_size": 8192,
                "max_chunks": 1
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "jina-embeddings-v2-base-code"
              },
              "model": "jina-embeddings-v2-base-code",
              "model_properties": {
                "context_size": 8192,
                "max_chunks": 1
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "jina-embeddings-v2-base-zh"
              },
              "model": "jina-embeddings-v2-base-zh",
              "model_properties": {
                "context_size": 8192,
                "max_chunks": 1
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": null
            }
          ],
          "position": {},
          "provider": "infiniai",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "infiniai_api_key"
              }
            ]
          },
          "supported_model_types": [
            "llm",
            "text-embedding",
            "rerank",
            "tts",
            "speech2text",
            "moderation"
          ]
        },
        "name": "infiniai",
        "org": "infiniai",
        "plugin_id": "infiniai/infiniai",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/infiniai.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": true,
              "rerank": true,
              "speech2text": true,
              "text_embedding": true,
              "tts": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-10T15:12:52Z",
        "version_updated_at": "2025-04-10T15:12:52Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Query Prometheus metrics using PromQL with time range support",
          "ja_JP": "時間範囲をサポートしたPromQLによるPrometheusメトリクスのクエリ",
          "pt_BR": "Consulta métricas do Prometheus usando PromQL com suporte a intervalo de tempo",
          "zh_Hans": "使用PromQL查询Prometheus指标数据，支持时间范围"
        },
        "category": "tool",
        "created_at": "2025-03-14T11:43:05Z",
        "endpoint": {},
        "icon": "lework/packages/prometheus/_assets/icon.svg",
        "index_id": "lework___prometheus",
        "install_count": 562,
        "introduction": "## prometheus\n\n**Author:** lework\n**Version:** 0.0.1\n**Type:** tool\n\n### Description\n\n## 创建 Dify 插件\n\ndify plugin init\n\n## 打包插件\n\ndify plugin package ./google\n\n# Prometheus 查询插件\n\nDify 的 Prometheus 查询插件，允许用户通过 PromQL 查询 Prometheus 指标数据。\n\n## 功能\n\n- 使用 PromQL 查询 Prometheus 指标数据\n- 支持时间范围查询（相对时间和绝对时间）\n- 支持基本认证和令牌认证\n- 自动格式化结果以便于理解\n- **支持 Markdown 表格输出**，将标签作为列清晰展示每个指标的最新值\n- **Kubernetes Pod 资源指标查询**，获取 Pod 的 CPU、内存使用情况和重启次数\n\n## 配置\n\n在使用此插件前，需要配置以下信息：\n\n- **API URL**: Prometheus 服务器的 URL，例如 `http://localhost:9090`\n- **用户名/密码**: (可选) 基本认证的用户名和密码\n- **令牌**: (可选) Bearer 令牌认证\n\n## 工具\n\n### 1. Prometheus 查询\n\n#### 参数\n\n- **PromQL 查询语句**: 必填，要执行的 PromQL 查询语句\n- **开始时间**: 可选，查询的开始时间，支持以下格式：\n  - RFC3339/ISO8601 格式: `2023-01-01T00:00:00Z`\n  - 相对时间: `1h`, `2d`, `3w`, `4m`, `5y` 等\n  - 默认值: `1h` (1 小时前)\n- **结束时间**: 可选，查询的结束时间，支持与开始时间相同的格式\n  - 默认值: `now` (当前时间)\n- **步长**: 可选，查询分辨率步长\n  - 格式: `15s`, `1m`, `1h` 等\n  - 默认值: `15s` (15 秒)\n\n#### 示例\n\n##### 查询 CPU 使用率\n\n```\nquery: 100 - (avg by (instance) (irate(node_cpu_seconds_total{mode=\"idle\"}[5m])) * 100)\nstart_time: 1h\nend_time: now\nstep: 1m\n```\n\n##### 查询内存使用率\n\n```\nquery: 100 * (1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes))\nstart_time: 12h\nend_time: now\nstep: 5m\n```\n\n### 2. Kubernetes Pod 资源指标查询\n\n获取 Kubernetes Pod 的资源使用情况，包括 CPU、内存使用率以及重启次数等信息，并以 Markdown 表格的形式展示。\n\n#### 参数\n\n- **命名空间**: 可选，Kubernetes 命名空间名称，不填则查询所有命名空间\n- **标签选择器**: 可选，用于过滤 Pod 的标签选择器，例如 `app=myapp,component=database`\n- **Pod 名称模式**: 可选，用于过滤 Pod 名称的正则表达式，例如 `frontend-.*`\n\n#### 示例\n\n##### 查询特定命名空间的 Pod 资源使用情况\n\n```\nnamespace: default\n```\n\n##### 查询特定应用的 Pod 资源使用情况\n\n```\nselector: app=myapp\n```\n\n##### 查询特定前缀的 Pod 资源使用情况\n\n```\npod_name_pattern: frontend-.*\n```\n\n#### 返回结果\n\n返回包含以下信息的 Markdown 表格：\n\n| Pod 名称 | 存活时长 | 命名空间 | 节点  | 就绪状态 | Phase   | CPU 使用% | 内存使用 MiB | CPU 请求 | CPU 限制 | 内存请求 MiB | 内存限制 MiB | 24h 重启次数 |\n| -------- | -------- | -------- | ----- | -------- | ------- | --------- | ------------ | -------- | -------- | ------------ | ------------ | ------------ |\n| pod-1    | 1.0 天   | default  | node1 | ✓        | Running | 0.819%    | 500 MiB      | 0.100    | 1        | 500 MiB      | 2 GiB        | 0            |\n| pod-2    | 1.7 天   | default  | node2 | ✓        | Running | 0.380%    | 256 MiB      | 0.100    | 1        | 256 MiB      | 2 GiB        | 0            |\n\n## 返回结果\n\n### Markdown 表格格式 (新增特性)\n\n对于矩阵类型的查询结果，插件会生成 Markdown 表格，**将标签作为表格列**，便于清晰展示数据：\n\n```markdown\n### node_cpu_seconds_total\n\n| timestamp           | instance       | job        | mode   | value |\n| :------------------ | :------------- | :--------- | :----- | ----: |\n| 2023-03-11T18:15:00 | 10.131.242.148 | prometheus | idle   | 0.278 |\n| 2023-03-11T18:15:00 | 10.131.242.149 | prometheus | system | 0.156 |\n\n_显示最近的数据点_\n```\n\n### JSON 格式\n\n当无法生成 Markdown 表格时，插件会返回 JSON 格式的完整结果：\n\n```json\n{\n  \"success\": true,\n  \"result_type\": \"matrix\",\n  \"data\": [\n    {\n      \"metric\": \"metric_name\",\n      \"labels\": {\n        \"instance\": \"localhost:9090\",\n        \"job\": \"prometheus\"\n      },\n      \"values\": [\n        {\n          \"timestamp\": \"2023-01-01T00:00:00.000000\",\n          \"value\": 12.34\n        },\n        ...\n      ]\n    },\n    ...\n  ]\n}\n```\n",
        "label": {
          "en_US": "Prometheus Query",
          "ja_JP": "Prometheus クエリ",
          "pt_BR": "Consulta Prometheus",
          "zh_Hans": "Prometheus查询"
        },
        "latest_package_identifier": "lework/prometheus:0.0.1@73c63eed6b4c672164072a6cb0ffc16d46df42bf933d7a315c6ca09ab9708aec",
        "latest_version": "0.0.1",
        "model": {},
        "name": "prometheus",
        "org": "lework",
        "plugin_id": "lework/prometheus",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/prometheus.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "The URL of your Prometheus server, e.g. http://localhost:9090",
                "pt_BR": "The URL of your Prometheus server, e.g. http://localhost:9090",
                "zh_Hans": "Prometheus服务器的URL，例如 http://localhost:9090"
              },
              "label": {
                "en_US": "API URL",
                "pt_BR": "API URL",
                "zh_Hans": "API URL"
              },
              "name": "api_url",
              "options": null,
              "placeholder": {
                "en_US": "http://localhost:9090",
                "pt_BR": "http://localhost:9090",
                "zh_Hans": "http://localhost:9090"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://prometheus.io/docs/prometheus/latest/querying/api/"
            },
            {
              "default": null,
              "help": {
                "en_US": "Username for basic authentication (optional)",
                "pt_BR": "Username for basic authentication (optional)",
                "zh_Hans": "基本认证的用户名（可选）"
              },
              "label": {
                "en_US": "Username",
                "pt_BR": "Username",
                "zh_Hans": "用户名"
              },
              "name": "username",
              "options": null,
              "placeholder": {
                "en_US": "username",
                "pt_BR": "username",
                "zh_Hans": "用户名"
              },
              "required": false,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "help": {
                "en_US": "Password for basic authentication (optional)",
                "pt_BR": "Password for basic authentication (optional)",
                "zh_Hans": "基本认证的密码（可选）"
              },
              "label": {
                "en_US": "Password",
                "pt_BR": "Password",
                "zh_Hans": "密码"
              },
              "name": "password",
              "options": null,
              "placeholder": {
                "en_US": "password",
                "pt_BR": "password",
                "zh_Hans": "密码"
              },
              "required": false,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "help": {
                "en_US": "Bearer token for authentication (optional)",
                "pt_BR": "Bearer token for authentication (optional)",
                "zh_Hans": "认证的Bearer令牌（可选）"
              },
              "label": {
                "en_US": "Token",
                "pt_BR": "Token",
                "zh_Hans": "令牌"
              },
              "name": "token",
              "options": null,
              "placeholder": {
                "en_US": "token",
                "pt_BR": "token",
                "zh_Hans": "令牌"
              },
              "required": false,
              "scope": null,
              "type": "secret-input",
              "url": null
            }
          ],
          "identity": {
            "author": "lework",
            "description": {
              "en_US": "Query Prometheus metrics using PromQL",
              "pt_BR": "Query Prometheus metrics using PromQL",
              "zh_Hans": "使用PromQL查询Prometheus指标数据"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Prometheus",
              "pt_BR": "Prometheus",
              "zh_Hans": "Prometheus"
            },
            "name": "prometheus",
            "tags": [
              "other"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Query Prometheus metrics using PromQL",
                  "pt_BR": "Query Prometheus metrics using PromQL",
                  "zh_Hans": "使用PromQL查询Prometheus指标数据"
                },
                "llm": "Query Prometheus metrics with PromQL query and time range"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "lework",
                "label": {
                  "en_US": "prometheus",
                  "pt_BR": "prometheus",
                  "zh_Hans": "Prometheus 指标数据查询"
                },
                "name": "prometheus"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The PromQL query string to execute",
                    "pt_BR": "The PromQL query string to execute",
                    "zh_Hans": "要执行的PromQL查询语句"
                  },
                  "label": {
                    "en_US": "PromQL Query",
                    "pt_BR": "PromQL Query",
                    "zh_Hans": "PromQL查询语句"
                  },
                  "llm_description": "The Prometheus Query Language (PromQL) query string to execute",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Start time for the query in RFC3339 format or relative format (e.g. '1h', '2d')",
                    "pt_BR": "Start time for the query in RFC3339 format or relative format",
                    "zh_Hans": "查询的开始时间，RFC3339格式或相对格式（如'1h', '2d'）"
                  },
                  "label": {
                    "en_US": "Start Time",
                    "pt_BR": "Start Time",
                    "zh_Hans": "开始时间"
                  },
                  "llm_description": "Start time for the query in RFC3339 format or relative format (e.g. '1h', '2d')",
                  "max": null,
                  "min": null,
                  "name": "start_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "End time for the query in RFC3339 format or relative format (e.g. 'now')",
                    "pt_BR": "End time for the query in RFC3339 format or relative format",
                    "zh_Hans": "查询的结束时间，RFC3339格式或相对格式（如'now'）"
                  },
                  "label": {
                    "en_US": "End Time",
                    "pt_BR": "End Time",
                    "zh_Hans": "结束时间"
                  },
                  "llm_description": "End time for the query in RFC3339 format or relative format (e.g. 'now')",
                  "max": null,
                  "min": null,
                  "name": "end_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Query resolution step width in duration format (e.g. '15s', '1m', '1h')",
                    "pt_BR": "Query resolution step width in duration format",
                    "zh_Hans": "查询分辨率步长，以持续时间格式表示（如'15s', '1m', '1h'）"
                  },
                  "label": {
                    "en_US": "Step",
                    "pt_BR": "Step",
                    "zh_Hans": "步长"
                  },
                  "llm_description": "Query resolution step width in duration format (e.g. '15s', '1m', '1h')",
                  "max": null,
                  "min": null,
                  "name": "step",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get resource usage information for Kubernetes pods over a time period",
                  "zh_Hans": "获取一段时间内Kubernetes Pod的资源使用情况信息"
                },
                "llm": "Get resource metrics (CPU, memory, restart count) for Kubernetes pods in a deployment over a specified time period and display as a Markdown table with statistics"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "lework",
                "label": {
                  "en_US": "Kubernetes Pod Metrics",
                  "zh_Hans": "Kubernetes Pod 资源指标查询"
                },
                "name": "kubernetes_pod_metrics"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Kubernetes namespace to query (default is all namespaces)",
                    "zh_Hans": "要查询的Kubernetes命名空间（默认为所有命名空间）"
                  },
                  "label": {
                    "en_US": "Namespace",
                    "zh_Hans": "命名空间"
                  },
                  "llm_description": "Kubernetes namespace to filter pods (leave empty for all namespaces)",
                  "max": null,
                  "min": null,
                  "name": "namespace",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Label selector to filter pods (e.g. 'app=myapp')",
                    "zh_Hans": "用于过滤Pod的标签选择器（例如'app=myapp'）"
                  },
                  "label": {
                    "en_US": "Label Selector",
                    "zh_Hans": "标签选择器"
                  },
                  "llm_description": "Kubernetes label selector to filter pods (e.g. 'app=myapp', 'component=database')",
                  "max": null,
                  "min": null,
                  "name": "selector",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Regular expression to filter pods by name",
                    "zh_Hans": "用于按名称过滤Pod的正则表达式"
                  },
                  "label": {
                    "en_US": "Pod Name Pattern",
                    "zh_Hans": "Pod名称模式"
                  },
                  "llm_description": "Regular expression to match pod names (e.g. 'frontend-.*' to match all pods starting with 'frontend-')",
                  "max": null,
                  "min": null,
                  "name": "pod_name_pattern",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Start time for the metrics query (e.g. '1h' for 1 hour ago, '2d' for 2 days ago, or ISO timestamp)",
                    "zh_Hans": "指标查询的开始时间（例如'1h'表示1小时前，'2d'表示2天前，或ISO时间戳）"
                  },
                  "label": {
                    "en_US": "Start Time",
                    "zh_Hans": "开始时间"
                  },
                  "llm_description": "The start time for the query period. Can be relative (e.g. '24h' for 24 hours ago) or absolute time in ISO format.",
                  "max": null,
                  "min": null,
                  "name": "start_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "End time for the metrics query (e.g. 'now' for current time, or ISO timestamp)",
                    "zh_Hans": "指标查询的结束时间（例如'now'表示当前时间，或ISO时间戳）"
                  },
                  "label": {
                    "en_US": "End Time",
                    "zh_Hans": "结束时间"
                  },
                  "llm_description": "The end time for the query period. Can be 'now' or absolute time in ISO format.",
                  "max": null,
                  "min": null,
                  "name": "end_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "5m",
                  "form": "llm",
                  "human_description": {
                    "en_US": "Step interval for time series data (e.g. '5m' for 5 minutes)",
                    "zh_Hans": "时间序列数据的步长间隔（例如'5m'表示5分钟）"
                  },
                  "label": {
                    "en_US": "Step",
                    "zh_Hans": "步长"
                  },
                  "llm_description": "The step size between data points. Affects resolution and query performance.",
                  "max": null,
                  "min": null,
                  "name": "step",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-14T11:43:11Z",
        "version_updated_at": "2025-03-14T11:43:11Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Database Query Tool",
          "ja_JP": "Database Query Tool",
          "pt_BR": "Database Query Tool",
          "zh_Hans": "Database Query Tool"
        },
        "category": "tool",
        "created_at": "2025-04-13T17:06:33Z",
        "endpoint": {},
        "icon": "qjzt_cn/packages/sql-db/_assets/icon.svg",
        "index_id": "qjzt_cn___sql-db",
        "install_count": 555,
        "introduction": "# SQL Database Tool (sql-db)\n\n[English](README.md) | [中文](README_CN.md)\n\nA simple and efficient SQL database query tool.\n\n**Author:** qjzt_cn  \n**Version:** 0.0.1  \n**Type:** tool  \n**Repository:** [https://github.com/QJZT/sql-db](https://github.com/QJZT/sql-db)\n\n## Features\n\n- Lightweight dependencies with only two core libraries:\n  - sqlalchemy>=2.0.0\n  - psycopg2-binary>=2.9.9\n\n- Simplified workflow:\n  - No complex URL authorization configuration needed\n  - Direct database connection with simple parameters\n  - Support for standard SQL operations (SELECT)\n\n## Usage Examples\n\n![Database Connection](_assets/1.jpg)\n![Query Interface](_assets/2.jpg)\n![Query Execution](_assets/3.jpg)\n![Results Display](_assets/4.jpg)\n![Advanced Features](_assets/5.jpg)\n",
        "label": {
          "en_US": "sql-db",
          "ja_JP": "sql-db",
          "pt_BR": "sql-db",
          "zh_Hans": "sql-db"
        },
        "latest_package_identifier": "qjzt_cn/sql-db:0.0.1@525b4146dbf93a68665dd857503ed6121e0e283b3c53580db83a33377b7d4b7b",
        "latest_version": "0.0.1",
        "model": {},
        "name": "sql-db",
        "org": "qjzt_cn",
        "plugin_id": "qjzt_cn/sql-db",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/sql-db.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {}
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "qjzt_cn",
            "description": {
              "en_US": "Database Query Tool",
              "pt_BR": "Database Query Tool",
              "zh_Hans": "Database Query Tool"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "sql-db",
              "pt_BR": "sql-db",
              "zh_Hans": "sql-db"
            },
            "name": "sql-db",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool for executing SQL queries on databases. Supports various SQL operations like SELECT.",
                  "pt_BR": "Uma ferramenta para executar consultas SQL em bancos de dados. Suporta várias operações SQL.",
                  "zh_Hans": "用于执行SQL数据库查询的工具。支持SELECT查询操作。"
                },
                "llm": "A tool for executing SQL queries on databases. You can use this tool to perform database operations including SELECT statements."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "qjzt_cn",
                "label": {
                  "en_US": "SQL Database Query",
                  "pt_BR": "Consulta de Banco de Dados SQL",
                  "zh_Hans": "SQL数据库查询"
                },
                "name": "sql-query"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Enter your SQL query statement (e.g., SELECT * FROM table_name)",
                    "pt_BR": "Enter your SQL query statement (e.g., SELECT * FROM table_name)",
                    "zh_Hans": "输入要执行的SQL查询语句（例如：SELECT * FROM table_name）"
                  },
                  "label": {
                    "en_US": "SQL string",
                    "pt_BR": "SQL string",
                    "zh_Hans": "SQL语句"
                  },
                  "llm_description": "The SQL query to execute. Support standard SQL syntax including SELECT statements.",
                  "max": null,
                  "min": null,
                  "name": "sql_query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Database connection string (e.g., postgresql://user:password@localhost:5432/dbname)",
                    "pt_BR": "tring de conexão do banco de dados postgresql://user:password@localhost:5432/dbname",
                    "zh_Hans": "数据库连接字符串（例如：postgresql://user:password@localhost:5432/dbname）"
                  },
                  "label": {
                    "en_US": "Database Connection URI",
                    "pt_BR": "URI de Conexão do Banco de Dados",
                    "zh_Hans": "数据库连接地址"
                  },
                  "llm_description": "The database connection URI in the format of dialect+driver://username:password@host:port/database",
                  "max": null,
                  "min": null,
                  "name": "db_uri",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "json",
                  "form": "form",
                  "human_description": {
                    "en_US": "Choose the output format.",
                    "zh_Hans": "选择输出格式。"
                  },
                  "label": {
                    "en_US": "Output format",
                    "zh_Hans": "输出格式"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "format",
                  "options": [
                    {
                      "label": {
                        "en_US": "JSON",
                        "zh_Hans": "JSON"
                      },
                      "value": "json"
                    },
                    {
                      "label": {
                        "en_US": "JSON rows arr",
                        "zh_Hans": "JSON rows arr"
                      },
                      "value": "json rows arr"
                    },
                    {
                      "label": {
                        "en_US": "CSV to file",
                        "zh_Hans": "CSV to file"
                      },
                      "value": "csv"
                    },
                    {
                      "label": {
                        "en_US": "YAML to file",
                        "zh_Hans": "YAML to file"
                      },
                      "value": "yaml to file"
                    },
                    {
                      "label": {
                        "en_US": "YAML to string",
                        "zh_Hans": "YAML to string"
                      },
                      "value": "yaml to string"
                    },
                    {
                      "label": {
                        "en_US": "Markdown to file",
                        "zh_Hans": "Markdown to file"
                      },
                      "value": "Markdown to file"
                    },
                    {
                      "label": {
                        "en_US": "Markdown to string",
                        "zh_Hans": "Markdown to string"
                      },
                      "value": "Markdown to string"
                    },
                    {
                      "label": {
                        "en_US": "xlsx to file",
                        "zh_Hans": "xlsx to file"
                      },
                      "value": "xlsx to file"
                    },
                    {
                      "label": {
                        "en_US": "xlsx to string",
                        "zh_Hans": "xlsx to string"
                      },
                      "value": "xlsx to string"
                    },
                    {
                      "label": {
                        "en_US": "html to file",
                        "zh_Hans": "html to file"
                      },
                      "value": "html to file"
                    },
                    {
                      "label": {
                        "en_US": "html to string",
                        "zh_Hans": "html to string"
                      },
                      "value": "html to string"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-13T17:06:51Z",
        "version_updated_at": "2025-04-13T17:06:51Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Yuque, https://www.yuque.com.",
          "pt_BR": "Yuque, https://www.yuque.com.",
          "zh_Hans": "语雀，https://www.yuque.com。"
        },
        "category": "tool",
        "created_at": "2024-11-29T09:44:57Z",
        "endpoint": {},
        "icon": "langgenius/packages/aliyuque/_assets/icon.svg",
        "index_id": "langgenius___aliyuque",
        "install_count": 554,
        "introduction": "# Overview\n\nThe **Yuque Plugin** provides seamless integration with **Yuque (语雀)**, a powerful knowledge management and collaboration platform. This plugin includes a comprehensive set of tools to manage documents, books, and repositories programmatically within workflows.\n\nTools Included:\n1. **Create Document**: Create a new document in a specified book.\n2. **Delete Document**: Delete an existing document by its ID.\n3. **Get Repo Index Page**: Retrieve the index page of a repository.\n4. **Get Book's Table of Contents**: Fetch the table of contents for a specific book.\n5. **Fetch Document Content**: Retrieve the content of a specific document.\n6. **Get Doc Detail**: Fetch detailed metadata about a document.\n7. **Update Book's Table of Contents**: Modify the table of contents for a book.\n8. **Update Document**: Update the content or metadata of an existing document.\n\n# Configure\n\n1. Install the plugin.\n1. Go to the **Dify Marketplace**.\n2. Search for the **Yuque Plugin**.\n3. Click \"Install\" to add the plugin to your workspace.\n![](./_assets/yuque_install.PNG)\n\n2. Obtain Yuque Team Token\n1. Log in to your Yuque account at [Yuque](https://www.yuque.com/).\n2. Navigate to your account settings and go to the [Tokens Page](https://www.yuque.com/settings/tokens).\n3. Generate a new team token and copy it for use in Dify.\n\n3. Authorize the Plugin\n1. Add any of the Yuque tools (e.g., \"Create Document\" or \"Fetch Document Content\") to your workflow in Dify.\n2. Click on the \"To authorize\" button in the tool configuration panel.\n3. Enter your **Yuque Team Token** in the provided field.\n4. Save your credentials to complete the authorization process.\n\n4. Input Variables\nEach tool requires specific input variables:\n\n### Create Document\n- Repo ID (String, Required): The ID of the repository where you want to create the document.\n- Title (String, Required): The title of the new document.\n- Content (String, Required): The content of the document.\n\n### Delete Document\n- Doc ID (String, Required): The ID of the document you want to delete.\n\n### Get Repo Index Page\n- Repo ID (String, Required): The ID of the repository whose index page you want to retrieve.\n\n### Get Book's Table of Contents\n- Book ID (String, Required): The ID of the book whose table of contents you want to fetch.\n\n### Fetch Document Content\n- Doc ID (String, Required): The ID of the document whose content you want to retrieve.\n\n### Get Doc Detail\n- Doc ID (String, Required): The ID of the document whose details you want to fetch.\n\n### Update Book's Table of Contents\n- Book ID (String, Required): The ID of the book whose table of contents you want to update.\n- TOC Data (JSON String, Required): The updated table of contents in JSON format.\n\n### Update Document\n- Doc ID (String, Required): The ID of the document you want to update.\n- Title (String, Optional): The new title for the document.\n- Content (String, Optional): The updated content for the document.\n\n# Example Workflow\n1. Add the \"Create Document\" tool to your workflow in Dify.\n2. Input:\n  - `Repo ID`: `\"123456\"`\n  - `Title`: `\"New Project Plan\"`\n  - `Content`: `\"This is a detailed project plan for Q1.\"`\n3. Run the tool to create a new document in your specified repository.\n\n4. Use \"Fetch Document Content\" or \"Update Document\" tools as needed for further operations on this document.",
        "label": {
          "en_US": "yuque",
          "pt_BR": "yuque",
          "zh_Hans": "语雀"
        },
        "latest_package_identifier": "langgenius/aliyuque:0.0.2@59fafbe986a3dce7555b08b1364b809daeca9948974943d9c075ce2586320cca",
        "latest_version": "0.0.2",
        "model": {},
        "name": "aliyuque",
        "org": "langgenius",
        "plugin_id": "langgenius/aliyuque",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/aliyuque.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "search"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "Yuque Team Token",
                "zh_Hans": "语雀团队Token"
              },
              "name": "token",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Yuque team token",
                "zh_Hans": "请输入你的语雀团队Token"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://www.yuque.com/settings/tokens"
            }
          ],
          "identity": {
            "author": "佐井",
            "description": {
              "en_US": "Yuque, https://www.yuque.com.",
              "pt_BR": "Yuque, https://www.yuque.com.",
              "zh_Hans": "语雀，https://www.yuque.com。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "yuque",
              "pt_BR": "yuque",
              "zh_Hans": "语雀"
            },
            "name": "aliyuque",
            "tags": [
              "productivity",
              "search"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Creates a new document within a knowledge base without automatic addition to the table of contents. Requires a subsequent call to the \"knowledge base directory update API\". Supports setting visibility, format, and content.",
                  "zh_Hans": "在知识库中创建新文档，但不会自动加入目录，需额外调用“知识库目录更新接口”。允许设置公开性、格式及正文内容。"
                },
                "llm": "Creates docs in a KB."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "佐井",
                "label": {
                  "en_US": "Create Document",
                  "zh_Hans": "创建文档"
                },
                "name": "aliyuque_create_document"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The unique identifier of the knowledge base where the document will be created.",
                    "zh_Hans": "文档将被创建的知识库的唯一标识。"
                  },
                  "label": {
                    "en_US": "Knowledge Base ID",
                    "zh_Hans": "知识库ID"
                  },
                  "llm_description": "ID of the target knowledge base.",
                  "max": null,
                  "min": null,
                  "name": "book_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The title of the document, defaults to 'Untitled' if not provided.",
                    "zh_Hans": "文档标题，默认为'无标题'如未提供。"
                  },
                  "label": {
                    "en_US": "Title",
                    "zh_Hans": "标题"
                  },
                  "llm_description": "Title of the document, defaults to 'Untitled'.",
                  "max": null,
                  "min": null,
                  "name": "title",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Document visibility (0 Private, 1 Public, 2 Enterprise-only).",
                    "zh_Hans": "文档可见性（0 私密, 1 公开, 2 企业内公开）。"
                  },
                  "label": {
                    "en_US": "Visibility",
                    "zh_Hans": "公开性"
                  },
                  "llm_description": "Doc visibility options, 0-private, 1-public, 2-enterprise.",
                  "max": null,
                  "min": null,
                  "name": "public",
                  "options": [
                    {
                      "label": {
                        "en_US": "Private",
                        "zh_Hans": "私密"
                      },
                      "value": "0"
                    },
                    {
                      "label": {
                        "en_US": "Public",
                        "zh_Hans": "公开"
                      },
                      "value": "1"
                    },
                    {
                      "label": {
                        "en_US": "Enterprise-only",
                        "zh_Hans": "企业内公开"
                      },
                      "value": "2"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Format of the document content (markdown, HTML, Lake).",
                    "zh_Hans": "文档内容格式（markdown, HTML, Lake）。"
                  },
                  "label": {
                    "en_US": "Content Format",
                    "zh_Hans": "内容格式"
                  },
                  "llm_description": "Content format choices, markdown, HTML, Lake.",
                  "max": null,
                  "min": null,
                  "name": "format",
                  "options": [
                    {
                      "label": {
                        "en_US": "markdown",
                        "zh_Hans": "markdown"
                      },
                      "value": "markdown"
                    },
                    {
                      "label": {
                        "en_US": "html",
                        "zh_Hans": "html"
                      },
                      "value": "html"
                    },
                    {
                      "label": {
                        "en_US": "lake",
                        "zh_Hans": "lake"
                      },
                      "value": "lake"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The actual content of the document.",
                    "zh_Hans": "文档的实际内容。"
                  },
                  "label": {
                    "en_US": "Body Content",
                    "zh_Hans": "正文内容"
                  },
                  "llm_description": "Content of the document.",
                  "max": null,
                  "min": null,
                  "name": "body",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Retrieves document content from Yuque based on the provided document URL, which can be a normal or shared link.",
                  "zh_Hans": "根据提供的语雀文档地址（支持正常链接或分享链接）获取文档内容。"
                },
                "llm": "Fetches Yuque document content given a URL."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "佐井",
                "label": {
                  "en_US": "Fetch Document Content",
                  "zh_Hans": "获取文档内容"
                },
                "name": "aliyuque_describe_document_content"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The URL of the document to retrieve content from, can be normal or shared.",
                    "zh_Hans": "需要获取内容的文档地址，可以是正常链接或分享链接。"
                  },
                  "label": {
                    "en_US": "Document URL",
                    "zh_Hans": "文档地址"
                  },
                  "llm_description": "URL of the Yuque document to fetch content.",
                  "max": null,
                  "min": null,
                  "name": "url",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "true:Body content only, false:Full response with metadata.",
                    "zh_Hans": "true:仅返回body内容，不返回其他元数据，false:返回所有元数据。"
                  },
                  "label": {
                    "en_US": "return body content only",
                    "zh_Hans": "仅返回body内容"
                  },
                  "llm_description": "true:Body content only, false:Full response with metadata.",
                  "max": null,
                  "min": null,
                  "name": "body_only",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The token for calling the Yuque API defaults to the Yuque token bound to the current tool if not provided.",
                    "zh_Hans": "调用语雀接口的token，如果不传则默认为当前工具绑定的语雀Token。"
                  },
                  "label": {
                    "en_US": "Yuque API Token",
                    "zh_Hans": "语雀接口Token"
                  },
                  "llm_description": "If the token for calling the Yuque API is not provided, it will default to the Yuque token bound to the current tool.",
                  "max": null,
                  "min": null,
                  "name": "token",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get Book's Table of Contents.",
                  "zh_Hans": "获取知识库的目录。"
                },
                "llm": "Get Book's Table of Contents."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "佐井",
                "label": {
                  "en_US": "Get Book's Table of Contents",
                  "zh_Hans": "获取知识库的目录"
                },
                "name": "aliyuque_describe_book_table_of_contents"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Book ID.",
                    "zh_Hans": "知识库 ID。"
                  },
                  "label": {
                    "en_US": "Book ID",
                    "zh_Hans": "知识库 ID"
                  },
                  "llm_description": "Book ID.",
                  "max": null,
                  "min": null,
                  "name": "book_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Delete Document",
                  "zh_Hans": "根据id删除文档"
                },
                "llm": "Delete document."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "佐井",
                "label": {
                  "en_US": "Delete Document",
                  "zh_Hans": "删除文档"
                },
                "name": "aliyuque_delete_document"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The unique identifier of the knowledge base where the document will be created.",
                    "zh_Hans": "文档将被创建的知识库的唯一标识。"
                  },
                  "label": {
                    "en_US": "Knowledge Base ID",
                    "zh_Hans": "知识库ID"
                  },
                  "llm_description": "ID of the target knowledge base.",
                  "max": null,
                  "min": null,
                  "name": "book_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Document ID or path.",
                    "zh_Hans": "文档 ID or 路径。"
                  },
                  "label": {
                    "en_US": "Document ID or Path",
                    "zh_Hans": "文档 ID or 路径"
                  },
                  "llm_description": "Document ID or path.",
                  "max": null,
                  "min": null,
                  "name": "id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Retrieves the homepage of a knowledge base within a group, supporting both book ID and group login with book slug access.",
                  "zh_Hans": "获取团队中知识库的首页信息，可通过书籍ID或团队登录名与书籍路径访问。"
                },
                "llm": "Fetches the knowledge base homepage using group and book identifiers with support for alternate access paths."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "佐井",
                "label": {
                  "en_US": "Get Repo Index Page",
                  "zh_Hans": "获取知识库首页"
                },
                "name": "aliyuque_describe_book_index_page"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The login name of the group that owns the knowledge base.",
                    "zh_Hans": "拥有该知识库的团队登录名。"
                  },
                  "label": {
                    "en_US": "Group Login",
                    "zh_Hans": "团队登录名"
                  },
                  "llm_description": "Team login identifier for the knowledge base owner.",
                  "max": null,
                  "min": null,
                  "name": "group_login",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The unique slug representing the path of the knowledge base.",
                    "zh_Hans": "知识库的唯一路径标识。"
                  },
                  "label": {
                    "en_US": "Book Slug",
                    "zh_Hans": "知识库路径"
                  },
                  "llm_description": "Unique path identifier for the knowledge base.",
                  "max": null,
                  "min": null,
                  "name": "book_slug",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Retrieves detailed information of a specific document identified by its ID or path within a knowledge base.",
                  "zh_Hans": "根据知识库ID和文档ID或路径获取文档详细信息。"
                },
                "llm": "Fetches detailed doc info using ID/path from a knowledge base; supports doc lookup in Yuque."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "佐井",
                "label": {
                  "en_US": "Get Doc Detail",
                  "zh_Hans": "获取文档详情"
                },
                "name": "aliyuque_describe_documents"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Identifier for the knowledge base where the document resides.",
                    "zh_Hans": "文档所属知识库的唯一标识。"
                  },
                  "label": {
                    "en_US": "Knowledge Base ID",
                    "zh_Hans": "知识库 ID"
                  },
                  "llm_description": "ID of the knowledge base holding the document.",
                  "max": null,
                  "min": null,
                  "name": "book_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The unique identifier or path of the document to retrieve.",
                    "zh_Hans": "需要获取的文档的ID或其在知识库中的路径。"
                  },
                  "label": {
                    "en_US": "Document ID or Path",
                    "zh_Hans": "文档 ID 或路径"
                  },
                  "llm_description": "Unique doc ID or its path for retrieval.",
                  "max": null,
                  "min": null,
                  "name": "id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Update Book's Table of Contents.",
                  "zh_Hans": "更新知识库目录。"
                },
                "llm": "Update Book's Table of Contents."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "佐井",
                "label": {
                  "en_US": "Update Book's Table of Contents",
                  "zh_Hans": "更新知识库目录"
                },
                "name": "aliyuque_update_book_table_of_contents"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Book ID.",
                    "zh_Hans": "知识库 ID。"
                  },
                  "label": {
                    "en_US": "Book ID",
                    "zh_Hans": "知识库 ID"
                  },
                  "llm_description": "Book ID.",
                  "max": null,
                  "min": null,
                  "name": "book_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "In the operation scenario, sibling node prepending is not supported, deleting a node doesn't remove associated documents, and node deletion has two modes, 'sibling' (delete current node) and 'child' (delete current node and its children).",
                    "zh_Hans": "操作，创建场景下不支持同级头插 prependNode，删除节点不会删除关联文档，删除节点时action_mode=sibling (删除当前节点), action_mode=child (删除当前节点及子节点)"
                  },
                  "label": {
                    "en_US": "Action Type",
                    "zh_Hans": "操作"
                  },
                  "llm_description": "In the operation scenario, sibling node prepending is not supported, deleting a node doesn't remove associated documents, and node deletion has two modes, 'sibling' (delete current node) and 'child' (delete current node and its children).",
                  "max": null,
                  "min": null,
                  "name": "action",
                  "options": [
                    {
                      "label": {
                        "en_US": "appendNode",
                        "pt_BR": "appendNode",
                        "zh_Hans": "appendNode"
                      },
                      "value": "appendNode"
                    },
                    {
                      "label": {
                        "en_US": "prependNode",
                        "pt_BR": "prependNode",
                        "zh_Hans": "prependNode"
                      },
                      "value": "prependNode"
                    },
                    {
                      "label": {
                        "en_US": "editNode",
                        "pt_BR": "editNode",
                        "zh_Hans": "editNode"
                      },
                      "value": "editNode"
                    },
                    {
                      "label": {
                        "en_US": "removeNode",
                        "pt_BR": "removeNode",
                        "zh_Hans": "removeNode"
                      },
                      "value": "editNode"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Operation mode (sibling:same level, child:child level).",
                    "zh_Hans": "操作模式 (sibling:同级, child:子级)。"
                  },
                  "label": {
                    "en_US": "Action Type",
                    "zh_Hans": "操作"
                  },
                  "llm_description": "Operation mode (sibling:same level, child:child level).",
                  "max": null,
                  "min": null,
                  "name": "action_mode",
                  "options": [
                    {
                      "label": {
                        "en_US": "sibling",
                        "pt_BR": "sibling",
                        "zh_Hans": "同级"
                      },
                      "value": "sibling"
                    },
                    {
                      "label": {
                        "en_US": "child",
                        "pt_BR": "child",
                        "zh_Hans": "子集"
                      },
                      "value": "child"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Target node UUID, defaults to root node if left empty.",
                    "zh_Hans": "目标节点 UUID, 不填默认为根节点。"
                  },
                  "label": {
                    "en_US": "Target node UUID",
                    "zh_Hans": "目标节点 UUID"
                  },
                  "llm_description": "Target node UUID, defaults to root node if left empty.",
                  "max": null,
                  "min": null,
                  "name": "target_uuid",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Operation node UUID [required for move/update/delete].",
                    "zh_Hans": "操作节点 UUID [移动/更新/删除必填]。"
                  },
                  "label": {
                    "en_US": "Node UUID",
                    "zh_Hans": "操作节点 UUID"
                  },
                  "llm_description": "Operation node UUID [required for move/update/delete].",
                  "max": null,
                  "min": null,
                  "name": "node_uuid",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Document IDs [required for creating documents], separate multiple IDs with ','.",
                    "zh_Hans": "文档 IDs [创建文档必填]，多个用','分隔。"
                  },
                  "label": {
                    "en_US": "Document IDs",
                    "zh_Hans": "文档id列表"
                  },
                  "llm_description": "Document IDs [required for creating documents], separate multiple IDs with ','.",
                  "max": null,
                  "min": null,
                  "name": "doc_ids",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "DOC",
                  "form": "llm",
                  "human_description": {
                    "en_US": "Node type [required for creation] (DOC:document, LINK:external link, TITLE:group).",
                    "zh_Hans": "操节点类型 [创建必填] (DOC:文档, LINK:外链, TITLE:分组)。"
                  },
                  "label": {
                    "en_US": "Node type",
                    "zh_Hans": "操节点类型"
                  },
                  "llm_description": "Node type [required for creation] (DOC:document, LINK:external link, TITLE:group).",
                  "max": null,
                  "min": null,
                  "name": "type",
                  "options": [
                    {
                      "label": {
                        "en_US": "DOC",
                        "pt_BR": "DOC",
                        "zh_Hans": "文档"
                      },
                      "value": "DOC"
                    },
                    {
                      "label": {
                        "en_US": "LINK",
                        "pt_BR": "LINK",
                        "zh_Hans": "链接"
                      },
                      "value": "LINK"
                    },
                    {
                      "label": {
                        "en_US": "TITLE",
                        "pt_BR": "TITLE",
                        "zh_Hans": "分组"
                      },
                      "value": "TITLE"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Node name [required for creating groups/external links].",
                    "zh_Hans": "节点名称 [创建分组/外链必填]。"
                  },
                  "label": {
                    "en_US": "Node Name",
                    "zh_Hans": "节点名称"
                  },
                  "llm_description": "Node name [required for creating groups/external links].",
                  "max": null,
                  "min": null,
                  "name": "title",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Node URL [required for creating external links].",
                    "zh_Hans": "节点 URL [创建外链必填]。"
                  },
                  "label": {
                    "en_US": "Node URL",
                    "zh_Hans": "节点URL"
                  },
                  "llm_description": "Node URL [required for creating external links].",
                  "max": null,
                  "min": null,
                  "name": "url",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 0,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Open in new window [optional for external links] (0:open in current page, 1:open in new window).",
                    "zh_Hans": "是否新窗口打开 [外链选填] (0:当前页打开, 1:新窗口打开)。"
                  },
                  "label": {
                    "en_US": "Open in new window",
                    "zh_Hans": "是否新窗口打开"
                  },
                  "llm_description": "Open in new window [optional for external links] (0:open in current page, 1:open in new window).",
                  "max": null,
                  "min": null,
                  "name": "open_window",
                  "options": [
                    {
                      "label": {
                        "en_US": "DOC",
                        "pt_BR": "DOC",
                        "zh_Hans": "Current Page"
                      },
                      "value": "0"
                    },
                    {
                      "label": {
                        "en_US": "LINK",
                        "pt_BR": "LINK",
                        "zh_Hans": "New Page"
                      },
                      "value": "1"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 1,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Visibility (0:invisible, 1:visible).",
                    "zh_Hans": "是否可见 (0:不可见, 1:可见)。"
                  },
                  "label": {
                    "en_US": "Visibility",
                    "zh_Hans": "是否可见"
                  },
                  "llm_description": "Visibility (0:invisible, 1:visible).",
                  "max": null,
                  "min": null,
                  "name": "visible",
                  "options": [
                    {
                      "label": {
                        "en_US": "Invisible",
                        "pt_BR": "Invisible",
                        "zh_Hans": "隐藏"
                      },
                      "value": "0"
                    },
                    {
                      "label": {
                        "en_US": "Visible",
                        "pt_BR": "Visible",
                        "zh_Hans": "可见"
                      },
                      "value": "1"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Update an existing document within a specified knowledge base by providing the document ID or path.",
                  "zh_Hans": "通过提供文档ID或路径，更新指定知识库中的现有文档。"
                },
                "llm": "Update doc in a knowledge base via ID/path."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "佐井",
                "label": {
                  "en_US": "Update Document",
                  "zh_Hans": "更新文档"
                },
                "name": "aliyuque_update_document"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The unique identifier of the knowledge base where the document resides.",
                    "zh_Hans": "文档所属知识库的ID。"
                  },
                  "label": {
                    "en_US": "Knowledge Base ID",
                    "zh_Hans": "知识库 ID"
                  },
                  "llm_description": "ID of the knowledge base holding the doc.",
                  "max": null,
                  "min": null,
                  "name": "book_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The unique identifier or the path of the document to be updated.",
                    "zh_Hans": "要更新的文档的唯一ID或路径。"
                  },
                  "label": {
                    "en_US": "Document ID or Path",
                    "zh_Hans": "文档 ID 或 路径"
                  },
                  "llm_description": "Doc's ID or path for update.",
                  "max": null,
                  "min": null,
                  "name": "id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The title of the document, defaults to 'Untitled' if not provided.",
                    "zh_Hans": "文档标题，默认为'无标题'如未提供。"
                  },
                  "label": {
                    "en_US": "Title",
                    "zh_Hans": "标题"
                  },
                  "llm_description": "Title of the document, defaults to 'Untitled'.",
                  "max": null,
                  "min": null,
                  "name": "title",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Format of the document content (markdown, HTML, Lake).",
                    "zh_Hans": "文档内容格式（markdown, HTML, Lake）。"
                  },
                  "label": {
                    "en_US": "Content Format",
                    "zh_Hans": "内容格式"
                  },
                  "llm_description": "Content format choices, markdown, HTML, Lake.",
                  "max": null,
                  "min": null,
                  "name": "format",
                  "options": [
                    {
                      "label": {
                        "en_US": "markdown",
                        "pt_BR": "markdown",
                        "zh_Hans": "markdown"
                      },
                      "value": "markdown"
                    },
                    {
                      "label": {
                        "en_US": "html",
                        "pt_BR": "html",
                        "zh_Hans": "html"
                      },
                      "value": "html"
                    },
                    {
                      "label": {
                        "en_US": "lake",
                        "pt_BR": "lake",
                        "zh_Hans": "lake"
                      },
                      "value": "lake"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The actual content of the document.",
                    "zh_Hans": "文档的实际内容。"
                  },
                  "label": {
                    "en_US": "Body Content",
                    "zh_Hans": "正文内容"
                  },
                  "llm_description": "Content of the document.",
                  "max": null,
                  "min": null,
                  "name": "body",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:10:36Z",
        "version_updated_at": "2025-02-17T07:10:36Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Models provide by Tencent LKEAP, such as deepseek-v3-0324, deepseek-r1.",
          "zh_Hans": "腾讯知识引擎大模型相关原子能力，如deepseek-v3-0324, deepseek-r1."
        },
        "category": "model",
        "created_at": "2025-04-10T14:32:25Z",
        "endpoint": {},
        "icon": "higgs-projects/packages/lkeap/_assets/icon_s_en.svg",
        "index_id": "higgs-projects___lkeap",
        "install_count": 536,
        "introduction": "### Overview\nLKEAP provides  APIs for large model inference, covering multiple modalities such as text, images, and videos. It supports the latest open-source LLM models like DeepSeek, as well as embedding and reranking models such as hunyuan. Configuration can be done via model names, API keys, and other parameters.\n\n### Configure\nInstall the LKEAP plugin, then configure it by entering your API Key. Get your API Key from [LKEAP](https://console.cloud.tencent.com/cam/capi) and save.\n<img src=\"./_assets/configure.png\" width=\"60%\" alt=\"配置界面\">\n\n\n### About LKEAP \nWebsite | [LKEAP](https://cloud.tencent.com/document/product/1772)\n\n### Contract\nrainsoft@163.com\n\n### Repository\nhttps://github.com/higgs-projects/higgs-lkeap",
        "label": {
          "en_US": "LKEAP",
          "zh_Hans": "腾讯知识引擎"
        },
        "latest_package_identifier": "higgs-projects/lkeap:0.0.2@d2bec04f7fff913b14cc856aa95b9ad0509cec332d155eeacccb8b63960cfda3",
        "latest_version": "0.0.2",
        "model": {
          "background": "#E5E7EB",
          "configurate_methods": [
            "predefined-model"
          ],
          "description": {
            "en_US": "Models provided by Tencent LKEAP.",
            "zh_Hans": "腾讯知识引擎原子能力 提供的模型。"
          },
          "help": {
            "title": {
              "en_US": "Get your API Key from LKEAP",
              "zh_Hans": "从 腾讯知识引擎 获取 API Key"
            },
            "url": {
              "en_US": "https://console.cloud.tencent.com/cam/capi"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.svg"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "LKEAP",
            "zh_Hans": "腾讯知识引擎"
          },
          "model_credential_schema": null,
          "models": [
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "deepseek-r1",
                "zh_Hans": "deepseek-r1"
              },
              "model": "deepseek-r1",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.6,
                  "help": {
                    "en_US": "Control the diversity and randomness of generated results. The smaller the value, the more rigorous it is; the larger the value, the more divergent it is.",
                    "zh_Hans": "控制生成结果的多样性和随机性。数值越小，越严谨；数值越大，越发散。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 0.7,
                  "min": 0.5,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "4",
                "output": "16",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "deepseek-v3-0324",
                "zh_Hans": "deepseek-v3-0324"
              },
              "model": "deepseek-v3-0324",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.6,
                  "help": {
                    "en_US": "Control the diversity and randomness of generated results. The smaller the value, the more rigorous it is; the larger the value, the more divergent it is.",
                    "zh_Hans": "控制生成结果的多样性和随机性。数值越小，越严谨；数值越大，越发散。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "2",
                "output": "8",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "deepseek-v3",
                "zh_Hans": "deepseek-v3"
              },
              "model": "deepseek-v3",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.6,
                  "help": {
                    "en_US": "Control the diversity and randomness of generated results. The smaller the value, the more rigorous it is; the larger the value, the more divergent it is.",
                    "zh_Hans": "控制生成结果的多样性和随机性。数值越小，越严谨；数值越大，越发散。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 4096,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 8192,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "2",
                "output": "8",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "lke-reranker-base"
              },
              "model": "lke-reranker-base",
              "model_properties": {
                "context_size": 4000
              },
              "model_type": "rerank",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "lke-text-embedding-v1"
              },
              "model": "lke-text-embedding-v1",
              "model_properties": {
                "context_size": 500,
                "max_chunks": 7
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": null
            }
          ],
          "position": {
            "llm": [
              "deepseek-v3-0324",
              "deepseek-v3",
              "deepseek-r1"
            ],
            "rerank": [
              "lke-reranker-base"
            ],
            "text_embedding": [
              "lke-text-embedding-v1"
            ]
          },
          "provider": "lkeap",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "Secret ID"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Secret ID",
                  "zh_Hans": "在此输入您的 Secret ID"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "secret_id"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Secret Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Secret Key",
                  "zh_Hans": "在此输入您的 Secret Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "secret_key"
              }
            ]
          },
          "supported_model_types": [
            "llm",
            "rerank",
            "text-embedding"
          ]
        },
        "name": "lkeap",
        "org": "higgs-projects",
        "plugin_id": "higgs-projects/lkeap",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/lkeap.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-15T12:23:25Z",
        "version_updated_at": "2025-04-15T12:23:25Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "CogView art",
          "pt_BR": "CogView art",
          "zh_Hans": "CogView 绘画"
        },
        "category": "tool",
        "created_at": "2024-12-04T04:51:28Z",
        "endpoint": {},
        "icon": "langgenius/packages/cogview/_assets/icon.png",
        "index_id": "langgenius___cogview",
        "install_count": 526,
        "introduction": "# CogView\n\n## Overview\n\nCogView is an AI model for text-to-image and text-to-video generation. It can create both images and videos based on textual descriptions provided by users. The model offers a variety of artistic styles and content generation options across both image and video formats.\n\n## Configuration\n\n### 1. Ensure that you are allowed to use the BigModel service\n> If you don't have an account, go to the [BigModel site](https://bigmodel.cn/) and follow their instruction to create an account.\n\nYou can get the API key from the [ZHIPU AI OPEN PLATFORM](https://bigmodel.cn/).\n\n### 2. Get CogView tools from Plugin Marketplace\nThe CogView tools could be found at the Plugin Marketplace, please install it.\n\n### 3. Setup the CogView API in the Dify Tool page\nOn the Dify navigation page, click `Tools > CogView > To Authorize` and fill the API Key.\n\n![](./_assets/cogview_1.PNG)\n\n### 4. Using the tool\nYou can use the CogView tool in the following application types.\n\n![](./_assets/cogview_2.png)\n\n#### Chatflow / Workflow applications\nBoth Chatflow and Workflow applications support adding a CogView tool node.\n\n#### Agent applications\nAdd the CogView tool in the Agent application, then enter online search instructions to call this tool.",
        "label": {
          "en_US": "CogView",
          "pt_BR": "CogView",
          "zh_Hans": "CogView 绘画"
        },
        "latest_package_identifier": "langgenius/cogview:0.0.2@17466097638bef32714535c068d454966974ddeacaf0621fe3c53dcfbebe6d25",
        "latest_version": "0.0.2",
        "model": {},
        "name": "cogview",
        "org": "langgenius",
        "plugin_id": "langgenius/cogview",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/cogview.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "image"
          },
          {
            "name": "productivity"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "ZhipuAI API key",
                "pt_BR": "ZhipuAI API key",
                "zh_Hans": "ZhipuAI API key"
              },
              "name": "zhipuai_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your ZhipuAI API key",
                "pt_BR": "Please input your ZhipuAI API key",
                "zh_Hans": "请输入你的 ZhipuAI API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "ZhipuAI base URL",
                "pt_BR": "ZhipuAI base URL",
                "zh_Hans": "ZhipuAI base URL"
              },
              "name": "zhipuai_base_url",
              "options": null,
              "placeholder": {
                "en_US": "Please input your ZhipuAI base URL",
                "pt_BR": "Please input your ZhipuAI base URL",
                "zh_Hans": "请输入你的 ZhipuAI base URL"
              },
              "required": false,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "ZhipuAI organization ID",
                "pt_BR": "ZhipuAI organization ID",
                "zh_Hans": "ZhipuAI organization ID"
              },
              "name": "zhipuai_organizaion_id",
              "options": null,
              "placeholder": {
                "en_US": "Please input your ZhipuAI organization ID",
                "pt_BR": "Please input your ZhipuAI organization ID",
                "zh_Hans": "请输入你的 ZhipuAI organization ID"
              },
              "required": false,
              "scope": null,
              "type": "text-input",
              "url": null
            }
          ],
          "identity": {
            "author": "Waffle",
            "description": {
              "en_US": "CogView art",
              "pt_BR": "CogView art",
              "zh_Hans": "CogView 绘画"
            },
            "icon": "icon.png",
            "label": {
              "en_US": "CogView",
              "pt_BR": "CogView",
              "zh_Hans": "CogView 绘画"
            },
            "name": "cogview",
            "tags": [
              "image",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Get the result of CogVideo tool generation.",
                  "zh_Hans": "根据 CogVideo 工具返回的 id 获取视频生成结果。"
                },
                "llm": "Get the result of CogVideo tool generation. The input is the id which is returned by the CogVideo tool. The output is the url of video and video cover image."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "hjlarry",
                "label": {
                  "en_US": "CogVideo Result",
                  "zh_Hans": "CogVideo 结果获取"
                },
                "name": "cogvideo_job"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The id returned by the CogVideo.",
                    "zh_Hans": "CogVideo 工具返回的 id。"
                  },
                  "label": {
                    "en_US": "id"
                  },
                  "llm_description": "The id returned by the cogvideo.",
                  "max": null,
                  "min": null,
                  "name": "id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "CogView 3 is a text to image tool",
                  "pt_BR": "CogView 3 is a text to image tool",
                  "zh_Hans": "CogView 3 是一个文本到图像的工具"
                },
                "llm": "CogView 3 is a tool used to generate images from text"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Waffle",
                "label": {
                  "en_US": "CogView 3",
                  "pt_BR": "CogView 3",
                  "zh_Hans": "CogView 3 绘画"
                },
                "name": "cogview3"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Image prompt, you can check the official documentation of CogView 3",
                    "pt_BR": "Image prompt, you can check the official documentation of CogView 3",
                    "zh_Hans": "图像提示词，您可以查看 CogView 3 的官方文档"
                  },
                  "label": {
                    "en_US": "Prompt",
                    "pt_BR": "Prompt",
                    "zh_Hans": "提示词"
                  },
                  "llm_description": "Image prompt of CogView 3, you should describe the image you want to generate as a list of words as possible as detailed",
                  "max": null,
                  "min": null,
                  "name": "prompt",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "square",
                  "form": "form",
                  "human_description": {
                    "en_US": "selecting the image size",
                    "pt_BR": "selecting the image size",
                    "zh_Hans": "选择图像大小"
                  },
                  "label": {
                    "en_US": "Image size",
                    "pt_BR": "Image size",
                    "zh_Hans": "图像大小"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "size",
                  "options": [
                    {
                      "label": {
                        "en_US": "Square_cogview_3(1024x1024)",
                        "pt_BR": "Square_cogview_3(1024x1024)",
                        "zh_Hans": "方_cogview_3(1024x1024)"
                      },
                      "value": "cogview_3"
                    },
                    {
                      "label": {
                        "en_US": "Square(1024x1024)",
                        "pt_BR": "Square(1024x1024)",
                        "zh_Hans": "方(1024x1024)"
                      },
                      "value": "square"
                    },
                    {
                      "label": {
                        "en_US": "Vertical(768x1344)",
                        "pt_BR": "Vertical(768x1344)",
                        "zh_Hans": "竖屏(768x1344)"
                      },
                      "value": "vertical_768"
                    },
                    {
                      "label": {
                        "en_US": "Vertical(864x1152)",
                        "pt_BR": "Vertical(864x1152)",
                        "zh_Hans": "竖屏(864x1152)"
                      },
                      "value": "vertical_864"
                    },
                    {
                      "label": {
                        "en_US": "Horizontal(1344x768)",
                        "pt_BR": "Horizontal(1344x768)",
                        "zh_Hans": "横屏(1344x768)"
                      },
                      "value": "horizontal_1344"
                    },
                    {
                      "label": {
                        "en_US": "Horizontal(1152x864)",
                        "pt_BR": "Horizontal(1152x864)",
                        "zh_Hans": "横屏(1152x864)"
                      },
                      "value": "horizontal_1152"
                    },
                    {
                      "label": {
                        "en_US": "Widescreen(1440x720)",
                        "pt_BR": "Widescreen(1440x720)",
                        "zh_Hans": "宽屏(1440x720)"
                      },
                      "value": "widescreen_1440"
                    },
                    {
                      "label": {
                        "en_US": "Tallscreen(720x1440)",
                        "pt_BR": "Tallscreen(720x1440)",
                        "zh_Hans": "高屏(720x1440)"
                      },
                      "value": "tallscreen_720"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 1,
                  "form": "form",
                  "human_description": {
                    "en_US": "selecting the number of images",
                    "pt_BR": "selecting the number of images",
                    "zh_Hans": "选择图像数量"
                  },
                  "label": {
                    "en_US": "Number of images",
                    "pt_BR": "Number of images",
                    "zh_Hans": "图像数量"
                  },
                  "llm_description": "",
                  "max": 1,
                  "min": 1,
                  "name": "n",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "standard",
                  "form": "form",
                  "human_description": {
                    "en_US": "selecting the image quality",
                    "pt_BR": "selecting the image quality",
                    "zh_Hans": "选择图像质量"
                  },
                  "label": {
                    "en_US": "Image quality",
                    "pt_BR": "Image quality",
                    "zh_Hans": "图像质量"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "quality",
                  "options": [
                    {
                      "label": {
                        "en_US": "Standard",
                        "pt_BR": "Standard",
                        "zh_Hans": "标准"
                      },
                      "value": "standard"
                    },
                    {
                      "label": {
                        "en_US": "HD",
                        "pt_BR": "HD",
                        "zh_Hans": "高清"
                      },
                      "value": "hd"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "vivid",
                  "form": "form",
                  "human_description": {
                    "en_US": "selecting the image style",
                    "pt_BR": "selecting the image style",
                    "zh_Hans": "选择图像风格"
                  },
                  "label": {
                    "en_US": "Image style",
                    "pt_BR": "Image style",
                    "zh_Hans": "图像风格"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "style",
                  "options": [
                    {
                      "label": {
                        "en_US": "Vivid",
                        "pt_BR": "Vivid",
                        "zh_Hans": "生动"
                      },
                      "value": "vivid"
                    },
                    {
                      "label": {
                        "en_US": "Natural",
                        "pt_BR": "Natural",
                        "zh_Hans": "自然"
                      },
                      "value": "natural"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Use the CogVideox model provided by ZhipuAI to generate videos based on user prompts and images.",
                  "zh_Hans": "使用智谱cogvideox模型，根据用户输入的提示词和图片，生成视频。"
                },
                "llm": "A tool for generating videos. The input is user's prompt or image url or both of them, the output is a task id. You can use another tool with this task id to check the status and get the video."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "hjlarry",
                "label": {
                  "en_US": "CogVideo",
                  "zh_Hans": "CogVideo 视频生成"
                },
                "name": "cogvideo"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The prompt text used to generate video.",
                    "zh_Hans": "用于生成视频的提示词。"
                  },
                  "label": {
                    "en_US": "prompt",
                    "zh_Hans": "提示词"
                  },
                  "llm_description": "The prompt text used to generate video. Optional.",
                  "max": null,
                  "min": null,
                  "name": "prompt",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The image url used to generate video.",
                    "zh_Hans": "输入一个图片链接，生成的视频将基于该图片和提示词。"
                  },
                  "label": {
                    "en_US": "image url",
                    "zh_Hans": "图片链接"
                  },
                  "llm_description": "The image url used to generate video. Optional.",
                  "max": null,
                  "min": null,
                  "name": "image_url",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:13:00Z",
        "version_updated_at": "2025-02-17T07:13:00Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "a tool to compress the multimodal files",
          "zh_Hans": "一个压缩多模态文件的工具"
        },
        "category": "tool",
        "created_at": "2025-03-19T18:45:15Z",
        "endpoint": {},
        "icon": "hjlarry/packages/compress/_assets/icon.svg",
        "index_id": "hjlarry___compress",
        "install_count": 513,
        "introduction": "# compress\n\n[![Version](https://img.shields.io/badge/version-0.0.1-blue.svg)](https://github.com/hjlarry/dify-plugin-compress)\n[![Repo](https://img.shields.io/badge/repo&issue-github-green.svg)](https://github.com/hjlarry/dify-plugin-compress)\n\nA tool to compress Image/Audio/Video files.\n\nWhen sending a video to the LLM, it extracts the key frames. So, why not compress the video beforehand? This would significantly lower both token and transfer costs.\n\nThis tool utilizes Pillow to compress image quality, effectively reducing image size. Additionally, it employs FFmpeg to adjust parameters, minimizing the size of video and audio files.\n![1](_assets/1.png)\n\nThe video has been compressed to just 1/20 of its original size.\n![2](_assets/2.png)\n\n\n",
        "label": {
          "en_US": "Compress",
          "zh_Hans": "压缩"
        },
        "latest_package_identifier": "hjlarry/compress:0.0.1@0f037cb2fb18989af63f7fd68cc03aae288a59158245fc6635386de2f0448127",
        "latest_version": "0.0.1",
        "model": {},
        "name": "compress",
        "org": "hjlarry",
        "plugin_id": "hjlarry/compress",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/compress.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {}
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "hjlarry",
            "description": {
              "en_US": "a tool to compress the multimodal files",
              "zh_Hans": "一个压缩多模态文件的工具"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Compress",
              "zh_Hans": "压缩"
            },
            "name": "compress",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "a tool to compress the image",
                  "zh_Hans": "一个压缩图片的工具"
                },
                "llm": "a tool to compress the image"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "hjlarry",
                "label": {
                  "en_US": "Image Compress",
                  "zh_Hans": "图片压缩"
                },
                "name": "image_compress"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "a tool to compress the image",
                    "zh_Hans": "一个压缩图片的工具"
                  },
                  "label": {
                    "en_US": "Image file",
                    "zh_Hans": "图片文件"
                  },
                  "llm_description": "a tool to compress the image",
                  "max": null,
                  "min": null,
                  "name": "image_file",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "file"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The target size of the image (MB)",
                    "zh_Hans": "目标大小 (MB)"
                  },
                  "label": {
                    "en_US": "Target size (MB)",
                    "zh_Hans": "目标大小 (MB)"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "target_size",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "a tool to compress the video",
                  "zh_Hans": "一个压缩视频的工具"
                },
                "llm": "a tool to compress the video"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "hjlarry",
                "label": {
                  "en_US": "Video Compress",
                  "zh_Hans": "视频压缩"
                },
                "name": "video_compress"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "a tool to compress the video",
                    "zh_Hans": "一个压缩视频的工具"
                  },
                  "label": {
                    "en_US": "Video file",
                    "zh_Hans": "视频文件"
                  },
                  "llm_description": "a tool to compress the video",
                  "max": null,
                  "min": null,
                  "name": "video_file",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "file"
                },
                {
                  "auto_generate": null,
                  "default": "720",
                  "form": "form",
                  "human_description": {
                    "en_US": "The resolution of the video, more resolution means more size. If the video is larger than the set resolution, it will be scaled down proportionally",
                    "zh_Hans": "视频的分辨率，分辨率越高，视频文件越大。大于设定的分辨率，视频会被等比例的缩放"
                  },
                  "label": {
                    "en_US": "Resolution",
                    "zh_Hans": "分辨率"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "target_height",
                  "options": [
                    {
                      "label": {
                        "en_US": "480p",
                        "zh_Hans": "480p"
                      },
                      "value": "480"
                    },
                    {
                      "label": {
                        "en_US": "720p",
                        "zh_Hans": "720p"
                      },
                      "value": "720"
                    },
                    {
                      "label": {
                        "en_US": "1080p",
                        "zh_Hans": "1080p"
                      },
                      "value": "1080"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 1,
                  "form": "form",
                  "human_description": {
                    "en_US": "The FPS of the video, more FPS means more size",
                    "zh_Hans": "视频的帧率，帧率越高，视频文件越大"
                  },
                  "label": {
                    "en_US": "FPS",
                    "zh_Hans": "帧率"
                  },
                  "llm_description": "",
                  "max": 60,
                  "min": 1,
                  "name": "fps",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 35,
                  "form": "form",
                  "human_description": {
                    "en_US": "The compression level of the video, 0 means no compression, 51 means maximum compression",
                    "zh_Hans": "视频的压缩级别，0表示不压缩，51表示最大压缩"
                  },
                  "label": {
                    "en_US": "CRF",
                    "zh_Hans": "压缩率"
                  },
                  "llm_description": "",
                  "max": 51,
                  "min": 0,
                  "name": "crf",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "slower",
                  "form": "form",
                  "human_description": {
                    "en_US": "The preset of the video, slower means more compression but slower encoding speed",
                    "zh_Hans": "视频的预设，slower表示更多压缩但编码速度更慢"
                  },
                  "label": {
                    "en_US": "Preset",
                    "zh_Hans": "预设"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "preset",
                  "options": [
                    {
                      "label": {
                        "en_US": "slower",
                        "zh_Hans": "慢"
                      },
                      "value": "slower"
                    },
                    {
                      "label": {
                        "en_US": "medium",
                        "zh_Hans": "中"
                      },
                      "value": "medium"
                    },
                    {
                      "label": {
                        "en_US": "faster",
                        "zh_Hans": "快"
                      },
                      "value": "faster"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "a tool to compress the audio",
                  "zh_Hans": "一个压缩音频的工具"
                },
                "llm": "a tool to compress the audio"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "hjlarry",
                "label": {
                  "en_US": "Audio Compress",
                  "zh_Hans": "音频压缩"
                },
                "name": "audio_compress"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "a tool to compress the audio",
                    "zh_Hans": "一个压缩音频的工具"
                  },
                  "label": {
                    "en_US": "Audio file",
                    "zh_Hans": "音频文件"
                  },
                  "llm_description": "a tool to compress the audio",
                  "max": null,
                  "min": null,
                  "name": "audio_file",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "file"
                },
                {
                  "auto_generate": null,
                  "default": "16k",
                  "form": "form",
                  "human_description": {
                    "en_US": "The bitrate of the audio, more bitrate means more size",
                    "zh_Hans": "音频的比特率，比特率越高，音频文件越大"
                  },
                  "label": {
                    "en_US": "Bitrate",
                    "zh_Hans": "比特率"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "bitrate",
                  "options": [
                    {
                      "label": {
                        "en_US": "8k",
                        "zh_Hans": "8k"
                      },
                      "value": "8k"
                    },
                    {
                      "label": {
                        "en_US": "16k",
                        "zh_Hans": "16k"
                      },
                      "value": "16k"
                    },
                    {
                      "label": {
                        "en_US": "32k",
                        "zh_Hans": "32k"
                      },
                      "value": "32k"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "8000",
                  "form": "form",
                  "human_description": {
                    "en_US": "The sample rate of the audio, more sample rate means more size",
                    "zh_Hans": "音频的采样率，采样率越高，音频文件越大"
                  },
                  "label": {
                    "en_US": "Sample rate",
                    "zh_Hans": "采样率"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "sample_rate",
                  "options": [
                    {
                      "label": {
                        "en_US": "8000Hz",
                        "zh_Hans": "8000Hz"
                      },
                      "value": "8000"
                    },
                    {
                      "label": {
                        "en_US": "16000Hz",
                        "zh_Hans": "16000Hz"
                      },
                      "value": "16000"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 4,
                  "form": "form",
                  "human_description": {
                    "en_US": "The compression level of the audio, 0 means no compression, 9 means maximum compression",
                    "zh_Hans": "音频的压缩级别，0表示不压缩，9表示最大压缩"
                  },
                  "label": {
                    "en_US": "Compression level",
                    "zh_Hans": "压缩级别"
                  },
                  "llm_description": "",
                  "max": 9,
                  "min": 0,
                  "name": "compression_level",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-19T18:45:27Z",
        "version_updated_at": "2025-03-19T18:45:27Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Lark base, requires the following permissions: bitable:app.\n",
          "zh_Hans": "Lark 多维表格，需要开通以下权限: bitable:app。\n"
        },
        "category": "tool",
        "created_at": "2025-02-26T10:44:45Z",
        "endpoint": {},
        "icon": "langgenius/packages/lark_base/_assets/icon.png",
        "index_id": "langgenius___lark_base",
        "install_count": 512,
        "introduction": "",
        "label": {
          "en_US": "Lark Base",
          "zh_Hans": "Lark 多维表格"
        },
        "latest_package_identifier": "langgenius/lark_base:0.0.1@45fdeb8a3d5fe551642f2d36aeb9a7c40a7b882b01da78cc98392d7d8954e18a",
        "latest_version": "0.0.1",
        "model": {},
        "name": "lark_base",
        "org": "langgenius",
        "plugin_id": "langgenius/lark_base",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/lark_base.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "social"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "APP ID"
              },
              "name": "app_id",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Lark app id",
                "zh_Hans": "请输入你的 Lark app id"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": "https://open.larksuite.com/app"
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "APP Secret"
              },
              "name": "app_secret",
              "options": null,
              "placeholder": {
                "en_US": "Please input your app secret",
                "zh_Hans": "请输入你的 Lark app secret"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            }
          ],
          "identity": {
            "author": "Doug Lea",
            "description": {
              "en_US": "Lark base, requires the following permissions: bitable:app.\n",
              "zh_Hans": "Lark 多维表格，需要开通以下权限: bitable:app。\n"
            },
            "icon": "icon.png",
            "label": {
              "en_US": "Lark Base",
              "zh_Hans": "Lark 多维表格"
            },
            "name": "lark_base",
            "tags": [
              "social",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Batch Delete Data Tables from Multidimensional Table",
                  "zh_Hans": "批量删除多维表格中的数据表"
                },
                "llm": "A tool for batch deleting data tables from a multidimensional table. (批量删除多维表格中的数据表)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Delete Tables",
                  "zh_Hans": "删除数据表"
                },
                "name": "delete_tables"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for the multidimensional table, supports inputting document URL.",
                    "zh_Hans": "多维表格的唯一标识符，支持输入文档 URL。"
                  },
                  "label": {
                    "en_US": "app_token",
                    "zh_Hans": "app_token"
                  },
                  "llm_description": "多维表格的唯一标识符，支持输入文档 URL。",
                  "max": null,
                  "min": null,
                  "name": "app_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "IDs of the tables to be deleted. Each operation supports deleting up to 50 tables. Example: [\"tbl1TkhyTWDkSoZ3\"]. Ensure that either table_ids or table_names is not empty.\n",
                    "zh_Hans": "待删除的数据表的 ID，每次操作最多支持删除 50 个数据表。示例值：[\"tbl1TkhyTWDkSoZ3\"]。请确保 table_ids 和 table_names 至少有一个不为空。"
                  },
                  "label": {
                    "en_US": "Table IDs",
                    "zh_Hans": "数据表 ID"
                  },
                  "llm_description": "待删除的数据表的 ID，每次操作最多支持删除 50 个数据表。示例值：[\"tbl1TkhyTWDkSoZ3\"]。请确保 table_ids 和 table_names 至少有一个不为空。",
                  "max": null,
                  "min": null,
                  "name": "table_ids",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Names of the tables to be deleted. Each operation supports deleting up to 50 tables. Example: [\"Table1\", \"Table2\"]. Ensure that either table_names or table_ids is not empty.\n",
                    "zh_Hans": "待删除的数据表的名称，每次操作最多支持删除 50 个数据表。示例值：[\"数据表1\", \"数据表2\"]。请确保 table_names 和 table_ids 至少有一个不为空。"
                  },
                  "label": {
                    "en_US": "Table Names",
                    "zh_Hans": "数据表名称"
                  },
                  "llm_description": "待删除的数据表的名称，每次操作最多支持删除 50 个数据表。示例值：[\"数据表1\", \"数据表2\"]。请确保 table_names 和 table_ids 至少有一个不为空。",
                  "max": null,
                  "min": null,
                  "name": "table_names",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get All Data Tables under Multidimensional Table",
                  "zh_Hans": "获取多维表格下的所有数据表"
                },
                "llm": "A tool for getting all data tables under a multidimensional table. (获取多维表格下的所有数据表)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "List Tables",
                  "zh_Hans": "列出数据表"
                },
                "name": "list_tables"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for the multidimensional table, supports inputting document URL.",
                    "zh_Hans": "多维表格的唯一标识符，支持输入文档 URL。"
                  },
                  "label": {
                    "en_US": "app_token",
                    "zh_Hans": "app_token"
                  },
                  "llm_description": "多维表格的唯一标识符，支持输入文档 URL。",
                  "max": null,
                  "min": null,
                  "name": "app_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 20,
                  "form": "form",
                  "human_description": {
                    "en_US": "Page size, default value: 20, maximum value: 100.\n",
                    "zh_Hans": "分页大小，默认值：20，最大值：100。"
                  },
                  "label": {
                    "en_US": "page_size",
                    "zh_Hans": "分页大小"
                  },
                  "llm_description": "分页大小，默认值：20，最大值：100。",
                  "max": null,
                  "min": null,
                  "name": "page_size",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Page token, leave empty for the first request to start from the beginning; a new page_token will be returned if there are more items in the paginated query results, which can be used for the next traversal. Example value: \"tblsRc9GRRXKqhvW\".\n",
                    "zh_Hans": "分页标记，第一次请求不填，表示从头开始遍历；分页查询结果还有更多项时会同时返回新的 page_token，下次遍历可采用该 page_token 获取查询结果。示例值：\"tblsRc9GRRXKqhvW\"。"
                  },
                  "label": {
                    "en_US": "page_token",
                    "zh_Hans": "分页标记"
                  },
                  "llm_description": "分页标记，第一次请求不填，表示从头开始遍历；分页查询结果还有更多项时会同时返回新的 page_token，下次遍历可采用该 page_token 获取查询结果。示例值：\"tblsRc9GRRXKqhvW\"。",
                  "max": null,
                  "min": null,
                  "name": "page_token",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Create Multidimensional Table in Specified Directory",
                  "zh_Hans": "在指定目录下创建多维表格"
                },
                "llm": "A tool for creating a multidimensional table in a specified directory. (在指定目录下创建多维表格)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Create Base",
                  "zh_Hans": "创建多维表格"
                },
                "name": "create_base"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Name of the multidimensional table App. Example value: \"A new multidimensional table\".\n",
                    "zh_Hans": "多维表格 App 名字，示例值：\"一篇新的多维表格\"。"
                  },
                  "label": {
                    "en_US": "name",
                    "zh_Hans": "多维表格 App 名字"
                  },
                  "llm_description": "多维表格 App 名字，示例值：\"一篇新的多维表格\"。",
                  "max": null,
                  "min": null,
                  "name": "name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Folder where the multidimensional table App belongs. Default is empty, meaning the table will be created in the root directory of the cloud space. Example values: Lf8uf6BoAlWkUfdGtpMjUV0PpZd or https://lark-japan.jp.larksuite.com/drive/folder/Lf8uf6BoAlWkUfdGtpMjUV0PpZd.\nThe folder_token must be an existing folder and supports inputting folder token or folder URL.\n",
                    "zh_Hans": "多维表格 App 归属文件夹。默认为空，表示多维表格将被创建在云空间根目录。示例值: Lf8uf6BoAlWkUfdGtpMjUV0PpZd 或者 https://lark-japan.jp.larksuite.com/drive/folder/Lf8uf6BoAlWkUfdGtpMjUV0PpZd。\nfolder_token 必须是已存在的文件夹，支持输入文件夹 token 或者文件夹 URL。\n"
                  },
                  "label": {
                    "en_US": "folder_token",
                    "zh_Hans": "多维表格 App 归属文件夹"
                  },
                  "llm_description": "多维表格 App 归属文件夹。默认为空，表示多维表格将被创建在云空间根目录。示例值: Lf8uf6BoAlWkUfdGtpMjUV0PpZd 或者 https://lark-japan.jp.larksuite.com/drive/folder/Lf8uf6BoAlWkUfdGtpMjUV0PpZd。\nfolder_token 必须是已存在的文件夹，支持输入文件夹 token 或者文件夹 URL。\n",
                  "max": null,
                  "min": null,
                  "name": "folder_token",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Add Multiple Records to Multidimensional Table",
                  "zh_Hans": "在多维表格数据表中新增多条记录"
                },
                "llm": "A tool for adding multiple records to a multidimensional table. (在多维表格数据表中新增多条记录)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Add Records",
                  "zh_Hans": "新增多条记录"
                },
                "name": "add_records"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for the multidimensional table, supports inputting document URL.",
                    "zh_Hans": "多维表格的唯一标识符，支持输入文档 URL。"
                  },
                  "label": {
                    "en_US": "app_token",
                    "zh_Hans": "app_token"
                  },
                  "llm_description": "多维表格的唯一标识符，支持输入文档 URL。",
                  "max": null,
                  "min": null,
                  "name": "app_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for the multidimensional table data, either table_id or table_name must be provided, cannot be empty simultaneously.",
                    "zh_Hans": "多维表格数据表的唯一标识符，table_id 和 table_name 至少需要提供一个，不能同时为空。"
                  },
                  "label": {
                    "en_US": "table_id",
                    "zh_Hans": "table_id"
                  },
                  "llm_description": "多维表格数据表的唯一标识符，table_id 和 table_name 至少需要提供一个，不能同时为空。",
                  "max": null,
                  "min": null,
                  "name": "table_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Name of the multidimensional table data, either table_name or table_id must be provided, cannot be empty simultaneously.",
                    "zh_Hans": "多维表格数据表的名称，table_name 和 table_id 至少需要提供一个，不能同时为空。"
                  },
                  "label": {
                    "en_US": "table_name",
                    "zh_Hans": "table_name"
                  },
                  "llm_description": "多维表格数据表的名称，table_name 和 table_id 至少需要提供一个，不能同时为空。",
                  "max": null,
                  "min": null,
                  "name": "table_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "List of records to be added in this request. Example value: [{\"multi-line-text\":\"text content\",\"single_select\":\"option 1\",\"date\":1674206443000}]\nFor supported field types, refer to the integration guide (https://open.larkoffice.com/document/server-docs/docs/bitable-v1/notification). For data structures of different field types, refer to the data structure overview (https://open.larkoffice.com/document/server-docs/docs/bitable-v1/bitable-structure).\n",
                    "zh_Hans": "本次请求将要新增的记录列表，示例值：[{\"多行文本\":\"文本内容\",\"单选\":\"选项 1\",\"日期\":1674206443000}]。\n当前接口支持的字段类型请参考接入指南(https://open.larkoffice.com/document/server-docs/docs/bitable-v1/notification)，不同类型字段的数据结构请参考数据结构概述(https://open.larkoffice.com/document/server-docs/docs/bitable-v1/bitable-structure)。\n"
                  },
                  "label": {
                    "en_US": "records",
                    "zh_Hans": "记录列表"
                  },
                  "llm_description": "本次请求将要新增的记录列表，示例值：[{\"多行文本\":\"文本内容\",\"单选\":\"选项 1\",\"日期\":1674206443000}]。\n当前接口支持的字段类型请参考接入指南(https://open.larkoffice.com/document/server-docs/docs/bitable-v1/notification)，不同类型字段的数据结构请参考数据结构概述(https://open.larkoffice.com/document/server-docs/docs/bitable-v1/bitable-structure)。\n",
                  "max": null,
                  "min": null,
                  "name": "records",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "open_id",
                  "form": "form",
                  "human_description": {
                    "en_US": "User ID type, optional values are open_id, union_id, user_id, with a default value of open_id.",
                    "zh_Hans": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。"
                  },
                  "label": {
                    "en_US": "user_id_type",
                    "zh_Hans": "用户 ID 类型"
                  },
                  "llm_description": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。",
                  "max": null,
                  "min": null,
                  "name": "user_id_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "open_id",
                        "zh_Hans": "open_id"
                      },
                      "value": "open_id"
                    },
                    {
                      "label": {
                        "en_US": "union_id",
                        "zh_Hans": "union_id"
                      },
                      "value": "union_id"
                    },
                    {
                      "label": {
                        "en_US": "user_id",
                        "zh_Hans": "user_id"
                      },
                      "value": "user_id"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Query records in a multidimensional table, up to 500 rows per query.",
                  "zh_Hans": "查询多维表格数据表中的记录，单次最多查询 500 行记录。"
                },
                "llm": "A tool for querying records in a multidimensional table, up to 500 rows per query. (查询多维表格数据表中的记录，单次最多查询 500 行记录)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Search Records",
                  "zh_Hans": "查询记录"
                },
                "name": "search_records"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for the multidimensional table, supports inputting document URL.",
                    "zh_Hans": "多维表格的唯一标识符，支持输入文档 URL。"
                  },
                  "label": {
                    "en_US": "app_token",
                    "zh_Hans": "app_token"
                  },
                  "llm_description": "多维表格的唯一标识符，支持输入文档 URL。",
                  "max": null,
                  "min": null,
                  "name": "app_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for the multidimensional table data, either table_id or table_name must be provided, cannot be empty simultaneously.",
                    "zh_Hans": "多维表格数据表的唯一标识符，table_id 和 table_name 至少需要提供一个，不能同时为空。"
                  },
                  "label": {
                    "en_US": "table_id",
                    "zh_Hans": "table_id"
                  },
                  "llm_description": "多维表格数据表的唯一标识符，table_id 和 table_name 至少需要提供一个，不能同时为空。",
                  "max": null,
                  "min": null,
                  "name": "table_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Name of the multidimensional table data, either table_name or table_id must be provided, cannot be empty simultaneously.",
                    "zh_Hans": "多维表格数据表的名称，table_name 和 table_id 至少需要提供一个，不能同时为空。"
                  },
                  "label": {
                    "en_US": "table_name",
                    "zh_Hans": "table_name"
                  },
                  "llm_description": "多维表格数据表的名称，table_name 和 table_id 至少需要提供一个，不能同时为空。",
                  "max": null,
                  "min": null,
                  "name": "table_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for a view in a multidimensional table. It can be found in the URL's query parameter with the key 'view'. For example: https://lark-japan.jp.larksuite.com/base/XXX0bfYEraW5OWsbhcFjEqj6pxh?table=tbl5I6jqwz8wBRMv&view=vewW5zXVEU.\n",
                    "zh_Hans": "多维表格中视图的唯一标识，可在多维表格的 URL 地址栏中找到，query 参数中 key 为 view 的部分。例如：https://lark-japan.jp.larksuite.com/base/XXX0bfYEraW5OWsbhcFjEqj6pxh?table=tbl5I6jqwz8wBRMv&view=vewW5zXVEU。"
                  },
                  "label": {
                    "en_US": "view_id",
                    "zh_Hans": "视图唯一标识"
                  },
                  "llm_description": "多维表格中视图的唯一标识，可在多维表格的 URL 地址栏中找到，query 参数中 key 为 view 的部分。例如：https://lark-japan.jp.larksuite.com/base/XXX0bfYEraW5OWsbhcFjEqj6pxh?table=tbl5I6jqwz8wBRMv&view=vewW5zXVEU。",
                  "max": null,
                  "min": null,
                  "name": "view_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Field names to specify which fields to include in the returned records. Example value: [\"Field1\", \"Field2\"].\n",
                    "zh_Hans": "字段名称，用于指定本次查询返回记录中包含的字段。示例值：[\"字段1\",\"字段2\"]。"
                  },
                  "label": {
                    "en_US": "field_names",
                    "zh_Hans": "字段名称"
                  },
                  "llm_description": "字段名称，用于指定本次查询返回记录中包含的字段。示例值：[\"字段1\",\"字段2\"]。",
                  "max": null,
                  "min": null,
                  "name": "field_names",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sorting conditions, for example: [{\"field_name\":\"Multiline Text\",\"desc\":true}].\n",
                    "zh_Hans": "排序条件，例如：[{\"field_name\":\"多行文本\",\"desc\":true}]。"
                  },
                  "label": {
                    "en_US": "sort",
                    "zh_Hans": "排序条件"
                  },
                  "llm_description": "排序条件，例如：[{\"field_name\":\"多行文本\",\"desc\":true}]。",
                  "max": null,
                  "min": null,
                  "name": "sort",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Object containing filter information. For details on how to fill in the filter, refer to the record filter parameter guide (https://open.larkoffice.com/document/uAjLw4CM/ukTMukTMukTM/reference/bitable-v1/app-table-record/record-filter-guide).",
                    "zh_Hans": "包含条件筛选信息的对象。了解如何填写 filter，参考记录筛选参数填写指南(https://open.larkoffice.com/document/uAjLw4CM/ukTMukTMukTM/reference/bitable-v1/app-table-record/record-filter-guide)。"
                  },
                  "label": {
                    "en_US": "filter",
                    "zh_Hans": "筛选条件"
                  },
                  "llm_description": "包含条件筛选信息的对象。了解如何填写 filter，参考记录筛选参数填写指南(https://open.larkoffice.com/document/uAjLw4CM/ukTMukTMukTM/reference/bitable-v1/app-table-record/record-filter-guide)。",
                  "max": null,
                  "min": null,
                  "name": "filter",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to return automatically calculated fields. Default is false, meaning they are not returned.",
                    "zh_Hans": "是否返回自动计算的字段。默认为 false，表示不返回。"
                  },
                  "label": {
                    "en_US": "automatic_fields",
                    "zh_Hans": "automatic_fields"
                  },
                  "llm_description": "是否返回自动计算的字段。默认为 false，表示不返回。",
                  "max": null,
                  "min": null,
                  "name": "automatic_fields",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": "open_id",
                  "form": "form",
                  "human_description": {
                    "en_US": "User ID type, optional values are open_id, union_id, user_id, with a default value of open_id.",
                    "zh_Hans": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。"
                  },
                  "label": {
                    "en_US": "user_id_type",
                    "zh_Hans": "用户 ID 类型"
                  },
                  "llm_description": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。",
                  "max": null,
                  "min": null,
                  "name": "user_id_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "open_id",
                        "zh_Hans": "open_id"
                      },
                      "value": "open_id"
                    },
                    {
                      "label": {
                        "en_US": "union_id",
                        "zh_Hans": "union_id"
                      },
                      "value": "union_id"
                    },
                    {
                      "label": {
                        "en_US": "user_id",
                        "zh_Hans": "user_id"
                      },
                      "value": "user_id"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 20,
                  "form": "form",
                  "human_description": {
                    "en_US": "Page size, default value: 20, maximum value: 500.\n",
                    "zh_Hans": "分页大小，默认值：20，最大值：500。"
                  },
                  "label": {
                    "en_US": "page_size",
                    "zh_Hans": "分页大小"
                  },
                  "llm_description": "分页大小，默认值：20，最大值：500。",
                  "max": null,
                  "min": null,
                  "name": "page_size",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Page token, leave empty for the first request to start from the beginning; a new page_token will be returned if there are more items in the paginated query results, which can be used for the next traversal. Example value: \"tblsRc9GRRXKqhvW\".\n",
                    "zh_Hans": "分页标记，第一次请求不填，表示从头开始遍历；分页查询结果还有更多项时会同时返回新的 page_token，下次遍历可采用该 page_token 获取查询结果。示例值：\"tblsRc9GRRXKqhvW\"。"
                  },
                  "label": {
                    "en_US": "page_token",
                    "zh_Hans": "分页标记"
                  },
                  "llm_description": "分页标记，第一次请求不填，表示从头开始遍历；分页查询结果还有更多项时会同时返回新的 page_token，下次遍历可采用该 page_token 获取查询结果。示例值：\"tblsRc9GRRXKqhvW\"。",
                  "max": null,
                  "min": null,
                  "name": "page_token",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Delete Multiple Records from Multidimensional Table",
                  "zh_Hans": "删除多维表格数据表中的多条记录"
                },
                "llm": "A tool for deleting multiple records from a multidimensional table. (删除多维表格数据表中的多条记录)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Delete Records",
                  "zh_Hans": "删除多条记录"
                },
                "name": "delete_records"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for the multidimensional table, supports inputting document URL.",
                    "zh_Hans": "多维表格的唯一标识符，支持输入文档 URL。"
                  },
                  "label": {
                    "en_US": "app_token",
                    "zh_Hans": "app_token"
                  },
                  "llm_description": "多维表格的唯一标识符，支持输入文档 URL。",
                  "max": null,
                  "min": null,
                  "name": "app_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for the multidimensional table data, either table_id or table_name must be provided, cannot be empty simultaneously.",
                    "zh_Hans": "多维表格数据表的唯一标识符，table_id 和 table_name 至少需要提供一个，不能同时为空。"
                  },
                  "label": {
                    "en_US": "table_id",
                    "zh_Hans": "table_id"
                  },
                  "llm_description": "多维表格数据表的唯一标识符，table_id 和 table_name 至少需要提供一个，不能同时为空。",
                  "max": null,
                  "min": null,
                  "name": "table_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Name of the multidimensional table data, either table_name or table_id must be provided, cannot be empty simultaneously.",
                    "zh_Hans": "多维表格数据表的名称，table_name 和 table_id 至少需要提供一个，不能同时为空。"
                  },
                  "label": {
                    "en_US": "table_name",
                    "zh_Hans": "table_name"
                  },
                  "llm_description": "多维表格数据表的名称，table_name 和 table_id 至少需要提供一个，不能同时为空。",
                  "max": null,
                  "min": null,
                  "name": "table_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "List of IDs for the records to be deleted, example value: [\"recwNXzPQv\"].\n",
                    "zh_Hans": "删除的多条记录 ID 列表，示例值：[\"recwNXzPQv\"]。"
                  },
                  "label": {
                    "en_US": "Record IDs",
                    "zh_Hans": "记录 ID 列表"
                  },
                  "llm_description": "删除的多条记录 ID 列表，示例值：[\"recwNXzPQv\"]。",
                  "max": null,
                  "min": null,
                  "name": "record_ids",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "open_id",
                  "form": "form",
                  "human_description": {
                    "en_US": "User ID type, optional values are open_id, union_id, user_id, with a default value of open_id.",
                    "zh_Hans": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。"
                  },
                  "label": {
                    "en_US": "user_id_type",
                    "zh_Hans": "用户 ID 类型"
                  },
                  "llm_description": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。",
                  "max": null,
                  "min": null,
                  "name": "user_id_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "open_id",
                        "zh_Hans": "open_id"
                      },
                      "value": "open_id"
                    },
                    {
                      "label": {
                        "en_US": "union_id",
                        "zh_Hans": "union_id"
                      },
                      "value": "union_id"
                    },
                    {
                      "label": {
                        "en_US": "user_id",
                        "zh_Hans": "user_id"
                      },
                      "value": "user_id"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Add a Data Table to Multidimensional Table",
                  "zh_Hans": "在多维表格中新增一个数据表"
                },
                "llm": "A tool for adding a data table to a multidimensional table. (在多维表格中新增一个数据表)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Create Table",
                  "zh_Hans": "新增数据表"
                },
                "name": "create_table"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for the multidimensional table, supports inputting document URL.",
                    "zh_Hans": "多维表格的唯一标识符，支持输入文档 URL。"
                  },
                  "label": {
                    "en_US": "app_token",
                    "zh_Hans": "app_token"
                  },
                  "llm_description": "多维表格的唯一标识符，支持输入文档 URL。",
                  "max": null,
                  "min": null,
                  "name": "app_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The name of the data table, length range: 1 character to 100 characters.\n",
                    "zh_Hans": "数据表名称，长度范围：1 字符 ～ 100 字符。"
                  },
                  "label": {
                    "en_US": "Table Name",
                    "zh_Hans": "数据表名称"
                  },
                  "llm_description": "数据表名称，长度范围：1 字符 ～ 100 字符。",
                  "max": null,
                  "min": null,
                  "name": "table_name",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The name of the default table view, defaults to \"Table\" if not filled.",
                    "zh_Hans": "默认表格视图的名称，不填则默认为\"表格\"。"
                  },
                  "label": {
                    "en_US": "Default View Name",
                    "zh_Hans": "默认表格视图的名称"
                  },
                  "llm_description": "默认表格视图的名称，不填则默认为\"表格\"。",
                  "max": null,
                  "min": null,
                  "name": "default_view_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Initial fields of the data table, format: [ { \"field_name\": \"Multi-line Text\",\"type\": 1 },{ \"field_name\": \"Number\",\"type\": 2 },{ \"field_name\": \"Single Select\",\"type\": 3 },{ \"field_name\": \"Multiple Select\",\"type\": 4 },{ \"field_name\": \"Date\",\"type\": 5 } ]. For field details, refer to: https://open.larkoffice.com/document/server-docs/docs/bitable-v1/app-table-field/guide\n",
                    "zh_Hans": "数据表的初始字段，格式为：[{\"field_name\":\"多行文本\",\"type\":1},{\"field_name\":\"数字\",\"type\":2},{\"field_name\":\"单选\",\"type\":3},{\"field_name\":\"多选\",\"type\":4},{\"field_name\":\"日期\",\"type\":5}]。字段详情参考：https://open.larkoffice.com/document/server-docs/docs/bitable-v1/app-table-field/guide"
                  },
                  "label": {
                    "en_US": "Initial Fields",
                    "zh_Hans": "初始字段"
                  },
                  "llm_description": "数据表的初始字段，格式为：[{\"field_name\":\"多行文本\",\"type\":1},{\"field_name\":\"数字\",\"type\":2},{\"field_name\":\"单选\",\"type\":3},{\"field_name\":\"多选\",\"type\":4},{\"field_name\":\"日期\",\"type\":5}]。字段详情参考：https://open.larkoffice.com/document/server-docs/docs/bitable-v1/app-table-field/guide",
                  "max": null,
                  "min": null,
                  "name": "fields",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Batch Retrieve Records from Multidimensional Table",
                  "zh_Hans": "批量获取多维表格数据表中的记录信息"
                },
                "llm": "A tool for batch retrieving records from a multidimensional table, supporting up to 100 records per call. (批量获取多维表格数据表中的记录信息，单次调用最多支持查询 100 条记录)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Read Records",
                  "zh_Hans": "批量获取记录"
                },
                "name": "read_records"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for the multidimensional table, supports inputting document URL.",
                    "zh_Hans": "多维表格的唯一标识符，支持输入文档 URL。"
                  },
                  "label": {
                    "en_US": "app_token",
                    "zh_Hans": "app_token"
                  },
                  "llm_description": "多维表格的唯一标识符，支持输入文档 URL。",
                  "max": null,
                  "min": null,
                  "name": "app_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for the multidimensional table data, either table_id or table_name must be provided, cannot be empty simultaneously.",
                    "zh_Hans": "多维表格数据表的唯一标识符，table_id 和 table_name 至少需要提供一个，不能同时为空。"
                  },
                  "label": {
                    "en_US": "table_id",
                    "zh_Hans": "table_id"
                  },
                  "llm_description": "多维表格数据表的唯一标识符，table_id 和 table_name 至少需要提供一个，不能同时为空。",
                  "max": null,
                  "min": null,
                  "name": "table_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Name of the multidimensional table data, either table_name or table_id must be provided, cannot be empty simultaneously.",
                    "zh_Hans": "多维表格数据表的名称，table_name 和 table_id 至少需要提供一个，不能同时为空。"
                  },
                  "label": {
                    "en_US": "table_name",
                    "zh_Hans": "table_name"
                  },
                  "llm_description": "多维表格数据表的名称，table_name 和 table_id 至少需要提供一个，不能同时为空。",
                  "max": null,
                  "min": null,
                  "name": "table_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "List of record IDs, which can be obtained by calling the \"Query Records API\".",
                    "zh_Hans": "记录 ID 列表，可以通过调用\"查询记录接口\"获取。"
                  },
                  "label": {
                    "en_US": "record_ids",
                    "zh_Hans": "记录 ID 列表"
                  },
                  "llm_description": "记录 ID 列表，可以通过调用\"查询记录接口\"获取。",
                  "max": null,
                  "min": null,
                  "name": "record_ids",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "open_id",
                  "form": "form",
                  "human_description": {
                    "en_US": "User ID type, optional values are open_id, union_id, user_id, with a default value of open_id.",
                    "zh_Hans": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。"
                  },
                  "label": {
                    "en_US": "user_id_type",
                    "zh_Hans": "用户 ID 类型"
                  },
                  "llm_description": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。",
                  "max": null,
                  "min": null,
                  "name": "user_id_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "open_id",
                        "zh_Hans": "open_id"
                      },
                      "value": "open_id"
                    },
                    {
                      "label": {
                        "en_US": "union_id",
                        "zh_Hans": "union_id"
                      },
                      "value": "union_id"
                    },
                    {
                      "label": {
                        "en_US": "user_id",
                        "zh_Hans": "user_id"
                      },
                      "value": "user_id"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get Metadata Information of Specified Multidimensional Table",
                  "zh_Hans": "获取指定多维表格的元数据信息"
                },
                "llm": "A tool for getting metadata information of a specified multidimensional table. (获取指定多维表格的元数据信息)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Get Base Info",
                  "zh_Hans": "获取多维表格元数据"
                },
                "name": "get_base_info"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for the multidimensional table, supports inputting document URL.",
                    "zh_Hans": "多维表格的唯一标识符，支持输入文档 URL。"
                  },
                  "label": {
                    "en_US": "app_token",
                    "zh_Hans": "app_token"
                  },
                  "llm_description": "多维表格的唯一标识符，支持输入文档 URL。",
                  "max": null,
                  "min": null,
                  "name": "app_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Update Multiple Records in Multidimensional Table",
                  "zh_Hans": "更新多维表格数据表中的多条记录"
                },
                "llm": "A tool for updating multiple records in a multidimensional table. (更新多维表格数据表中的多条记录)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Update Records",
                  "zh_Hans": "更新多条记录"
                },
                "name": "update_records"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for the multidimensional table, supports inputting document URL.",
                    "zh_Hans": "多维表格的唯一标识符，支持输入文档 URL。"
                  },
                  "label": {
                    "en_US": "app_token",
                    "zh_Hans": "app_token"
                  },
                  "llm_description": "多维表格的唯一标识符，支持输入文档 URL。",
                  "max": null,
                  "min": null,
                  "name": "app_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for the multidimensional table data, either table_id or table_name must be provided, cannot be empty simultaneously.",
                    "zh_Hans": "多维表格数据表的唯一标识符，table_id 和 table_name 至少需要提供一个，不能同时为空。"
                  },
                  "label": {
                    "en_US": "table_id",
                    "zh_Hans": "table_id"
                  },
                  "llm_description": "多维表格数据表的唯一标识符，table_id 和 table_name 至少需要提供一个，不能同时为空。",
                  "max": null,
                  "min": null,
                  "name": "table_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Name of the multidimensional table data, either table_name or table_id must be provided, cannot be empty simultaneously.",
                    "zh_Hans": "多维表格数据表的名称，table_name 和 table_id 至少需要提供一个，不能同时为空。"
                  },
                  "label": {
                    "en_US": "table_name",
                    "zh_Hans": "table_name"
                  },
                  "llm_description": "多维表格数据表的名称，table_name 和 table_id 至少需要提供一个，不能同时为空。",
                  "max": null,
                  "min": null,
                  "name": "table_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "List of records to be updated in this request. Example value: [{\"fields\":{\"multi-line-text\":\"text content\",\"single_select\":\"option 1\",\"date\":1674206443000},\"record_id\":\"recupK4f4RM5RX\"}].\nFor supported field types, refer to the integration guide (https://open.larkoffice.com/document/server-docs/docs/bitable-v1/notification). For data structures of different field types, refer to the data structure overview (https://open.larkoffice.com/document/server-docs/docs/bitable-v1/bitable-structure).\n",
                    "zh_Hans": "本次请求将要更新的记录列表，示例值：[{\"fields\":{\"多行文本\":\"文本内容\",\"单选\":\"选项 1\",\"日期\":1674206443000},\"record_id\":\"recupK4f4RM5RX\"}]。\n当前接口支持的字段类型请参考接入指南(https://open.larkoffice.com/document/server-docs/docs/bitable-v1/notification)，不同类型字段的数据结构请参考数据结构概述(https://open.larkoffice.com/document/server-docs/docs/bitable-v1/bitable-structure)。\n"
                  },
                  "label": {
                    "en_US": "records",
                    "zh_Hans": "记录列表"
                  },
                  "llm_description": "本次请求将要更新的记录列表，示例值：[{\"fields\":{\"多行文本\":\"文本内容\",\"单选\":\"选项 1\",\"日期\":1674206443000},\"record_id\":\"recupK4f4RM5RX\"}]。\n当前接口支持的字段类型请参考接入指南(https://open.larkoffice.com/document/server-docs/docs/bitable-v1/notification)，不同类型字段的数据结构请参考数据结构概述(https://open.larkoffice.com/document/server-docs/docs/bitable-v1/bitable-structure)。\n",
                  "max": null,
                  "min": null,
                  "name": "records",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "open_id",
                  "form": "form",
                  "human_description": {
                    "en_US": "User ID type, optional values are open_id, union_id, user_id, with a default value of open_id.",
                    "zh_Hans": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。"
                  },
                  "label": {
                    "en_US": "user_id_type",
                    "zh_Hans": "用户 ID 类型"
                  },
                  "llm_description": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。",
                  "max": null,
                  "min": null,
                  "name": "user_id_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "open_id",
                        "zh_Hans": "open_id"
                      },
                      "value": "open_id"
                    },
                    {
                      "label": {
                        "en_US": "union_id",
                        "zh_Hans": "union_id"
                      },
                      "value": "union_id"
                    },
                    {
                      "label": {
                        "en_US": "user_id",
                        "zh_Hans": "user_id"
                      },
                      "value": "user_id"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-26T10:44:49Z",
        "version_updated_at": "2025-02-26T10:44:49Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Encode and decode JWT (JSON Web Token).",
          "zh_Hans": "Encode and decode JWT (JSON Web Token)."
        },
        "category": "tool",
        "created_at": "2025-03-10T22:59:31Z",
        "endpoint": {},
        "icon": "bowenliang123/packages/jwt/_assets/icon.svg",
        "index_id": "bowenliang123___jwt",
        "install_count": 508,
        "introduction": "## JWT\n\n**Author:** [bowenliang123](https://github.com/bowenliang123)\n**Github Repository:** https://github.com/bowenliang123/jwt\n\n### Description\n\nThis plugin provides tools to encode and decode JSON Web Token (JWT) as defined in [RFC 7519](https://tools.ietf.org/html/rfc7519).\n\nJSON Web Token (JWT) is an open standard (RFC 7519) that defines a compact and self-contained way for securely transmitting information between parties as a JSON object. This information can be verified and trusted because it is digitally signed. JWTs can be signed using a secret (with the HMAC algorithm) or a public/private key pair using RSA or ECDSA.\n\nAs using the `PyJWT` library for implementation, this plugin supports the following algorithms: HS256, RS256, PS256, EdDSA, ES256.\nFor further usage in the combination of algorithm and keys, please refer [PyJWT's usage docs](https://pyjwt.readthedocs.io/en/stable/usage.html).\n\n\n### Usage\n\n- JWT Encoder\n\n<img src=\"./_assets/img1.png\" width=\"650\" >\n\n\n- JWT Decoder\n\nWhen the option `Extract headers to _headers field` is set to `Yes`, the headers are extracted from JWT and will be put into `_header` field of the output JSON object.\n\n<img src=\"./_assets/img2.png\" width=\"650\" >\n\n<img src=\"./_assets/img3.png\" width=\"650\" >\n\n",
        "label": {
          "en_US": "JWT",
          "zh_Hans": "JWT"
        },
        "latest_package_identifier": "bowenliang123/jwt:0.0.1@dc568367f8ea56849dbba71bf17148eef68c05f2ebbc0d73a92a9de882812cb5",
        "latest_version": "0.0.1",
        "model": {},
        "name": "jwt",
        "org": "bowenliang123",
        "plugin_id": "bowenliang123/jwt",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/jwt.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "bowenliang123",
            "description": {
              "en_US": "Encode and decode JWT (JSON Web Token).",
              "zh_Hans": "Encode and decode JWT (JSON Web Token)."
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "JWT (JSON Web Token)",
              "pt_BR": "JWT (JSON Web Token)",
              "zh_Hans": "JWT (JSON Web Token)"
            },
            "name": "jwt",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Generate encoded JWT (JSON Web Token).",
                  "zh_Hans": "生成 JWT (JSON Web Token)."
                },
                "llm": "A tool to encode JWT (JSON Web Token)."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "bowenliang123",
                "label": {
                  "en_US": "JWT Encoder",
                  "zh_Hans": "JWT 编码"
                },
                "name": "jwt_encoder"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": "{}",
                  "form": "llm",
                  "human_description": {
                    "en_US": "JSON object string for payload",
                    "zh_Hans": "表示载荷的JSON对象字符串"
                  },
                  "label": {
                    "en_US": "Payload",
                    "zh_Hans": "载荷"
                  },
                  "llm_description": "payload JSON string",
                  "max": null,
                  "min": null,
                  "name": "payload",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "HS256",
                  "form": "form",
                  "human_description": {
                    "en_US": "one of supported algorithms in HS256, RS256, PS256, EdDSA, ES256",
                    "zh_Hans": "其中一个支持的加密算法 HS256, RS256, PS256, EdDSA, ES256"
                  },
                  "label": {
                    "en_US": "encryption algorithm",
                    "zh_Hans": "加密算法"
                  },
                  "llm_description": "encryption algorithm",
                  "max": null,
                  "min": null,
                  "name": "algorithm",
                  "options": [
                    {
                      "label": {
                        "en_US": "HS256"
                      },
                      "value": "HS256"
                    },
                    {
                      "label": {
                        "en_US": "RS256 (RSA)"
                      },
                      "value": "RS256"
                    },
                    {
                      "label": {
                        "en_US": "PS256 (RSA)"
                      },
                      "value": "PS256"
                    },
                    {
                      "label": {
                        "en_US": "EdDSA (Ed25519)"
                      },
                      "value": "EdDSA"
                    },
                    {
                      "label": {
                        "en_US": "ES256 (ECDSA)"
                      },
                      "value": "ES256"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Secret key for encryption. For HS256, it is a string; For RS256, PS256, EdDSA, ES256, it is a string starting with \"-----BEGIN PRIVATE KEY-----\"",
                    "zh_Hans": "加密秘钥, 对于HS256, 是一个秘钥字符串; 对于RS256, PS256, EdDSA, ES256, 是一个\"-----BEGIN PRIVATE KEY-----\"开头的秘钥字符串"
                  },
                  "label": {
                    "en_US": "Encryption key",
                    "zh_Hans": "加密秘钥"
                  },
                  "llm_description": "secret key for encryption",
                  "max": null,
                  "min": null,
                  "name": "key",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "JSON object string for headers",
                    "zh_Hans": "用于表示Header的JSON对象字符串"
                  },
                  "label": {
                    "en_US": "Headers",
                    "zh_Hans": "Headers"
                  },
                  "llm_description": "Headers JSON string",
                  "max": null,
                  "min": null,
                  "name": "headers",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Decode a JWT (JSON Web Token).",
                  "zh_Hans": "解码 JWT (JSON Web Token)."
                },
                "llm": "A tool to decode JWT (JSON Web Token)."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "bowenliang123",
                "label": {
                  "en_US": "JWT Decoder",
                  "zh_Hans": "JWT 解码"
                },
                "name": "jwt_decoder"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Encoded JWT string",
                    "zh_Hans": "JWT 密文"
                  },
                  "label": {
                    "en_US": "Encoded JWT string",
                    "zh_Hans": "JWT 密文"
                  },
                  "llm_description": "Encoded JWT (JSON Web Token) string",
                  "max": null,
                  "min": null,
                  "name": "jwt",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "HS256",
                  "form": "form",
                  "human_description": {
                    "en_US": "one of supported algorithms in HS256, RS256, PS256, EdDSA, ES256",
                    "zh_Hans": "其中一个支持的加密算法 HS256, RS256, PS256, EdDSA, ES256"
                  },
                  "label": {
                    "en_US": "decryption algorithm",
                    "zh_Hans": "解密算法"
                  },
                  "llm_description": "encryption algorithm",
                  "max": null,
                  "min": null,
                  "name": "algorithm",
                  "options": [
                    {
                      "label": {
                        "en_US": "HS256"
                      },
                      "value": "HS256"
                    },
                    {
                      "label": {
                        "en_US": "RS256 (RSA)"
                      },
                      "value": "RS256"
                    },
                    {
                      "label": {
                        "en_US": "PS256 (RSA)"
                      },
                      "value": "PS256"
                    },
                    {
                      "label": {
                        "en_US": "EdDSA (Ed25519)"
                      },
                      "value": "EdDSA"
                    },
                    {
                      "label": {
                        "en_US": "ES256 (ECDSA)"
                      },
                      "value": "ES256"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Secret key for encryption. For HS256, it is a string; For RS256, PS256, EdDSA, ES256, it is a string starting with \"-----BEGIN PUBLIC KEY-----\"",
                    "zh_Hans": "加密秘钥, 对于HS256, 是一个秘钥字符串; 对于RS256, PS256, EdDSA, ES256, 是一个\"-----BEGIN PUBLIC KEY-----\"开头的秘钥字符串"
                  },
                  "label": {
                    "en_US": "decryption key",
                    "zh_Hans": "解密秘钥"
                  },
                  "llm_description": "secret key for decryption",
                  "max": null,
                  "min": null,
                  "name": "key",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": "true",
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to extract headers put into \"_headers\" field",
                    "zh_Hans": "提取Headers对象并放入\"_headers\"字段"
                  },
                  "label": {
                    "en_US": "Extract headers to _headers field",
                    "zh_Hans": "是否提取Headers到_headers字段"
                  },
                  "llm_description": "Whether to extract headers object",
                  "max": null,
                  "min": null,
                  "name": "extract_headers",
                  "options": [
                    {
                      "label": {
                        "en_US": "Yes",
                        "zh_Hans": "是"
                      },
                      "value": "true"
                    },
                    {
                      "label": {
                        "en_US": "No",
                        "zh_Hans": "否"
                      },
                      "value": "false"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-10T22:59:40Z",
        "version_updated_at": "2025-03-10T22:59:40Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Comprehensive Notion integration allowing you to search, retrieve, create, and update pages, databases, and comments directly from your Dify applications. Query databases with filters, manage database properties, and organize your Notion workspace efficiently.",
          "ja_JP": "Difyアプリケーションから直接Notionのページ、データベース、コメントを検索、取得、作成、更新できる包括的な統合。フィルター付きでデータベースを照会し、データベースのプロパティを管理し、Notionワークスペースを効率的に整理します。",
          "pt_BR": "Integração abrangente com o Notion permitindo pesquisar, recuperar, criar e atualizar páginas, bancos de dados e comentários diretamente de seus aplicativos Dify. Consulte bancos de dados com filtros, gerencie propriedades de banco de dados e organize seu espaço de trabalho do Notion de forma eficiente.",
          "zh_Hans": "全面的 Notion 集成，允许您直接从 Dify 应用程序中搜索、获取、创建和更新页面、数据库和评论。使用筛选器查询数据库，管理数据库属性，高效组织您的 Notion 工作区。"
        },
        "category": "tool",
        "created_at": "2025-04-15T02:42:00Z",
        "endpoint": {},
        "icon": "langgenius/packages/notion/_assets/icon.svg",
        "index_id": "langgenius___notion",
        "install_count": 508,
        "introduction": "# Notion Plugin for Dify\n\n## Overview\n\nThe Notion Plugin for Dify provides integration with Notion workspaces, allowing you to search, query databases, create and update pages directly from your Dify applications. It enables seamless interaction with your Notion content without leaving your Dify environment.\n\n## Features\n\n- **Search Notion**: Search for pages and databases in your Notion workspace by keywords\n- **Query Database**: Retrieve and filter content from specific Notion databases\n- **Create Page**: Create new pages in your Notion workspace with custom title and content\n- **Retrieve Page**: Get a specific page and its content by ID\n- **Update Page**: Update an existing page's title or add new content\n- **Retrieve Database**: Get database structure and schema information\n- **Create Database**: Create a new database with custom properties and schema\n- **Update Database**: Modify an existing database's title or properties\n- **Retrieve Comments**: Get comments from a specific page or block\n- **Create Comment**: Add a new comment to a Notion page\n\n## Configuration\n\n### 1. Setting up Integration in Notion\n\nGo to [Notion Integrations](https://www.notion.so/my-integrations) and create a new **internal** integration or select an existing one.\n\n![](_assets/docs/integrations-creation.png)\n\nGive your integration an appropriate name and select the workspace you want to connect it to.\n\nFor security reasons, you may want to limit the capabilities of your integration. For example, you can create a read-only integration by only enabling \"Read content\" permission:\n\n![](_assets/docs/integrations-capabilities.png)\n\nCopy your \"Internal Integration Secret\" from the \"Secrets\" tab. You'll need this to configure the plugin in Dify.\n\n**Important:** Keep this secret secure. Anyone with this token can access content shared with your integration.\n\n### 2. Connecting Content to Your Integration\n\nFor your integration to access specific pages or databases, you must explicitly share them with your integration:\n\n1. Navigate to the page or database you want to access through the plugin\n2. Click the \"•••\" (three dots) menu in the top-right corner\n3. Select \"Add connections\" and choose your integration from the list\n\n![](_assets/docs/connections.png)\n\nRepeat this process for each page or database you want to access with the plugin.\n\n### 3. Configuring the Plugin in Dify\n\n1. In your Dify workspace, navigate to the Plugins section\n2. Find and select the Notion plugin\n3. Paste your Integration Secret in the configuration field\n4. Save your configuration\n\n## Usage Examples\n\n### Search Notion\n```\nFind pages in my Notion workspace containing \"project plan\"\n```\n\n### Query a Database\n```\nShow me all items in my Notion database with ID \"abc123\" where Status is \"In Progress\"\n```\n\n### Create a Page\n```\nCreate a new Notion page titled \"Meeting Notes\" with content \"Discussed project timeline and assigned tasks.\"\n```\n\n### Retrieve a Page\n```\nGet the Notion page with ID \"abc123\" and include its content\n```\n\n### Update a Page\n```\nUpdate the title of Notion page \"abc123\" to \"Updated Meeting Notes\" and add \"Follow-up scheduled for next week\" to the content\n```\n\n### Retrieve Database Structure\n```\nGet the structure and properties of Notion database \"abc123\"\n```\n\n### Create Database\n```\nCreate a new database in Notion page \"abc123\" titled \"Project Tasks\" with properties for Name (title), Status (select), and Due Date (date)\n```\n\n### Update Database\n```\nUpdate the Notion database \"abc123\" to rename the \"Status\" property to \"Progress\"\n```\n\n### Retrieve Comments\n```\nGet all comments from the Notion page \"abc123\"\n```\n\n### Create Comment\n```\nAdd a comment \"Great progress on this task!\" to Notion page \"abc123\"\n```\n\n## Supported Operations\n\n1. **Search**: Find pages and databases across your workspace\n2. **Query Database**: Retrieve and filter records from a specific database\n3. **Create Page**: Create new pages with title and content\n4. **Retrieve Page**: Get page details including properties and content blocks\n5. **Update Page**: Modify page titles or append new content \n6. **Retrieve Database**: Get database structure, schema and property types\n7. **Create Database**: Create new databases with custom properties\n8. **Update Database**: Update database title or modify properties\n9. **Retrieve Comments**: Get comments from a page or block\n10. **Create Comment**: Add comments to a page\n11. **Extract Data**: Process various Notion property types including rich text, select, multi-select, etc.\n\n## Troubleshooting\n\n- **Authentication Errors**: Make sure your integration token is valid and not expired\n- **Access Errors**: Ensure the integration has been given access to the pages/databases you're trying to work with\n- **Not Found Errors**: Check that the database or page IDs are correct and accessible\n- **Rate Limiting**: If you receive rate limit errors, the plugin will automatically retry with backoff\n",
        "label": {
          "en_US": "Notion",
          "ja_JP": "Notion",
          "pt_BR": "Notion",
          "zh_Hans": "Notion"
        },
        "latest_package_identifier": "langgenius/notion:0.0.1@5156ceb22a99c29985723b1b0bb6dd73cdf927a8ad8cc1c77c7424621166e753",
        "latest_version": "0.0.1",
        "model": {},
        "name": "notion",
        "org": "langgenius",
        "plugin_id": "langgenius/notion",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/notion.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "utilities"
          },
          {
            "name": "business"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Get your integration token from the Notion Integrations page",
                "ja_JP": "Notion統合ページから統合トークンを取得してください",
                "pt_BR": "Obtenha seu token de integração na página de Integrações do Notion",
                "zh_Hans": "从 Notion 集成页面获取您的接口令牌"
              },
              "label": {
                "en_US": "Integration Secret",
                "ja_JP": "統合シークレット (Integration Secret)",
                "pt_BR": "Segredo de Integração (Integration Secret)",
                "zh_Hans": "接口密钥 (Integration Secret)"
              },
              "name": "integration_token",
              "options": null,
              "placeholder": {
                "en_US": "Enter your Notion Integration Token",
                "ja_JP": "Notion統合トークンを入力してください",
                "pt_BR": "Digite seu Token de Integração do Notion",
                "zh_Hans": "输入您的 Notion 接口令牌"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://www.notion.so/profile/integrations"
            }
          ],
          "identity": {
            "author": "langgenius",
            "description": {
              "en_US": "Connect to Notion to search, query databases, and create content",
              "ja_JP": "Notionに接続して検索、データベースのクエリ、コンテンツの作成を行います",
              "pt_BR": "Conecte-se ao Notion para pesquisar, consultar bancos de dados e criar conteúdo",
              "zh_Hans": "连接 Notion 以搜索、查询数据库和创建内容"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Notion",
              "ja_JP": "Notion",
              "pt_BR": "Notion",
              "zh_Hans": "Notion"
            },
            "name": "notion",
            "tags": [
              "productivity",
              "business",
              "utilities"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Search for pages and databases in your Notion workspace",
                  "ja_JP": "Notion ワークスペース内のページとデータベースを検索します",
                  "pt_BR": "Pesquise páginas e bancos de dados em seu workspace do Notion",
                  "zh_Hans": "在您的 Notion 工作区中搜索页面和数据库"
                },
                "llm": "Search for pages and databases in a Notion workspace by title or content. Returns a list of matching results with their URLs, titles, and object types (page or database)."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Search Notion",
                  "ja_JP": "Notion を検索",
                  "pt_BR": "Pesquisar no Notion",
                  "zh_Hans": "搜索 Notion"
                },
                "name": "search_notion"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Enter keywords to search for in Notion",
                    "ja_JP": "Notion で検索するキーワードを入力してください",
                    "pt_BR": "Digite palavras-chave para pesquisar no Notion",
                    "zh_Hans": "输入要在 Notion 中搜索的关键词"
                  },
                  "label": {
                    "en_US": "Search Query",
                    "ja_JP": "検索クエリ",
                    "pt_BR": "Consulta de Pesquisa",
                    "zh_Hans": "搜索查询"
                  },
                  "llm_description": "The search query to find pages or databases in Notion. Can be any keywords that might appear in the title or content.",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 10,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Maximum number of search results to return",
                    "ja_JP": "返す検索結果の最大数",
                    "pt_BR": "Número máximo de resultados de pesquisa a retornar",
                    "zh_Hans": "返回的搜索结果最大数量"
                  },
                  "label": {
                    "en_US": "Maximum Results",
                    "ja_JP": "最大結果数",
                    "pt_BR": "Resultados Máximos",
                    "zh_Hans": "最大结果数"
                  },
                  "llm_description": "The maximum number of search results to return. Default is 10.",
                  "max": null,
                  "min": null,
                  "name": "limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Query and filter data from a Notion database",
                  "ja_JP": "Notion データベースからデータを照会およびフィルタリングします",
                  "pt_BR": "Consultar e filtrar dados de um banco de dados do Notion",
                  "zh_Hans": "查询和筛选 Notion 数据库中的数据"
                },
                "llm": "Query a specific Notion database by its ID, with optional filtering and sorting. Returns database records with their properties."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Query Notion Database",
                  "ja_JP": "Notion データベースを照会",
                  "pt_BR": "Consultar Banco de Dados do Notion",
                  "zh_Hans": "查询 Notion 数据库"
                },
                "name": "query_database"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the Notion database to query",
                    "ja_JP": "照会する Notion データベースの ID",
                    "pt_BR": "O ID do banco de dados do Notion a ser consultado",
                    "zh_Hans": "要查询的 Notion 数据库的 ID"
                  },
                  "label": {
                    "en_US": "Database ID",
                    "ja_JP": "データベース ID",
                    "pt_BR": "ID do Banco de Dados",
                    "zh_Hans": "数据库 ID"
                  },
                  "llm_description": "The ID of the Notion database to query. This can be found in the database URL or page URL after the workspace name and slash.",
                  "max": null,
                  "min": null,
                  "name": "database_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Property name to filter by (optional)",
                    "ja_JP": "フィルタリングするプロパティ名（オプション）",
                    "pt_BR": "Nome da propriedade para filtrar (opcional)",
                    "zh_Hans": "要筛选的属性名称（可选）"
                  },
                  "label": {
                    "en_US": "Filter Property",
                    "ja_JP": "フィルタープロパティ",
                    "pt_BR": "Propriedade de Filtro",
                    "zh_Hans": "筛选属性"
                  },
                  "llm_description": "Optional property name to filter by. If provided, filter_value must also be provided.",
                  "max": null,
                  "min": null,
                  "name": "filter_property",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Value to filter by (optional)",
                    "ja_JP": "フィルタリングする値（オプション）",
                    "pt_BR": "Valor para filtrar (opcional)",
                    "zh_Hans": "要筛选的值（可选）"
                  },
                  "label": {
                    "en_US": "Filter Value",
                    "ja_JP": "フィルター値",
                    "pt_BR": "Valor do Filtro",
                    "zh_Hans": "筛选值"
                  },
                  "llm_description": "Optional value to filter by. Works with filter_property to create a simple equals filter.",
                  "max": null,
                  "min": null,
                  "name": "filter_value",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 10,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Maximum number of database records to return",
                    "ja_JP": "返すデータベースレコードの最大数",
                    "pt_BR": "Número máximo de registros do banco de dados a retornar",
                    "zh_Hans": "返回的数据库记录的最大数量"
                  },
                  "label": {
                    "en_US": "Maximum Results",
                    "ja_JP": "最大結果数",
                    "pt_BR": "Resultados Máximos",
                    "zh_Hans": "最大结果数"
                  },
                  "llm_description": "The maximum number of database records to return. Default is 10.",
                  "max": null,
                  "min": null,
                  "name": "limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Create a new page in Notion with title and content",
                  "ja_JP": "タイトルとコンテンツを含む新しい Notion ページを作成します",
                  "pt_BR": "Criar uma nova página no Notion com título e conteúdo",
                  "zh_Hans": "在 Notion 中创建带有标题和内容的新页面"
                },
                "llm": "Create a new page in Notion with a title and content. The page can be created in a parent page or database. Returns the URL of the newly created page."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Create Notion Page",
                  "ja_JP": "Notion ページを作成",
                  "pt_BR": "Criar Página no Notion",
                  "zh_Hans": "创建 Notion 页面"
                },
                "name": "create_page"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Title for the new Notion page",
                    "ja_JP": "新しい Notion ページのタイトル",
                    "pt_BR": "Título para a nova página do Notion",
                    "zh_Hans": "新 Notion 页面的标题"
                  },
                  "label": {
                    "en_US": "Page Title",
                    "ja_JP": "ページタイトル",
                    "pt_BR": "Título da Página",
                    "zh_Hans": "页面标题"
                  },
                  "llm_description": "Title for the new Notion page.",
                  "max": null,
                  "min": null,
                  "name": "title",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Content for the new Notion page",
                    "ja_JP": "新しい Notion ページのコンテンツ",
                    "pt_BR": "Conteúdo para a nova página do Notion",
                    "zh_Hans": "新 Notion 页面的内容"
                  },
                  "label": {
                    "en_US": "Page Content",
                    "ja_JP": "ページコンテンツ",
                    "pt_BR": "Conteúdo da Página",
                    "zh_Hans": "页面内容"
                  },
                  "llm_description": "Content for the new Notion page. Plain text that will be converted to a paragraph block.",
                  "max": null,
                  "min": null,
                  "name": "content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "ID of parent page or database (optional)",
                    "ja_JP": "親ページまたはデータベースの ID（オプション）",
                    "pt_BR": "ID da página ou banco de dados pai (opcional)",
                    "zh_Hans": "父级页面或数据库的 ID（可选）"
                  },
                  "label": {
                    "en_US": "Parent ID",
                    "ja_JP": "親 ID",
                    "pt_BR": "ID Pai",
                    "zh_Hans": "父级 ID"
                  },
                  "llm_description": "Optional ID of the parent page or database where the new page will be created. If not provided, the page will be created at the top level.",
                  "max": null,
                  "min": null,
                  "name": "parent_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "page",
                  "form": "llm",
                  "human_description": {
                    "en_US": "Type of parent (page or database)",
                    "ja_JP": "親のタイプ（ページまたはデータベース）",
                    "pt_BR": "Tipo de pai (página ou banco de dados)",
                    "zh_Hans": "父级的类型（页面或数据库）"
                  },
                  "label": {
                    "en_US": "Parent Type",
                    "ja_JP": "親タイプ",
                    "pt_BR": "Tipo de Pai",
                    "zh_Hans": "父级类型"
                  },
                  "llm_description": "Type of the parent - either 'page' or 'database'. Default is 'page'. This determines how the new page will be created.",
                  "max": null,
                  "min": null,
                  "name": "parent_type",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Retrieve a page from Notion by its ID",
                  "ja_JP": "ID で Notion ページを取得します",
                  "pt_BR": "Recuperar uma página do Notion pelo seu ID",
                  "zh_Hans": "通过 ID 获取 Notion 页面"
                },
                "llm": "Retrieve a Notion page by its ID. Returns page content, properties, and metadata. The page must be shared with your integration."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Retrieve Notion Page",
                  "ja_JP": "Notion ページを取得",
                  "pt_BR": "Recuperar Página do Notion",
                  "zh_Hans": "获取 Notion 页面"
                },
                "name": "retrieve_page"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the Notion page to retrieve",
                    "ja_JP": "取得する Notion ページの ID",
                    "pt_BR": "O ID da página do Notion a ser recuperada",
                    "zh_Hans": "要获取的 Notion 页面的 ID"
                  },
                  "label": {
                    "en_US": "Page ID",
                    "ja_JP": "ページ ID",
                    "pt_BR": "ID da Página",
                    "zh_Hans": "页面 ID"
                  },
                  "llm_description": "The ID of the Notion page to retrieve. This can be found in the page URL after the workspace name and slash, usually ending with a hyphen and random characters.",
                  "max": null,
                  "min": null,
                  "name": "page_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Whether to include the page content in the response",
                    "ja_JP": "レスポンスにページコンテンツを含めるかどうか",
                    "pt_BR": "Se deve incluir o conteúdo da página na resposta",
                    "zh_Hans": "是否在响应中包含页面内容"
                  },
                  "label": {
                    "en_US": "Include Content",
                    "ja_JP": "コンテンツを含める",
                    "pt_BR": "Incluir Conteúdo",
                    "zh_Hans": "包含内容"
                  },
                  "llm_description": "Whether to include the page blocks/content in the response. If set to false, only page properties will be returned.",
                  "max": null,
                  "min": null,
                  "name": "include_content",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Update a page in Notion with new title or content",
                  "ja_JP": "新しいタイトルやコンテンツで Notion ページを更新します",
                  "pt_BR": "Atualizar uma página no Notion com novo título ou conteúdo",
                  "zh_Hans": "使用新标题或内容更新 Notion 页面"
                },
                "llm": "Update an existing Notion page with a new title, new content, or both. Returns the updated page URL and metadata."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Update Notion Page",
                  "ja_JP": "Notion ページを更新",
                  "pt_BR": "Atualizar Página do Notion",
                  "zh_Hans": "更新 Notion 页面"
                },
                "name": "update_page"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the Notion page to update",
                    "ja_JP": "更新する Notion ページの ID",
                    "pt_BR": "O ID da página do Notion a ser atualizada",
                    "zh_Hans": "要更新的 Notion 页面的 ID"
                  },
                  "label": {
                    "en_US": "Page ID",
                    "ja_JP": "ページ ID",
                    "pt_BR": "ID da Página",
                    "zh_Hans": "页面 ID"
                  },
                  "llm_description": "The ID of the Notion page to update. This can be found in the page URL after the workspace name and slash, usually ending with a hyphen and random characters.",
                  "max": null,
                  "min": null,
                  "name": "page_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "New title for the page (leave empty to keep current title)",
                    "ja_JP": "ページの新しいタイトル（現在のタイトルを維持する場合は空白）",
                    "pt_BR": "Novo título para a página (deixe em branco para manter o título atual)",
                    "zh_Hans": "页面的新标题（留空以保留当前标题）"
                  },
                  "label": {
                    "en_US": "New Title",
                    "ja_JP": "新しいタイトル",
                    "pt_BR": "Novo Título",
                    "zh_Hans": "新标题"
                  },
                  "llm_description": "New title for the page. Leave empty or omit to keep the current title.",
                  "max": null,
                  "min": null,
                  "name": "title",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "New content to append to the page",
                    "ja_JP": "ページに追加する新しいコンテンツ",
                    "pt_BR": "Novo conteúdo para anexar à página",
                    "zh_Hans": "要附加到页面的新内容"
                  },
                  "label": {
                    "en_US": "New Content",
                    "ja_JP": "新しいコンテンツ",
                    "pt_BR": "Novo Conteúdo",
                    "zh_Hans": "新内容"
                  },
                  "llm_description": "New content to append to the page as a paragraph. This will add a new paragraph to the page, not replace existing content.",
                  "max": null,
                  "min": null,
                  "name": "content",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Whether to archive the page",
                    "ja_JP": "ページをアーカイブするかどうか",
                    "pt_BR": "Se deve arquivar a página",
                    "zh_Hans": "是否归档页面"
                  },
                  "label": {
                    "en_US": "Archive Page",
                    "ja_JP": "ページをアーカイブ",
                    "pt_BR": "Arquivar Página",
                    "zh_Hans": "归档页面"
                  },
                  "llm_description": "Whether to archive the page. If set to true, the page will be moved to the archive.",
                  "max": null,
                  "min": null,
                  "name": "archive",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Retrieve a database structure from Notion by its ID",
                  "ja_JP": "ID で Notion データベース構造を取得します",
                  "pt_BR": "Recuperar uma estrutura de banco de dados do Notion pelo seu ID",
                  "zh_Hans": "通过 ID 获取 Notion 数据库结构"
                },
                "llm": "Retrieve a Notion database structure by its ID. Returns database properties, schema, and metadata. The database must be shared with your integration."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Retrieve Notion Database",
                  "ja_JP": "Notion データベースを取得",
                  "pt_BR": "Recuperar Banco de Dados do Notion",
                  "zh_Hans": "获取 Notion 数据库"
                },
                "name": "retrieve_database"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the Notion database to retrieve",
                    "ja_JP": "取得する Notion データベースの ID",
                    "pt_BR": "O ID do banco de dados do Notion a ser recuperado",
                    "zh_Hans": "要获取的 Notion 数据库的 ID"
                  },
                  "label": {
                    "en_US": "Database ID",
                    "ja_JP": "データベース ID",
                    "pt_BR": "ID do Banco de Dados",
                    "zh_Hans": "数据库 ID"
                  },
                  "llm_description": "The ID of the Notion database to retrieve. This can be found in the database URL after the workspace name and slash, usually ending with a hyphen and random characters.",
                  "max": null,
                  "min": null,
                  "name": "database_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Create a new database in Notion with custom properties",
                  "ja_JP": "カスタムプロパティを持つ新しい Notion データベースを作成します",
                  "pt_BR": "Criar um novo banco de dados no Notion com propriedades personalizadas",
                  "zh_Hans": "在 Notion 中创建具有自定义属性的新数据库"
                },
                "llm": "Create a new database in Notion with specified properties. The database will be created as a child of a specified parent page."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Create Notion Database",
                  "ja_JP": "Notion データベースを作成",
                  "pt_BR": "Criar Banco de Dados do Notion",
                  "zh_Hans": "创建 Notion 数据库"
                },
                "name": "create_database"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the parent page where the database will be created",
                    "ja_JP": "データベースが作成される親ページの ID",
                    "pt_BR": "O ID da página pai onde o banco de dados será criado",
                    "zh_Hans": "数据库将被创建在哪个父页面中"
                  },
                  "label": {
                    "en_US": "Parent Page ID",
                    "ja_JP": "親ページ ID",
                    "pt_BR": "ID da Página Pai",
                    "zh_Hans": "父页面 ID"
                  },
                  "llm_description": "The ID of the parent page where the database will be created. Must be a page ID (not a database ID) and the page must be shared with your integration.",
                  "max": null,
                  "min": null,
                  "name": "parent_page_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Title for the new database",
                    "ja_JP": "新しいデータベースのタイトル",
                    "pt_BR": "Título para o novo banco de dados",
                    "zh_Hans": "新数据库的标题"
                  },
                  "label": {
                    "en_US": "Database Title",
                    "ja_JP": "データベースタイトル",
                    "pt_BR": "Título do Banco de Dados",
                    "zh_Hans": "数据库标题"
                  },
                  "llm_description": "Title for the new database. This will be displayed at the top of the database in Notion.",
                  "max": null,
                  "min": null,
                  "name": "title",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Properties definition for the database in JSON format",
                    "ja_JP": "データベースのプロパティ定義（JSON 形式）",
                    "pt_BR": "Definição de propriedades para o banco de dados em formato JSON",
                    "zh_Hans": "数据库属性定义（JSON 格式）"
                  },
                  "label": {
                    "en_US": "Database Properties",
                    "ja_JP": "データベースプロパティ",
                    "pt_BR": "Propriedades do Banco de Dados",
                    "zh_Hans": "数据库属性"
                  },
                  "llm_description": "Properties definition for the database in JSON format. Example: \n{\"Name\":{\"title\":{}},\"Description\":{\"rich_text\":{}},\"Status\":{\"select\":{\"options\":[{\"name\":\"Not started\"},{\"name\":\"In progress\"},{\"name\":\"Done\"}]}},\"Due Date\":{\"date\":{}}}\n",
                  "max": null,
                  "min": null,
                  "name": "properties",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Update a database in Notion with new title or properties",
                  "ja_JP": "新しいタイトルやプロパティで Notion データベースを更新します",
                  "pt_BR": "Atualizar um banco de dados no Notion com novo título ou propriedades",
                  "zh_Hans": "使用新标题或属性更新 Notion 数据库"
                },
                "llm": "Update an existing Notion database with a new title or modified properties. Returns the updated database URL and metadata."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Update Notion Database",
                  "ja_JP": "Notion データベースを更新",
                  "pt_BR": "Atualizar Banco de Dados do Notion",
                  "zh_Hans": "更新 Notion 数据库"
                },
                "name": "update_database"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the Notion database to update",
                    "ja_JP": "更新する Notion データベースの ID",
                    "pt_BR": "O ID do banco de dados do Notion a ser atualizado",
                    "zh_Hans": "要更新的 Notion 数据库的 ID"
                  },
                  "label": {
                    "en_US": "Database ID",
                    "ja_JP": "データベース ID",
                    "pt_BR": "ID do Banco de Dados",
                    "zh_Hans": "数据库 ID"
                  },
                  "llm_description": "The ID of the Notion database to update. This can be found in the database URL after the workspace name and slash, usually ending with a hyphen and random characters.",
                  "max": null,
                  "min": null,
                  "name": "database_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "New title for the database (leave empty to keep current title)",
                    "ja_JP": "データベースの新しいタイトル（現在のタイトルを維持する場合は空白）",
                    "pt_BR": "Novo título para o banco de dados (deixe em branco para manter o título atual)",
                    "zh_Hans": "数据库的新标题（留空以保留当前标题）"
                  },
                  "label": {
                    "en_US": "New Title",
                    "ja_JP": "新しいタイトル",
                    "pt_BR": "Novo Título",
                    "zh_Hans": "新标题"
                  },
                  "llm_description": "New title for the database. Leave empty or omit to keep the current title.",
                  "max": null,
                  "min": null,
                  "name": "title",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Updated properties definition for the database in JSON format",
                    "ja_JP": "データベースの更新プロパティ定義（JSON 形式）",
                    "pt_BR": "Definição de propriedades atualizadas para o banco de dados em formato JSON",
                    "zh_Hans": "数据库的更新属性定义（JSON 格式）"
                  },
                  "label": {
                    "en_US": "Database Properties",
                    "ja_JP": "データベースプロパティ",
                    "pt_BR": "Propriedades do Banco de Dados",
                    "zh_Hans": "数据库属性"
                  },
                  "llm_description": "Updated properties definition for the database in JSON format. Only include properties you want to update. Example to rename a property - {\"Old Name\":{\"name\":\"New Name\"}}",
                  "max": null,
                  "min": null,
                  "name": "properties",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Retrieve comments from a Notion page or block",
                  "ja_JP": "Notion ページまたはブロックからコメントを取得します",
                  "pt_BR": "Recuperar comentários de uma página ou bloco do Notion",
                  "zh_Hans": "获取 Notion 页面或块的评论"
                },
                "llm": "Retrieve comments from a Notion page or block. Returns the comments with their content, author information, and timestamps."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Retrieve Notion Comments",
                  "ja_JP": "Notion コメントを取得",
                  "pt_BR": "Recuperar Comentários do Notion",
                  "zh_Hans": "获取 Notion 评论"
                },
                "name": "retrieve_comments"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the Notion block or page to retrieve comments from",
                    "ja_JP": "コメントを取得する Notion ブロックまたはページの ID",
                    "pt_BR": "O ID do bloco ou página do Notion para recuperar comentários",
                    "zh_Hans": "要获取评论的 Notion 块或页面的 ID"
                  },
                  "label": {
                    "en_US": "Block or Page ID",
                    "ja_JP": "ブロックまたはページ ID",
                    "pt_BR": "ID do Bloco ou Página",
                    "zh_Hans": "块或页面 ID"
                  },
                  "llm_description": "The ID of the Notion block or page to retrieve comments from. This can be found in the page URL after the workspace name and slash, usually ending with a hyphen and random characters.",
                  "max": null,
                  "min": null,
                  "name": "block_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 100,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Maximum number of comments to retrieve (1-100)",
                    "ja_JP": "取得する最大コメント数（1〜100）",
                    "pt_BR": "Número máximo de comentários a serem recuperados (1-100)",
                    "zh_Hans": "要获取的最大评论数（1-100）"
                  },
                  "label": {
                    "en_US": "Page Size",
                    "ja_JP": "ページサイズ",
                    "pt_BR": "Tamanho da Página",
                    "zh_Hans": "页面大小"
                  },
                  "llm_description": "Maximum number of comments to retrieve. Must be between 1 and 100, default is 100.",
                  "max": null,
                  "min": null,
                  "name": "page_size",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Create a new comment on a Notion page",
                  "ja_JP": "Notion ページに新しいコメントを作成します",
                  "pt_BR": "Criar um novo comentário em uma página do Notion",
                  "zh_Hans": "在 Notion 页面上创建新评论"
                },
                "llm": "Create a new comment on a Notion page. Returns the created comment's ID and content."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Create Notion Comment",
                  "ja_JP": "Notion コメントを作成",
                  "pt_BR": "Criar Comentário no Notion",
                  "zh_Hans": "创建 Notion 评论"
                },
                "name": "create_comment"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the Notion page to comment on",
                    "ja_JP": "コメントする Notion ページの ID",
                    "pt_BR": "O ID da página do Notion para comentar",
                    "zh_Hans": "要评论的 Notion 页面的 ID"
                  },
                  "label": {
                    "en_US": "Page ID",
                    "ja_JP": "ページ ID",
                    "pt_BR": "ID da Página",
                    "zh_Hans": "页面 ID"
                  },
                  "llm_description": "The ID of the Notion page to comment on. This can be found in the page URL after the workspace name and slash, usually ending with a hyphen and random characters.",
                  "max": null,
                  "min": null,
                  "name": "page_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The text content of the comment",
                    "ja_JP": "コメントのテキスト内容",
                    "pt_BR": "O conteúdo de texto do comentário",
                    "zh_Hans": "评论的文本内容"
                  },
                  "label": {
                    "en_US": "Comment Content",
                    "ja_JP": "コメント内容",
                    "pt_BR": "Conteúdo do Comentário",
                    "zh_Hans": "评论内容"
                  },
                  "llm_description": "The text content of the comment. This supports basic text formatting.",
                  "max": null,
                  "min": null,
                  "name": "content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-15T02:42:12Z",
        "version_updated_at": "2025-04-15T02:42:12Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "The tools based on the AWS Services",
          "ja_JP": "The tools based on the AWS Services",
          "pt_BR": "The tools based on the AWS Services",
          "zh_Hans": "The tools based on the AWS Services"
        },
        "category": "tool",
        "created_at": "2025-02-28T11:01:53Z",
        "endpoint": {},
        "icon": "langgenius/packages/aws_tools/_assets/icon.svg",
        "index_id": "langgenius___aws_tools",
        "install_count": 497,
        "introduction": "## AWS Tools\n\n**Author:** aws  \n**Type:** Tool\n\n\n\n## Overview | 概述\n\nThe AWS Tools plugin provides a comprehensive set of tools based on various AWS services, enabling you to leverage AWS capabilities directly within your Dify applications. These tools cover a wide range of functionalities including content moderation, text reranking, text-to-speech conversion, speech recognition, and more.\n\nThe AWS Tools plugin includes the following tools:\n- Apply Guardrail\n- Bedrock Retrieve\n- Bedrock Retrieve and Generate\n- Lambda Translate Utils\n- Lambda YAML to JSON\n- Nova Canvas\n- Nova Reel\n- S3 Operator\n- SageMaker Chinese Toxicity Detector\n- SageMaker Text Rerank\n- SageMaker TTS\n- Transcribe ASR\n\n\n\nAWS Tools 插件提供了一套基于各种 AWS 服务的综合工具集，使您能够在 Dify 应用程序中直接利用 AWS 功能。这些工具涵盖了广泛的功能，包括内容审核、文本重排序、文本转语音转换、语音识别等。\n\nAWS Tools 插件包含以下工具：\n- 应用护栏\n- Bedrock 检索\n- Bedrock 检索和生成\n- Lambda 翻译工具\n- Lambda YAML 转 JSON\n- Nova 画布\n- Nova 卷轴\n- S3 操作器\n- SageMaker 中文毒性检测器\n- SageMaker 文本重排序\n- SageMaker 文本转语音\n- Transcribe 自动语音识别\n\n\n\n## Configure | 配置\n\nAWS Tools generally do not obtain authorization by configuring AK/SK through the Dify interface. Typically, authorization can be obtained by binding an AWS IAM Role to the Dify environment, or by setting AK/SK in the environment (EC2/EKS).\n\nAWS Tools 一般不通过在Dify的界面上配置AK/SK来获取授权，一般可以通过Dify环境绑定AWS IAM Role，或者在环境(Ec2/EKS)中设置AK/SK。\n\nThe AWS Tool interface is generally used to configure some tool call parameters, as shown in the following image.\n\nAWS Tool的界面一般用于配置一些工具的调用参数，如下图\n![](./_assets/guardrails.png)\n\n\n\n## Issue Feedback | 问题反馈\n\nFor more detailed information, please refer to [aws-sample/dify-aws-tool](https://github.com/aws-samples/dify-aws-tool/), which contains multiple workflows for reference.\nIf you have issues that need feedback, feel free to raise questions or look for answers in the [Issue](https://github.com/aws-samples/dify-aws-tool/issues) section.\n\n更多详细信息可以参考 [aws-sample/dify-aws-tool](https://github.com/aws-samples/dify-aws-tool/)，其中包含多个 workflow 供参考。\n如果存在问题需要反馈，欢迎到 [Issue](https://github.com/aws-samples/dify-aws-tool/issues) 去提出问题或者寻找答案。\n",
        "label": {
          "en_US": "AWS Tools",
          "ja_JP": "AWS Tools",
          "pt_BR": "AWS Tools",
          "zh_Hans": "AWS Tools"
        },
        "latest_package_identifier": "langgenius/aws_tools:0.0.5@f87f7625757768621d3e39424e2d3f7737692305c4682dd240db0616536e4277",
        "latest_version": "0.0.5",
        "model": {},
        "name": "aws_tools",
        "org": "langgenius",
        "plugin_id": "langgenius/aws_tools",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/aws_tools.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "aws",
            "description": {
              "en_US": "the tools based on the aws services",
              "pt_BR": "the tools based on the aws services",
              "zh_Hans": "the tools based on the aws services"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "AWS Tools",
              "pt_BR": "AWS Tools",
              "zh_Hans": "亚马逊云科技工具集"
            },
            "name": "aws_tools",
            "tags": [
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Content Moderation Guardrails utilizes the ApplyGuardrail API, a feature of Guardrails for Amazon Bedrock. This API is capable of evaluating input prompts and model responses for all Foundation Models (FMs), including those on Amazon Bedrock, custom FMs, and third-party FMs. By implementing this functionality, organizations can achieve centralized governance across all their generative AI applications, thereby enhancing control and consistency in content moderation.",
                  "zh_Hans": "内容审查护栏采用 Guardrails for Amazon Bedrock 功能中的 ApplyGuardrail API 。ApplyGuardrail 可以评估所有基础模型(FMs)的输入提示和模型响应，包括 Amazon Bedrock 上的 FMs、自定义 FMs 和第三方 FMs。通过实施这一功能, 组织可以在所有生成式 AI 应用程序中实现集中化的治理，从而增强内容审核的控制力和一致性。"
                },
                "llm": "Content Moderation Guardrails utilizes the ApplyGuardrail API, a feature of Guardrails for Amazon Bedrock. This API is capable of evaluating input prompts and model responses for all Foundation Models (FMs), including those on Amazon Bedrock, custom FMs, and third-party FMs. By implementing this functionality, organizations can achieve centralized governance across all their generative AI applications, thereby enhancing control and consistency in content moderation."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "AWS",
                "label": {
                  "en_US": "Content Moderation Guardrails",
                  "zh_Hans": "内容审查护栏"
                },
                "name": "apply_guardrail"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Please enter the ID of the Guardrail that has already been created on Amazon Bedrock, for example 'qk5nk0e4b77b'.",
                    "zh_Hans": "请输入已经在 Amazon Bedrock 上创建好的 Guardrail ID, 例如 'qk5nk0e4b77b'."
                  },
                  "label": {
                    "en_US": "Guardrail ID",
                    "zh_Hans": "Guardrail ID"
                  },
                  "llm_description": "Please enter the ID of the Guardrail that has already been created on Amazon Bedrock, for example 'qk5nk0e4b77b'.",
                  "max": null,
                  "min": null,
                  "name": "guardrail_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Please enter the published version of the Guardrail ID that has already been created on Amazon Bedrock. This is typically a version number, such as 2.",
                    "zh_Hans": "请输入已经在Amazon Bedrock 上创建好的Guardrail ID发布的版本, 通常使用版本号, 例如2."
                  },
                  "label": {
                    "en_US": "Guardrail Version Number",
                    "zh_Hans": "Guardrail 版本号码"
                  },
                  "llm_description": "Please enter the published version of the Guardrail ID that has already been created on Amazon Bedrock. This is typically a version number, such as 2.",
                  "max": null,
                  "min": null,
                  "name": "guardrail_version",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The source of data used in the request to apply the guardrail. Valid Values \"INPUT | OUTPUT\"",
                    "zh_Hans": "用于应用护栏的请求中所使用的数据来源。有效值为 \"INPUT | OUTPUT\""
                  },
                  "label": {
                    "en_US": "Content Source (INPUT or OUTPUT)",
                    "zh_Hans": "内容来源 (INPUT or OUTPUT)"
                  },
                  "llm_description": "The source of data used in the request to apply the guardrail. Valid Values \"INPUT | OUTPUT\"",
                  "max": null,
                  "min": null,
                  "name": "source",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The content used for requesting guardrail review, which can be either user input or LLM output.",
                    "zh_Hans": "用于请求护栏审查的内容，可以是用户输入或 LLM 输出。"
                  },
                  "label": {
                    "en_US": "Content to be reviewed",
                    "zh_Hans": "待审查内容"
                  },
                  "llm_description": "The content used for requesting guardrail review, which can be either user input or LLM output.",
                  "max": null,
                  "min": null,
                  "name": "text",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Please enter the AWS region for the Bedrock client, for example 'us-east-1'.",
                    "zh_Hans": "请输入 Bedrock 客户端的 AWS 区域，例如 'us-east-1'。"
                  },
                  "label": {
                    "en_US": "AWS Region",
                    "zh_Hans": "AWS 区域"
                  },
                  "llm_description": "Please enter the AWS region for the Bedrock client, for example 'us-east-1'.",
                  "max": null,
                  "min": null,
                  "name": "aws_region",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for retrieving relevant information from Amazon Bedrock Knowledge Base. You can find deploy instructions on Github Repo - https://github.com/aws-samples/dify-aws-tool",
                  "pt_BR": "A tool for retrieving relevant information from Amazon Bedrock Knowledge Base.",
                  "zh_Hans": "Amazon Bedrock知识库检索工具, 请参考 Github Repo - https://github.com/aws-samples/dify-aws-tool上的部署说明"
                },
                "llm": "A tool for retrieving relevant information from Amazon Bedrock Knowledge Base. You can find deploy instructions on Github Repo - https://github.com/aws-samples/dify-aws-tool"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "AWS",
                "label": {
                  "en_US": "Bedrock Retrieve",
                  "pt_BR": "Bedrock Retrieve",
                  "zh_Hans": "Bedrock检索"
                },
                "name": "bedrock_retrieve"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "AWS region for the Bedrock service",
                    "zh_Hans": "Bedrock服务的AWS区域"
                  },
                  "label": {
                    "en_US": "AWS Region",
                    "zh_Hans": "AWS区域"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "aws_region",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "AWS access key ID for authentication (optional)",
                    "zh_Hans": "用于身份验证的AWS访问密钥ID（可选）"
                  },
                  "label": {
                    "en_US": "AWS Access Key ID",
                    "zh_Hans": "AWS访问密钥ID"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "aws_access_key_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "AWS secret access key for authentication (optional)",
                    "zh_Hans": "用于身份验证的AWS秘密访问密钥（可选）"
                  },
                  "label": {
                    "en_US": "AWS Secret Access Key",
                    "zh_Hans": "AWS秘密访问密钥"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "aws_secret_access_key",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "text",
                  "form": "form",
                  "human_description": {
                    "en_US": "return a list of json or texts",
                    "zh_Hans": "返回一个列表，内容是json还是纯文本"
                  },
                  "label": {
                    "en_US": "result type",
                    "zh_Hans": "结果类型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "result_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "JSON",
                        "zh_Hans": "JSON"
                      },
                      "value": "json"
                    },
                    {
                      "label": {
                        "en_US": "Text",
                        "zh_Hans": "文本"
                      },
                      "value": "text"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "ID of the Bedrock Knowledge Base to retrieve from",
                    "pt_BR": "ID of the Bedrock Knowledge Base to retrieve from",
                    "zh_Hans": "用于检索的Bedrock知识库ID"
                  },
                  "label": {
                    "en_US": "Bedrock Knowledge Base ID",
                    "pt_BR": "Bedrock Knowledge Base ID",
                    "zh_Hans": "Bedrock知识库ID"
                  },
                  "llm_description": "ID of the Bedrock Knowledge Base to retrieve from",
                  "max": null,
                  "min": null,
                  "name": "knowledge_base_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The search query to retrieve relevant information",
                    "pt_BR": "The search query to retrieve relevant information",
                    "zh_Hans": "用于检索相关信息的查询语句"
                  },
                  "label": {
                    "en_US": "Query string",
                    "pt_BR": "Query string",
                    "zh_Hans": "查询语句"
                  },
                  "llm_description": "The search query to retrieve relevant information",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 5,
                  "form": "form",
                  "human_description": {
                    "en_US": "Maximum number of results to return",
                    "pt_BR": "Maximum number of results to return",
                    "zh_Hans": "最大返回结果数量"
                  },
                  "label": {
                    "en_US": "Limit for results count",
                    "pt_BR": "Limit for results count",
                    "zh_Hans": "返回结果数量限制"
                  },
                  "llm_description": "",
                  "max": 10,
                  "min": 1,
                  "name": "topk",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "SEMANTIC",
                  "form": "form",
                  "human_description": {
                    "en_US": "search type",
                    "pt_BR": "search type",
                    "zh_Hans": "搜索类型"
                  },
                  "label": {
                    "en_US": "search type",
                    "pt_BR": "search type",
                    "zh_Hans": "搜索类型"
                  },
                  "llm_description": "search type",
                  "max": null,
                  "min": null,
                  "name": "search_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "SEMANTIC",
                        "zh_Hans": "语义搜索"
                      },
                      "value": "SEMANTIC"
                    },
                    {
                      "label": {
                        "en_US": "HYBRID",
                        "zh_Hans": "混合搜索"
                      },
                      "value": "HYBRID"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "default",
                  "form": "form",
                  "human_description": {
                    "en_US": "rerank model id",
                    "pt_BR": "rerank model id",
                    "zh_Hans": "重拍模型ID"
                  },
                  "label": {
                    "en_US": "rerank model id",
                    "pt_BR": "rerank model id",
                    "zh_Hans": "重拍模型ID"
                  },
                  "llm_description": "rerank model id",
                  "max": null,
                  "min": null,
                  "name": "rerank_model_id",
                  "options": [
                    {
                      "label": {
                        "en_US": "default",
                        "zh_Hans": "默认"
                      },
                      "value": "default"
                    },
                    {
                      "label": {
                        "en_US": "cohere.rerank-v3-5:0",
                        "zh_Hans": "cohere.rerank-v3-5:0"
                      },
                      "value": "cohere.rerank-v3-5:0"
                    },
                    {
                      "label": {
                        "en_US": "amazon.rerank-v1:0",
                        "zh_Hans": "amazon.rerank-v1:0"
                      },
                      "value": "amazon.rerank-v1:0"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "JSON formatted filter conditions for metadata (e.g., {\"greaterThan\": {\"key: \"aaa\", \"value\": 10}})",
                    "pt_BR": "JSON formatted filter conditions for metadata (e.g., {\"greaterThan\": {\"key: \"aaa\", \"value\": 10}})",
                    "zh_Hans": "元数据的JSON格式过滤条件（例如，{{\"greaterThan\": {\"key: \"aaa\", \"value\": 10}}）"
                  },
                  "label": {
                    "en_US": "Metadata Filter",
                    "pt_BR": "Metadata Filter",
                    "zh_Hans": "元数据过滤器"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "metadata_filter",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "This is an advanced usage of Bedrock Retrieve. Please refer to the API documentation for detailed parameters and paste them into the corresponding Knowledge Base Configuration or External Sources Configuration",
                  "zh_Hans": "这个工具为Bedrock Retrieve的高级用法，请参考API设置详细的参数，并粘贴到对应的知识库配置或者外部源配置"
                },
                "llm": "A tool for retrieving and generating information using Amazon Bedrock Knowledge Base"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "AWS",
                "label": {
                  "en_US": "Bedrock Retrieve and Generate",
                  "zh_Hans": "Bedrock检索和生成"
                },
                "name": "bedrock_retrieve_and_generate"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "AWS region for the Bedrock service",
                    "zh_Hans": "Bedrock服务的AWS区域"
                  },
                  "label": {
                    "en_US": "AWS Region",
                    "zh_Hans": "AWS区域"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "aws_region",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "AWS access key ID for authentication (optional)",
                    "zh_Hans": "用于身份验证的AWS访问密钥ID（可选）"
                  },
                  "label": {
                    "en_US": "AWS Access Key ID",
                    "zh_Hans": "AWS访问密钥ID"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "aws_access_key_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "AWS secret access key for authentication (optional)",
                    "zh_Hans": "用于身份验证的AWS秘密访问密钥（可选）"
                  },
                  "label": {
                    "en_US": "AWS Secret Access Key",
                    "zh_Hans": "AWS秘密访问密钥"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "aws_secret_access_key",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "text",
                  "form": "form",
                  "human_description": {
                    "en_US": "return a list of json or texts",
                    "zh_Hans": "返回一个列表，内容是json还是纯文本"
                  },
                  "label": {
                    "en_US": "result type",
                    "zh_Hans": "结果类型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "result_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "JSON",
                        "zh_Hans": "JSON"
                      },
                      "value": "json"
                    },
                    {
                      "label": {
                        "en_US": "Text",
                        "zh_Hans": "文本"
                      },
                      "value": "text"
                    },
                    {
                      "label": {
                        "en_US": "Text With Citations",
                        "zh_Hans": "文本（包含引用）"
                      },
                      "value": "text-with-citations"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The text query to retrieve information",
                    "zh_Hans": "用于检索信息的文本查询"
                  },
                  "label": {
                    "en_US": "Input Text",
                    "zh_Hans": "输入文本"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "input",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Type of retrieve and generate configuration",
                    "zh_Hans": "检索和生成配置的类型"
                  },
                  "label": {
                    "en_US": "Configuration Type",
                    "zh_Hans": "配置类型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "type",
                  "options": [
                    {
                      "label": {
                        "en_US": "Knowledge Base",
                        "zh_Hans": "知识库"
                      },
                      "value": "KNOWLEDGE_BASE"
                    },
                    {
                      "label": {
                        "en_US": "External Sources",
                        "zh_Hans": "外部源"
                      },
                      "value": "EXTERNAL_SOURCES"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Please refer to @https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/bedrock-agent-runtime/client/retrieve_and_generate.html#retrieve-and-generate for complete parameters and paste them here",
                    "zh_Hans": "请参考 https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/bedrock-agent-runtime/client/retrieve_and_generate.html#retrieve-and-generate 配置完整的参数并粘贴到这里"
                  },
                  "label": {
                    "en_US": "Knowledge Base Configuration",
                    "zh_Hans": "知识库配置"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "knowledge_base_configuration",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Please refer to https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/bedrock-agent-runtime/client/retrieve_and_generate.html#retrieve-and-generate for complete parameters and paste them here",
                    "zh_Hans": "请参考 https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/bedrock-agent-runtime/client/retrieve_and_generate.html#retrieve-and-generate 配置完整的参数并粘贴到这里"
                  },
                  "label": {
                    "en_US": "External Sources Configuration",
                    "zh_Hans": "外部源配置"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "external_sources_configuration",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "",
                  "form": "form",
                  "human_description": {
                    "en_US": "JSON formatted session configuration",
                    "zh_Hans": "JSON格式的会话配置"
                  },
                  "label": {
                    "en_US": "Session Configuration",
                    "zh_Hans": "会话配置"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "session_configuration",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Session ID for continuous conversations",
                    "zh_Hans": "用于连续对话的会话ID"
                  },
                  "label": {
                    "en_US": "Session ID",
                    "zh_Hans": "会话ID"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "session_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A util tools for LLM translation, extra deployment is needed on AWS. Please refer Github Repo - https://github.com/aws-samples/rag-based-translation-with-dynamodb-and-bedrock",
                  "pt_BR": "A util tools for LLM translation, specific Lambda Function deployment is needed on AWS. Please refer Github Repo - https://github.com/aws-samples/rag-based-translation-with-dynamodb-and-bedrock",
                  "zh_Hans": "大语言模型翻译工具(专词映射获取)，需要在AWS上进行额外部署，可参考Github Repo - https://github.com/aws-samples/rag-based-translation-with-dynamodb-and-bedrock"
                },
                "llm": "A util tools for translation."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "AWS",
                "label": {
                  "en_US": "TranslateTool",
                  "pt_BR": "TranslateTool",
                  "zh_Hans": "翻译工具"
                },
                "name": "lambda_translate_utils"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "source content for translation",
                    "pt_BR": "source content for translation",
                    "zh_Hans": "待翻译原文"
                  },
                  "label": {
                    "en_US": "source content for translation",
                    "pt_BR": "source content for translation",
                    "zh_Hans": "待翻译原文"
                  },
                  "llm_description": "source content for translation",
                  "max": null,
                  "min": null,
                  "name": "text_content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "source language code",
                    "pt_BR": "source language code",
                    "zh_Hans": "原文语言代号"
                  },
                  "label": {
                    "en_US": "source language code",
                    "pt_BR": "source language code",
                    "zh_Hans": "原文语言代号"
                  },
                  "llm_description": "source language code",
                  "max": null,
                  "min": null,
                  "name": "src_lang",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "target language code",
                    "pt_BR": "target language code",
                    "zh_Hans": "目标语言代号"
                  },
                  "label": {
                    "en_US": "target language code",
                    "pt_BR": "target language code",
                    "zh_Hans": "目标语言代号"
                  },
                  "llm_description": "target language code",
                  "max": null,
                  "min": null,
                  "name": "dest_lang",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "region of Lambda",
                    "pt_BR": "region of Lambda",
                    "zh_Hans": "Lambda 所在的region"
                  },
                  "label": {
                    "en_US": "region of Lambda",
                    "pt_BR": "region of Lambda",
                    "zh_Hans": "Lambda 所在的region"
                  },
                  "llm_description": "region of Lambda",
                  "max": null,
                  "min": null,
                  "name": "aws_region",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "anthropic.claude-3-sonnet-20240229-v1:0",
                  "form": "form",
                  "human_description": {
                    "en_US": "LLM model_id in bedrock",
                    "pt_BR": "LLM model_id in bedrock",
                    "zh_Hans": "bedrock上的大语言模型model_id"
                  },
                  "label": {
                    "en_US": "LLM model_id in bedrock",
                    "pt_BR": "LLM model_id in bedrock",
                    "zh_Hans": "bedrock上的大语言模型model_id"
                  },
                  "llm_description": "LLM model_id in bedrock",
                  "max": null,
                  "min": null,
                  "name": "model_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "dictionary name for term mapping",
                    "pt_BR": "dictionary name for term mapping",
                    "zh_Hans": "专词映射表名称"
                  },
                  "label": {
                    "en_US": "dictionary name for term mapping",
                    "pt_BR": "dictionary name for term mapping",
                    "zh_Hans": "专词映射表名称"
                  },
                  "llm_description": "dictionary name for term mapping",
                  "max": null,
                  "min": null,
                  "name": "dictionary_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "term_mapping",
                  "form": "form",
                  "human_description": {
                    "en_US": "request type",
                    "pt_BR": "request type",
                    "zh_Hans": "请求类型"
                  },
                  "label": {
                    "en_US": "request type",
                    "pt_BR": "request type",
                    "zh_Hans": "请求类型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "request_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "term_mapping",
                        "zh_Hans": "专词映射"
                      },
                      "value": "term_mapping"
                    },
                    {
                      "label": {
                        "en_US": "segment_only",
                        "zh_Hans": "仅切词"
                      },
                      "value": "segment_only"
                    },
                    {
                      "label": {
                        "en_US": "translate",
                        "zh_Hans": "翻译内容"
                      },
                      "value": "translate"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "translate_tool",
                  "form": "form",
                  "human_description": {
                    "en_US": "AWS Lambda  for term mapping retrieval",
                    "pt_BR": "AWS Lambda  for term mapping retrieval",
                    "zh_Hans": "专词召回映射 - AWS Lambda"
                  },
                  "label": {
                    "en_US": "AWS Lambda for term mapping retrieval",
                    "pt_BR": "lambda name for term mapping retrieval",
                    "zh_Hans": "专词召回映射 - AWS Lambda"
                  },
                  "llm_description": "AWS Lambda  for term mapping retrieval",
                  "max": null,
                  "min": null,
                  "name": "lambda_name",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool to convert yaml to json using AWS Lambda.",
                  "pt_BR": "A tool to convert yaml to json using AWS Lambda.",
                  "zh_Hans": "将 YAML 转为 JSON 的工具（通过AWS Lambda）。"
                },
                "llm": "A tool to convert yaml to json."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "AWS",
                "label": {
                  "en_US": "LambdaYamlToJson",
                  "pt_BR": "LambdaYamlToJson",
                  "zh_Hans": "LambdaYamlToJson"
                },
                "name": "lambda_yaml_to_json"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "YAML content to convert for",
                    "pt_BR": "YAML content to convert for",
                    "zh_Hans": "YAML 内容"
                  },
                  "label": {
                    "en_US": "YAML content to convert for",
                    "pt_BR": "YAML content to convert for",
                    "zh_Hans": "YAML 内容"
                  },
                  "llm_description": "YAML content to convert for",
                  "max": null,
                  "min": null,
                  "name": "yaml_content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "region of lambda",
                    "pt_BR": "region of lambda",
                    "zh_Hans": "Lambda 所在的region"
                  },
                  "label": {
                    "en_US": "region of lambda",
                    "pt_BR": "region of lambda",
                    "zh_Hans": "Lambda 所在的region"
                  },
                  "llm_description": "region of lambda",
                  "max": null,
                  "min": null,
                  "name": "aws_region",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "name of lambda",
                    "pt_BR": "name of lambda",
                    "zh_Hans": "Lambda 名称"
                  },
                  "label": {
                    "en_US": "name of lambda",
                    "pt_BR": "name of lambda",
                    "zh_Hans": "Lambda 名称"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "lambda_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for generating and modifying images using AWS Bedrock's Nova Canvas model. Supports text-to-image, color-guided generation, image variation, inpainting, outpainting, and background removal. Input parameters reference https://docs.aws.amazon.com/nova/latest/userguide/image-gen-req-resp-structure.html",
                  "zh_Hans": "使用 AWS Bedrock 的 Nova Canvas 模型生成和修改图像的工具。支持文生图、颜色引导生成、图像变体、内补绘制、外补绘制和背景移除功能, 输入参数参考 https://docs.aws.amazon.com/nova/latest/userguide/image-gen-req-resp-structure.html。"
                },
                "llm": "Generate or modify images using AWS Bedrock's Nova Canvas model with multiple task types including text-to-image, color-guided generation, image variation, inpainting, outpainting, and background removal."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "AWS",
                "label": {
                  "en_US": "AWS Bedrock Nova Canvas",
                  "zh_Hans": "AWS Bedrock Nova Canvas"
                },
                "name": "nova_canvas"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": "TEXT_IMAGE",
                  "form": "llm",
                  "human_description": {
                    "en_US": "Type of image generation task (TEXT_IMAGE, COLOR_GUIDED_GENERATION, IMAGE_VARIATION, INPAINTING, OUTPAINTING, BACKGROUND_REMOVAL)",
                    "zh_Hans": "图像生成任务的类型（文生图、颜色引导生成、图像变体、内补绘制、外补绘制、背景移除）"
                  },
                  "label": {
                    "en_US": "Task Type",
                    "zh_Hans": "任务类型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "task_type",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Text description of the image you want to generate or modify",
                    "zh_Hans": "您想要生成或修改的图像的文本描述"
                  },
                  "label": {
                    "en_US": "Prompt",
                    "zh_Hans": "提示词"
                  },
                  "llm_description": "Describe the image you want to generate or how you want to modify the input image",
                  "max": null,
                  "min": null,
                  "name": "prompt",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The input image to modify (required for all modes except TEXT_IMAGE)",
                    "zh_Hans": "要修改的输入图像（除文生图外的所有模式都需要）"
                  },
                  "label": {
                    "en_US": "Input image s3 uri",
                    "zh_Hans": "输入图片的s3 uri"
                  },
                  "llm_description": "The input image you want to modify. Required for all modes except TEXT_IMAGE.",
                  "max": null,
                  "min": null,
                  "name": "image_input_s3uri",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The S3 URI where the generated image will be saved. If provided, the image will be uploaded with name format canvas-output-{timestamp}.png",
                    "zh_Hans": "生成的图像将保存到的S3 URI。如果提供，图像将以canvas-output-{timestamp}.png的格式上传"
                  },
                  "label": {
                    "en_US": "Output S3 URI",
                    "zh_Hans": "输出S3 URI"
                  },
                  "llm_description": "Optional S3 URI where the generated image will be uploaded. The image will be saved with a timestamp-based filename.",
                  "max": null,
                  "min": null,
                  "name": "image_output_s3uri",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Things you don't want in the generated image",
                    "zh_Hans": "您不想在生成的图像中出现的内容"
                  },
                  "label": {
                    "en_US": "Negative Prompt",
                    "zh_Hans": "负面提示词"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "negative_prompt",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 1024,
                  "form": "form",
                  "human_description": {
                    "en_US": "Width of the generated image",
                    "zh_Hans": "生成图像的宽度"
                  },
                  "label": {
                    "en_US": "Width",
                    "zh_Hans": "宽度"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "width",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 1024,
                  "form": "form",
                  "human_description": {
                    "en_US": "Height of the generated image",
                    "zh_Hans": "生成图像的高度"
                  },
                  "label": {
                    "en_US": "Height",
                    "zh_Hans": "高度"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "height",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 8,
                  "form": "form",
                  "human_description": {
                    "en_US": "How strongly the image should conform to the prompt",
                    "zh_Hans": "图像应该多大程度上符合提示词"
                  },
                  "label": {
                    "en_US": "CFG Scale",
                    "zh_Hans": "CFG比例"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "cfg_scale",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 0,
                  "form": "form",
                  "human_description": {
                    "en_US": "Random seed for image generation",
                    "zh_Hans": "图像生成的随机种子"
                  },
                  "label": {
                    "en_US": "Seed",
                    "zh_Hans": "种子值"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "us-east-1",
                  "form": "form",
                  "human_description": {
                    "en_US": "AWS region for Bedrock service",
                    "zh_Hans": "Bedrock 服务的 AWS 区域"
                  },
                  "label": {
                    "en_US": "AWS Region",
                    "zh_Hans": "AWS 区域"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "aws_region",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "standard",
                  "form": "form",
                  "human_description": {
                    "en_US": "Quality of the generated image (standard or premium)",
                    "zh_Hans": "生成图像的质量（标准或高级）"
                  },
                  "label": {
                    "en_US": "Quality",
                    "zh_Hans": "质量"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "quality",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "List of colors for color-guided generation",
                    "zh_Hans": "颜色引导生成的颜色列表"
                  },
                  "label": {
                    "en_US": "Colors",
                    "zh_Hans": "颜色"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "colors",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 0.5,
                  "form": "form",
                  "human_description": {
                    "en_US": "How similar the generated image should be to the input image (0.0 to 1.0)",
                    "zh_Hans": "生成的图像应该与输入图像的相似程度（0.0到1.0）"
                  },
                  "label": {
                    "en_US": "Similarity Strength",
                    "zh_Hans": "相似度强度"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "similarity_strength",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Text description to generate mask for inpainting/outpainting",
                    "zh_Hans": "用于生成内补绘制/外补绘制蒙版的文本描述"
                  },
                  "label": {
                    "en_US": "Mask Prompt",
                    "zh_Hans": "蒙版提示词"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "mask_prompt",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "DEFAULT",
                  "form": "form",
                  "human_description": {
                    "en_US": "Mode for outpainting (DEFAULT or other supported modes)",
                    "zh_Hans": "外补绘制的模式（DEFAULT或其他支持的模式）"
                  },
                  "label": {
                    "en_US": "Outpainting Mode",
                    "zh_Hans": "外补绘制模式"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "outpainting_mode",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "AWS S3 Writer and Reader",
                  "pt_BR": "AWS S3 Writer and Reader",
                  "zh_Hans": "读写S3 bucket中的文件"
                },
                "llm": "AWS S3 Writer and Reader"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "AWS",
                "label": {
                  "en_US": "AWS S3 Operator",
                  "pt_BR": "AWS S3 Operator",
                  "zh_Hans": "AWS S3 读写器"
                },
                "name": "s3_operator"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The text to write",
                    "pt_BR": "The text to write",
                    "zh_Hans": "待写入的文本"
                  },
                  "label": {
                    "en_US": "The text to write",
                    "pt_BR": "The text to write",
                    "zh_Hans": "待写入的文本"
                  },
                  "llm_description": "The text to write",
                  "max": null,
                  "min": null,
                  "name": "text_content",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "s3 uri",
                    "pt_BR": "s3 uri",
                    "zh_Hans": "s3 uri"
                  },
                  "label": {
                    "en_US": "s3 uri",
                    "pt_BR": "s3 uri",
                    "zh_Hans": "s3 uri"
                  },
                  "llm_description": "s3 uri",
                  "max": null,
                  "min": null,
                  "name": "s3_uri",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "region of bucket",
                    "pt_BR": "region of bucket",
                    "zh_Hans": "bucket 所在的region"
                  },
                  "label": {
                    "en_US": "region of bucket",
                    "pt_BR": "region of bucket",
                    "zh_Hans": "bucket 所在的region"
                  },
                  "llm_description": "region of bucket",
                  "max": null,
                  "min": null,
                  "name": "aws_region",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "read",
                  "form": "form",
                  "human_description": {
                    "en_US": "operation type",
                    "pt_BR": "operation type",
                    "zh_Hans": "操作类型"
                  },
                  "label": {
                    "en_US": "operation type",
                    "pt_BR": "operation type",
                    "zh_Hans": "操作类型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "operation_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "read",
                        "zh_Hans": "读"
                      },
                      "value": "read"
                    },
                    {
                      "label": {
                        "en_US": "write",
                        "zh_Hans": "写"
                      },
                      "value": "write"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to generate a presigned URL for the S3 object",
                    "zh_Hans": "是否生成S3对象的预签名URL"
                  },
                  "label": {
                    "en_US": "Generate presigned URL",
                    "zh_Hans": "生成预签名URL"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "generate_presign_url",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": 3600,
                  "form": "form",
                  "human_description": {
                    "en_US": "Expiration time in seconds for the presigned URL",
                    "zh_Hans": "预签名URL的有效期（秒）"
                  },
                  "label": {
                    "en_US": "Presigned URL expiration time",
                    "zh_Hans": "预签名URL有效期"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "presign_expiry",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool to detect Chinese toxicity",
                  "zh_Hans": "检测中文有害内容的工具"
                },
                "llm": "A tool that checks if Chinese content is safe for work"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "AWS",
                "label": {
                  "en_US": "Chinese Toxicity Detector",
                  "zh_Hans": "中文有害内容检测"
                },
                "name": "chinese_toxicity_detector"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "sagemaker endpoint for content moderation",
                    "zh_Hans": "内容审核的SageMaker端点"
                  },
                  "label": {
                    "en_US": "sagemaker endpoint for moderation",
                    "zh_Hans": "内容审核的SageMaker端点"
                  },
                  "llm_description": "sagemaker endpoint for content moderation",
                  "max": null,
                  "min": null,
                  "name": "sagemaker_endpoint",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "text content to be moderated",
                    "zh_Hans": "需要审核的文本内容"
                  },
                  "label": {
                    "en_US": "content text",
                    "zh_Hans": "待审核文本"
                  },
                  "llm_description": "text content to be moderated",
                  "max": null,
                  "min": null,
                  "name": "content_text",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "region of sagemaker endpoint",
                    "zh_Hans": "SageMaker 端点所在的region"
                  },
                  "label": {
                    "en_US": "region of sagemaker endpoint",
                    "zh_Hans": "SageMaker 端点所在的region"
                  },
                  "llm_description": "region of sagemaker endpoint",
                  "max": null,
                  "min": null,
                  "name": "aws_region",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for performing text similarity ranking. You can find deploy notebook on Github Repo - https://github.com/aws-samples/dify-aws-tool",
                  "pt_BR": "A tool for performing text similarity ranking.",
                  "zh_Hans": "Sagemaker重排序工具, 请参考 Github Repo - https://github.com/aws-samples/dify-aws-tool上的部署脚本"
                },
                "llm": "A tool for performing text similarity ranking. You can find deploy notebook on Github Repo - https://github.com/aws-samples/dify-aws-tool"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "AWS",
                "label": {
                  "en_US": "SagemakerRerank",
                  "pt_BR": "SagemakerRerank",
                  "zh_Hans": "Sagemaker重排序"
                },
                "name": "sagemaker_text_rerank"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "sagemaker endpoint for reranking",
                    "pt_BR": "sagemaker endpoint for reranking",
                    "zh_Hans": "重排序的SageMaker 端点"
                  },
                  "label": {
                    "en_US": "sagemaker endpoint for reranking",
                    "pt_BR": "sagemaker endpoint for reranking",
                    "zh_Hans": "重排序的SageMaker 端点"
                  },
                  "llm_description": "sagemaker endpoint for reranking",
                  "max": null,
                  "min": null,
                  "name": "sagemaker_endpoint",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "key words for searching",
                    "pt_BR": "key words for searching",
                    "zh_Hans": "查询关键词"
                  },
                  "label": {
                    "en_US": "Query string",
                    "pt_BR": "Query string",
                    "zh_Hans": "查询语句"
                  },
                  "llm_description": "key words for searching",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "searched candidates by query",
                    "pt_BR": "searched candidates by query",
                    "zh_Hans": "查询文本搜到候选文本"
                  },
                  "label": {
                    "en_US": "text candidates",
                    "pt_BR": "text candidates",
                    "zh_Hans": "候选文本"
                  },
                  "llm_description": "searched candidates by query",
                  "max": null,
                  "min": null,
                  "name": "candidate_texts",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 5,
                  "form": "form",
                  "human_description": {
                    "en_US": "Limit for results count",
                    "pt_BR": "Limit for results count",
                    "zh_Hans": "返回个数限制"
                  },
                  "label": {
                    "en_US": "Limit for results count",
                    "pt_BR": "Limit for results count",
                    "zh_Hans": "返回个数限制"
                  },
                  "llm_description": "",
                  "max": 10,
                  "min": 1,
                  "name": "topk",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "region of sagemaker endpoint",
                    "pt_BR": "region of sagemaker endpoint",
                    "zh_Hans": "SageMaker 端点所在的region"
                  },
                  "label": {
                    "en_US": "region of sagemaker endpoint",
                    "pt_BR": "region of sagemaker endpoint",
                    "zh_Hans": "SageMaker 端点所在的region"
                  },
                  "llm_description": "region of sagemaker endpoint",
                  "max": null,
                  "min": null,
                  "name": "aws_region",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for Speech synthesis - https://github.com/aws-samples/dify-aws-tool",
                  "pt_BR": "A tool for Speech synthesis.",
                  "zh_Hans": "Sagemaker语音合成工具, 请参考 Github Repo - https://github.com/aws-samples/dify-aws-tool上的部署脚本"
                },
                "llm": "A tool for Speech synthesis. You can find deploy notebook on Github Repo - https://github.com/aws-samples/dify-aws-tool"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "AWS",
                "label": {
                  "en_US": "SagemakerTTS",
                  "pt_BR": "SagemakerTTS",
                  "zh_Hans": "Sagemaker语音合成"
                },
                "name": "sagemaker_tts"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "sagemaker endpoint for tts",
                    "pt_BR": "sagemaker endpoint for tts",
                    "zh_Hans": "语音生成的SageMaker端点"
                  },
                  "label": {
                    "en_US": "sagemaker endpoint for tts",
                    "pt_BR": "sagemaker endpoint for tts",
                    "zh_Hans": "语音生成的SageMaker端点"
                  },
                  "llm_description": "sagemaker endpoint for tts",
                  "max": null,
                  "min": null,
                  "name": "sagemaker_endpoint",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "tts text",
                    "pt_BR": "tts text",
                    "zh_Hans": "语音合成原文"
                  },
                  "label": {
                    "en_US": "tts text",
                    "pt_BR": "tts text",
                    "zh_Hans": "语音合成原文"
                  },
                  "llm_description": "tts text",
                  "max": null,
                  "min": null,
                  "name": "tts_text",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "tts infer type",
                    "pt_BR": "tts infer type",
                    "zh_Hans": "合成方式"
                  },
                  "label": {
                    "en_US": "tts infer type",
                    "pt_BR": "tts infer type",
                    "zh_Hans": "合成方式"
                  },
                  "llm_description": "tts infer type",
                  "max": null,
                  "min": null,
                  "name": "tts_infer_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "preset voice",
                        "zh_Hans": "预置音色"
                      },
                      "value": "PresetVoice"
                    },
                    {
                      "label": {
                        "en_US": "clone voice",
                        "zh_Hans": "克隆音色"
                      },
                      "value": "CloneVoice"
                    },
                    {
                      "label": {
                        "en_US": "clone crossLingual voice",
                        "zh_Hans": "克隆音色(跨语言)"
                      },
                      "value": "CloneVoice_CrossLingual"
                    },
                    {
                      "label": {
                        "en_US": "instruct voice",
                        "zh_Hans": "指令音色"
                      },
                      "value": "InstructVoice"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "preset voice",
                    "pt_BR": "preset voice",
                    "zh_Hans": "预置音色"
                  },
                  "label": {
                    "en_US": "preset voice",
                    "pt_BR": "preset voice",
                    "zh_Hans": "预置音色"
                  },
                  "llm_description": "preset voice",
                  "max": null,
                  "min": null,
                  "name": "voice",
                  "options": [
                    {
                      "label": {
                        "en_US": "zh-cn male",
                        "zh_Hans": "中文男"
                      },
                      "value": "中文男"
                    },
                    {
                      "label": {
                        "en_US": "zh-cn female",
                        "zh_Hans": "中文女"
                      },
                      "value": "中文女"
                    },
                    {
                      "label": {
                        "en_US": "zh-TW female",
                        "zh_Hans": "粤语女"
                      },
                      "value": "粤语女"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "clone voice link",
                    "pt_BR": "clone voice link",
                    "zh_Hans": "克隆音频链接"
                  },
                  "label": {
                    "en_US": "clone voice link",
                    "pt_BR": "clone voice link",
                    "zh_Hans": "克隆音频链接"
                  },
                  "llm_description": "clone voice link",
                  "max": null,
                  "min": null,
                  "name": "mock_voice_audio",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "text of clone voice",
                    "pt_BR": "text of clone voice",
                    "zh_Hans": "克隆音频对应文本"
                  },
                  "label": {
                    "en_US": "text of clone voice",
                    "pt_BR": "text of clone voice",
                    "zh_Hans": "克隆音频对应文本"
                  },
                  "llm_description": "text of clone voice",
                  "max": null,
                  "min": null,
                  "name": "mock_voice_text",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "instruct prompt for voice",
                    "pt_BR": "instruct prompt for voice",
                    "zh_Hans": "音色指令文本"
                  },
                  "label": {
                    "en_US": "instruct prompt for voice",
                    "pt_BR": "instruct prompt for voice",
                    "zh_Hans": "音色指令文本"
                  },
                  "llm_description": "instruct prompt for voice",
                  "max": null,
                  "min": null,
                  "name": "voice_instruct_prompt",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "region of sagemaker endpoint",
                    "pt_BR": "region of sagemaker endpoint",
                    "zh_Hans": "SageMaker 端点所在的region"
                  },
                  "label": {
                    "en_US": "region of sagemaker endpoint",
                    "pt_BR": "region of sagemaker endpoint",
                    "zh_Hans": "SageMaker 端点所在的region"
                  },
                  "llm_description": "region of sagemaker endpoint",
                  "max": null,
                  "min": null,
                  "name": "aws_region",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for ASR (Automatic Speech Recognition) - https://github.com/aws-samples/dify-aws-tool",
                  "pt_BR": "A tool for ASR (Automatic Speech Recognition).",
                  "zh_Hans": "AWS 语音识别转录服务, 请参考 https://aws.amazon.com/cn/pm/transcribe/#Learn_More_About_Amazon_Transcribe"
                },
                "llm": "A tool for ASR (Automatic Speech Recognition)."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "AWS",
                "label": {
                  "en_US": "TranscribeASR",
                  "pt_BR": "TranscribeASR",
                  "zh_Hans": "Transcribe语音识别转录"
                },
                "name": "transcribe_asr"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "video or audio file url for transcribe",
                    "pt_BR": "video or audio file url for transcribe",
                    "zh_Hans": "语音或者视频文件url"
                  },
                  "label": {
                    "en_US": "video or audio file url for transcribe",
                    "pt_BR": "video or audio file url for transcribe",
                    "zh_Hans": "语音或者视频文件url"
                  },
                  "llm_description": "video or audio file url for transcribe",
                  "max": null,
                  "min": null,
                  "name": "file_url",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The language code used to create your transcription job.  refer to :https://docs.aws.amazon.com/transcribe/latest/dg/supported-languages.html",
                    "pt_BR": "The language code used to create your transcription job.  refer to :https://docs.aws.amazon.com/transcribe/latest/dg/supported-languages.html",
                    "zh_Hans": "语言编码,例如zh-CN, en-US 可参考 https://docs.aws.amazon.com/transcribe/latest/dg/supported-languages.html"
                  },
                  "label": {
                    "en_US": "Language Code",
                    "pt_BR": "Language Code",
                    "zh_Hans": "语言编码"
                  },
                  "llm_description": "The language code used to create your transcription job.",
                  "max": null,
                  "min": null,
                  "name": "language_code",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "Automactically Identify Language",
                    "pt_BR": "Automactically Identify Language",
                    "zh_Hans": "自动识别语言"
                  },
                  "label": {
                    "en_US": "Automactically Identify Language",
                    "pt_BR": "Automactically Identify Language",
                    "zh_Hans": "自动识别语言"
                  },
                  "llm_description": "Enable Automactically Identify Language",
                  "max": null,
                  "min": null,
                  "name": "identify_language",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Automactically Identify Multiple Languages",
                    "pt_BR": "Automactically Identify Multiple Languages",
                    "zh_Hans": "自动识别多种语言"
                  },
                  "label": {
                    "en_US": "Automactically Identify Multiple Languages",
                    "pt_BR": "Automactically Identify Multiple Languages",
                    "zh_Hans": "自动识别多种语言"
                  },
                  "llm_description": "Enable Automactically Identify Multiple Languages",
                  "max": null,
                  "min": null,
                  "name": "identify_multiple_languages",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Seperated by |, e.g:zh-CN|en-US, You can specify two or more language codes that represent the languages you think may be present in your media",
                    "pt_BR": "Seperated by |, e.g:zh-CN|en-US, You can specify two or more language codes that represent the languages you think may be present in your media",
                    "zh_Hans": "您可以指定两个或更多的语言代码来表示您认为可能出现在媒体中的语言。用｜分隔,如 zh-CN|en-US"
                  },
                  "label": {
                    "en_US": "Language Options",
                    "pt_BR": "Language Options",
                    "zh_Hans": "语言种类选项"
                  },
                  "llm_description": "Seperated by |, e.g:zh-CN|en-US, You can specify two or more language codes that represent the languages you think may be present in your media",
                  "max": null,
                  "min": null,
                  "name": "language_options",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "s3 bucket name to store transcribe files  (don't add prefix s3://)",
                    "pt_BR": "s3 bucket name to store transcribe files  (don't add prefix s3://)",
                    "zh_Hans": "s3 存储桶名称,用于存储转录文件  (不需要前缀 s3://)"
                  },
                  "label": {
                    "en_US": "s3 bucket name",
                    "pt_BR": "s3 bucket name",
                    "zh_Hans": "s3 存储桶名称"
                  },
                  "llm_description": "s3 bucket name to store transcribe files",
                  "max": null,
                  "min": null,
                  "name": "s3_bucket_name",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "Enables speaker partitioning (diarization) in your transcription output",
                    "pt_BR": "Enables speaker partitioning (diarization) in your transcription output",
                    "zh_Hans": "在转录输出中启用说话人分区（说话人分离）"
                  },
                  "label": {
                    "en_US": "ShowSpeakerLabels",
                    "pt_BR": "ShowSpeakerLabels",
                    "zh_Hans": "显示说话人标签"
                  },
                  "llm_description": "Enables speaker partitioning (diarization) in your transcription output",
                  "max": null,
                  "min": null,
                  "name": "ShowSpeakerLabels",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": 2,
                  "form": "form",
                  "human_description": {
                    "en_US": "Specify the maximum number of speakers you want to partition in your media",
                    "pt_BR": "Specify the maximum number of speakers you want to partition in your media",
                    "zh_Hans": "指定您希望在媒体中划分的最多演讲者数量。"
                  },
                  "label": {
                    "en_US": "MaxSpeakerLabels",
                    "pt_BR": "MaxSpeakerLabels",
                    "zh_Hans": "说话人标签数量"
                  },
                  "llm_description": "Specify the maximum number of speakers you want to partition in your media",
                  "max": null,
                  "min": null,
                  "name": "MaxSpeakerLabels",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Please enter the AWS region for the transcribe service, for example 'us-east-1'.",
                    "zh_Hans": "请输入Transcribe的 AWS 区域，例如 'us-east-1'。"
                  },
                  "label": {
                    "en_US": "AWS Region",
                    "zh_Hans": "AWS 区域"
                  },
                  "llm_description": "Please enter the AWS region for the transcribe service, for example 'us-east-1'.",
                  "max": null,
                  "min": null,
                  "name": "aws_region",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for retrieving relevant information from Amazon OpenSearch.",
                  "pt_BR": "A tool for retrieving relevant information from Amazon OpenSearch.",
                  "zh_Hans": "Amazon OpenSearch 检索工具"
                },
                "llm": "A tool for retrieving relevant information from Amazon OpenSearch."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "aws",
                "label": {
                  "en_US": "OpenSearch Retrieve",
                  "pt_BR": "OpenSearch Retrieve",
                  "zh_Hans": "OpenSearch检索"
                },
                "name": "opensearch_retrieve"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "OpenSearch Endpoint",
                    "pt_BR": "OpenSearch Endpoint",
                    "zh_Hans": "OpenSearch 端点"
                  },
                  "label": {
                    "en_US": "OpenSearch Endpoint",
                    "pt_BR": "OpenSearch Endpoint",
                    "zh_Hans": "OpenSearch 端点"
                  },
                  "llm_description": "OpenSearch Endpoint to retrieve from",
                  "max": null,
                  "min": null,
                  "name": "opensearch_endpoint",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Target Index Name",
                    "pt_BR": "Target Index Name",
                    "zh_Hans": "目标索引名称"
                  },
                  "label": {
                    "en_US": "Target Index Name",
                    "pt_BR": "Target Index Name",
                    "zh_Hans": "目标索引名称"
                  },
                  "llm_description": "The target of index name",
                  "max": null,
                  "min": null,
                  "name": "index_name",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Image S3 Path",
                    "pt_BR": "Image S3 Path",
                    "zh_Hans": "图像s3路径"
                  },
                  "label": {
                    "en_US": "Image S3 Path",
                    "pt_BR": "Image S3 Path",
                    "zh_Hans": "图像s3路径"
                  },
                  "llm_description": "s3 path of image",
                  "max": null,
                  "min": null,
                  "name": "image_s3_path",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Query Text",
                    "pt_BR": "Query Text",
                    "zh_Hans": "查询文本"
                  },
                  "label": {
                    "en_US": "Query Text",
                    "pt_BR": "Query Text",
                    "zh_Hans": "查询文本"
                  },
                  "llm_description": "query text",
                  "max": null,
                  "min": null,
                  "name": "query_text",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "pic_emb",
                  "form": "llm",
                  "human_description": {
                    "en_US": "Embedding Field Name",
                    "pt_BR": "Embedding Field Name",
                    "zh_Hans": "向量字段名称"
                  },
                  "label": {
                    "en_US": "Embedding Field Name",
                    "pt_BR": "Embedding Field Name",
                    "zh_Hans": "向量字段名称"
                  },
                  "llm_description": "embedding field name",
                  "max": null,
                  "min": null,
                  "name": "embedding_field",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "s3_uri,pic_name",
                  "form": "llm",
                  "human_description": {
                    "en_US": "metadata fields",
                    "pt_BR": "metadata fields",
                    "zh_Hans": "元信息字段列表"
                  },
                  "label": {
                    "en_US": "Metadata Fields",
                    "pt_BR": "Metadata Fields",
                    "zh_Hans": "元信息字段列表"
                  },
                  "llm_description": "metadata fields",
                  "max": null,
                  "min": null,
                  "name": "metadata_fields",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 5,
                  "form": "form",
                  "human_description": {
                    "en_US": "Results Count",
                    "pt_BR": "Results Count",
                    "zh_Hans": "结果数量"
                  },
                  "label": {
                    "en_US": "Results Count",
                    "pt_BR": "Results Count",
                    "zh_Hans": "结果数量"
                  },
                  "llm_description": "",
                  "max": 10,
                  "min": 1,
                  "name": "topk",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "embedding size",
                    "pt_BR": "embedding size",
                    "zh_Hans": "纬度"
                  },
                  "label": {
                    "en_US": "embedding size",
                    "pt_BR": "embedding size",
                    "zh_Hans": "纬度"
                  },
                  "llm_description": "embedding size",
                  "max": null,
                  "min": null,
                  "name": "vector_size",
                  "options": [
                    {
                      "label": {
                        "en_US": "1024",
                        "zh_Hans": "1024"
                      },
                      "value": "1024"
                    },
                    {
                      "label": {
                        "en_US": "512",
                        "zh_Hans": "512"
                      },
                      "value": "512"
                    },
                    {
                      "label": {
                        "en_US": "384",
                        "zh_Hans": "384"
                      },
                      "value": "384"
                    },
                    {
                      "label": {
                        "en_US": "256",
                        "zh_Hans": "256"
                      },
                      "value": "256"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "SEMANTIC",
                  "form": "form",
                  "human_description": {
                    "en_US": "search type",
                    "pt_BR": "search type",
                    "zh_Hans": "搜索类型"
                  },
                  "label": {
                    "en_US": "search type",
                    "pt_BR": "search type",
                    "zh_Hans": "搜索类型"
                  },
                  "llm_description": "search type",
                  "max": null,
                  "min": null,
                  "name": "search_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "SEMANTIC",
                        "zh_Hans": "语义搜索"
                      },
                      "value": "SEMANTIC"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Model Id",
                    "pt_BR": "Model Id",
                    "zh_Hans": "向量模型ID"
                  },
                  "label": {
                    "en_US": "Model Id",
                    "pt_BR": "Model Id",
                    "zh_Hans": "向量模型ID"
                  },
                  "llm_description": "embedding model id",
                  "max": null,
                  "min": null,
                  "name": "embedding_model_id",
                  "options": [
                    {
                      "label": {
                        "en_US": "amazon.titan-embed-image-v1",
                        "zh_Hans": "amazon.titan-embed-image-v1"
                      },
                      "value": "amazon.titan-embed-image-v1"
                    },
                    {
                      "label": {
                        "en_US": "amazon.titan-embed-text-v1",
                        "zh_Hans": "amazon.titan-embed-text-v1"
                      },
                      "value": "amazon.titan-embed-text-v1"
                    },
                    {
                      "label": {
                        "en_US": "amazon.titan-embed-text-v2:0",
                        "zh_Hans": "amazon.titan-embed-text-v2:0"
                      },
                      "value": "amazon.titan-embed-text-v2:0"
                    },
                    {
                      "label": {
                        "en_US": "amazon.titan-embed-text-v2:0",
                        "zh_Hans": "amazon.titan-embed-text-v2:0"
                      },
                      "value": "amazon.titan-embed-text-v2:0"
                    },
                    {
                      "label": {
                        "en_US": "cohere.embed-english-v3",
                        "zh_Hans": "cohere.embed-english-v3"
                      },
                      "value": "cohere.embed-english-v3"
                    },
                    {
                      "label": {
                        "en_US": "cohere.embed-multilingual-v3",
                        "zh_Hans": "cohere.embed-multilingual-v3"
                      },
                      "value": "cohere.embed-multilingual-v3"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "AWS region where the Bedrock Knowledge Base is located",
                    "pt_BR": "AWS region where the Bedrock Knowledge Base is located",
                    "zh_Hans": "Bedrock知识库所在的AWS区域"
                  },
                  "label": {
                    "en_US": "AWS Region",
                    "pt_BR": "AWS Region",
                    "zh_Hans": "AWS 区域"
                  },
                  "llm_description": "AWS region where the Bedrock Knowledge Base is located",
                  "max": null,
                  "min": null,
                  "name": "aws_region",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-17T01:37:35Z",
        "version_updated_at": "2025-03-17T01:37:35Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Judge0 CE is an open-source code execution system. Support various languages, including C, C++, Java, Python, Ruby, etc.",
          "pt_BR": "Judge0 CE é um sistema de execução de código de código aberto. Suporta várias linguagens, incluindo C, C++, Java, Python, Ruby, etc.",
          "zh_Hans": "Judge0 CE 是一个开源的代码执行系统。支持多种语言，包括 C、C++、Java、Python、Ruby 等。"
        },
        "category": "tool",
        "created_at": "2024-11-29T09:58:48Z",
        "endpoint": {},
        "icon": "langgenius/packages/judge0ce/_assets/icon.svg",
        "index_id": "langgenius___judge0ce",
        "install_count": 492,
        "introduction": "# Overview\n[Judge0 CE](https://ce.judge0.com/) is a robust online code execution and compilation platform. This plugin allows users to compile and run code in multiple programming languages directly within workflows, making it ideal for automating tasks such as code evaluation, testing, or educational exercises. \n\nBy leveraging Judge0 CE, you can execute code snippets securely and efficiently in a sandboxed environment.\n\n# Configure\n\n## 1. Install the Plugin\n1. Go to the **Dify Marketplace**.\n2. Search for the **Judge0 CE Plugin**.\n3. Click \"Install\" to add the plugin to your workspace.\n![](./_assets/judge0ce_install.PNG)\n\n## 2. Obtain API Key\n1. Visit [RapidAPI](https://rapidapi.com/judge0-official/api/judge0-ce).\n2. Sign up or log in to your RapidAPI account.\n3. Subscribe to the Judge0 CE API and generate your API Key from the RapidAPI dashboard.\n\n## 3. Authorize the Plugin\n1. Add any of the Judge0 CE tools (e.g., \"Code Execution\") to your workflow in Dify.\n2. Click on the \"To authorize\" button in the tool configuration panel.\n3. Enter your RapidAPI API Key in the provided field.\n4. Save your credentials to complete the authorization process.",
        "label": {
          "en_US": "Judge0 CE",
          "pt_BR": "Judge0 CE",
          "zh_Hans": "Judge0 CE"
        },
        "latest_package_identifier": "langgenius/judge0ce:0.0.2@7f2f2bcb35c3413267a566ec6bc48fe7684613d01428618ff39a359250621cf2",
        "latest_version": "0.0.2",
        "model": {},
        "name": "judge0ce",
        "org": "langgenius",
        "plugin_id": "langgenius/judge0ce",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/judge0ce.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "other"
          },
          {
            "name": "utilities"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "RapidAPI Key",
                "pt_BR": "RapidAPI Key",
                "zh_Hans": "RapidAPI Key"
              },
              "name": "X-RapidAPI-Key",
              "options": null,
              "placeholder": {
                "en_US": "Enter your RapidAPI Key",
                "pt_BR": "Insira sua RapidAPI Key",
                "zh_Hans": "输入你的 RapidAPI Key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://rapidapi.com/judge0-official/api/judge0-ce"
            }
          ],
          "identity": {
            "author": "Richards_Tu",
            "description": {
              "en_US": "Judge0 CE is an open-source code execution system. Support various languages, including C, C++, Java, Python, Ruby, etc.",
              "pt_BR": "Judge0 CE é um sistema de execução de código de código aberto. Suporta várias linguagens, incluindo C, C++, Java, Python, Ruby, etc.",
              "zh_Hans": "Judge0 CE 是一个开源的代码执行系统。支持多种语言，包括 C、C++、Java、Python、Ruby 等。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Judge0 CE",
              "pt_BR": "Judge0 CE",
              "zh_Hans": "Judge0 CE"
            },
            "name": "judge0ce",
            "tags": [
              "utilities",
              "other"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool for executing code and getting the result.",
                  "zh_Hans": "一个用于执行代码并获取结果的工具。"
                },
                "llm": "This tool is used for executing code and getting the result."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Richards_Tu",
                "label": {
                  "en_US": "Submit Code Execution Task to Judge0 CE and get execution result.",
                  "zh_Hans": "提交代码执行任务到 Judge0 CE 并获取执行结果。"
                },
                "name": "submitCodeExecutionTask"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The source code to be executed.",
                    "zh_Hans": "要执行的源代码。"
                  },
                  "label": {
                    "en_US": "Source Code",
                    "zh_Hans": "源代码"
                  },
                  "llm_description": "The source code to be executed.",
                  "max": null,
                  "min": null,
                  "name": "source_code",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the language in which the source code is written.",
                    "zh_Hans": "源代码所使用的语言的 ID。"
                  },
                  "label": {
                    "en_US": "Language ID",
                    "zh_Hans": "语言 ID"
                  },
                  "llm_description": "The ID of the language in which the source code is written. For example, 50 for C++, 71 for Python, etc.",
                  "max": null,
                  "min": null,
                  "name": "language_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The standard input to be provided to the program.",
                    "zh_Hans": "提供给程序的标准输入。"
                  },
                  "label": {
                    "en_US": "Standard Input",
                    "zh_Hans": "标准输入"
                  },
                  "llm_description": "The standard input to be provided to the program. Optional.",
                  "max": null,
                  "min": null,
                  "name": "stdin",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The expected output of the program. Used for comparison in some scenarios.",
                    "zh_Hans": "程序的期望输出。在某些场景下用于比较。"
                  },
                  "label": {
                    "en_US": "Expected Output",
                    "zh_Hans": "期望输出"
                  },
                  "llm_description": "The expected output of the program. Used for comparison in some scenarios. Optional.",
                  "max": null,
                  "min": null,
                  "name": "expected_output",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Base64 encoded additional files for the submission.",
                    "zh_Hans": "提交的 Base64 编码的附加文件。"
                  },
                  "label": {
                    "en_US": "Additional Files",
                    "zh_Hans": "附加文件"
                  },
                  "llm_description": "Base64 encoded additional files for the submission. Optional.",
                  "max": null,
                  "min": null,
                  "name": "additional_files",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:15:23Z",
        "version_updated_at": "2025-02-17T07:15:23Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "A simple plugin that provides waiting functionality in Dify workflows",
          "zh_Hans": "在Dify工作流中提供等待功能的简单插件"
        },
        "category": "tool",
        "created_at": "2025-04-10T14:54:07Z",
        "endpoint": {},
        "icon": "agimaster/packages/justwait/_assets/icon.svg",
        "index_id": "agimaster___justwait",
        "install_count": 480,
        "introduction": "# JustWait Plugin for Dify\n\n## Introduction\n\nThis plugin was developed because I've had enough of having to use the CODE plugin specifically to write Python snippets to implement sleep functionality, which is essential in flow loops. The JustWait plugin provides simple waiting capabilities, similar to Python's `time.sleep()`, allowing you to easily implement delays in your Dify workflows.\n\n## Features\n\nJustWait plugin offers two main tools:\n\n1. **Wait** - Wait for a specified number of seconds\n   - Parameter: `seconds` - Number of seconds to wait\n\n2. **Random Wait** - Wait for a random period within a specified range\n   - Parameters:\n     - `min_seconds` - Minimum number of seconds to wait\n     - `max_seconds` - Maximum number of seconds to wait\n\n![](./_assets/justwait_1.jpg)\n\n## Usage Examples\n\n![](./_assets/justwait_2.jpg)\n\n### Using the Wait Tool in Workflows\n1. Add the JustWait tool to your Dify workflow\n2. Select the Wait tool\n3. Set the `seconds` parameter to your desired wait time (e.g., 5)\n4. Run the workflow, and it will pause for 5 seconds at this step before continuing\n\n### Using the Random Wait Tool in Workflows\n1. Add the JustWait tool to your Dify workflow\n2. Select the Random Wait tool\n3. Set the `min_seconds` parameter (e.g., 3) and `max_seconds` parameter (e.g., 10)\n4. Run the workflow, and it will pause for a random period between 3-10 seconds before continuing\n\n## Use Cases\n\n- Adding delays in loop operations to avoid too frequent API requests\n- Simulating intervals between user operations\n- Controlling execution speed when testing workflows\n- Implementing simple polling mechanisms while waiting for external services to respond\n\n## Important Notes\n\n- This plugin does not require any authentication\n- It does not collect any user data\n- When setting wait times, please consider reasonable ranges, as excessively long waits may cause workflow execution timeouts \n- Python code reference: https://github.com/AGIMaster/dify-plugin-my-development/tree/master/tools/justwait",
        "label": {
          "en_US": "Just Wait",
          "zh_Hans": "Just Wait"
        },
        "latest_package_identifier": "agimaster/justwait:0.0.2@b91dbf4317fb40575f2631ebf8cecae7db08ee8da2284c418a79b564fa583a38",
        "latest_version": "0.0.2",
        "model": {},
        "name": "justwait",
        "org": "agimaster",
        "plugin_id": "agimaster/justwait",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/justwait.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "privacy.md",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "app": {
              "enabled": false
            },
            "endpoint": {
              "enabled": false
            },
            "model": {
              "enabled": false,
              "llm": false,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "storage": {
              "enabled": false,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "utilities"
          }
        ],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "AGIMater",
            "description": {
              "en_US": "Simple waiting functionality for Dify workflows",
              "zh_Hans": "为Dify工作流提供简单的等待功能"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "JustWait",
              "zh_Hans": "JustWait"
            },
            "name": "justwait",
            "tags": [
              "utilities",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Wait for a specified number of seconds, similar to Python's time.sleep() function",
                  "zh_Hans": "等待指定的秒数，类似于Python的time.sleep()函数"
                },
                "llm": "A tool that pauses execution for a specified number of seconds. Use this to implement delays in workflows."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "AGIMaster",
                "label": {
                  "en_US": "Wait",
                  "zh_Hans": "等待"
                },
                "name": "wait"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The number of seconds to wait",
                    "zh_Hans": "等待的秒数"
                  },
                  "label": {
                    "en_US": "Seconds",
                    "zh_Hans": "秒数"
                  },
                  "llm_description": "The number of seconds to pause execution",
                  "max": null,
                  "min": null,
                  "name": "seconds",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Wait for a random number of seconds within a specified range",
                  "zh_Hans": "在指定范围内随机等待秒数"
                },
                "llm": "A tool that pauses execution for a random number of seconds within a specified range. The random value follows a uniform distribution between min_seconds and max_seconds."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "AGIMaster",
                "label": {
                  "en_US": "Random Wait",
                  "zh_Hans": "随机等待"
                },
                "name": "random_wait"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The minimum number of seconds to wait",
                    "zh_Hans": "最小等待秒数"
                  },
                  "label": {
                    "en_US": "Min Seconds",
                    "zh_Hans": "最小秒数"
                  },
                  "llm_description": "The minimum number of seconds for the random wait",
                  "max": null,
                  "min": null,
                  "name": "min_seconds",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The maximum number of seconds to wait",
                    "zh_Hans": "最大等待秒数"
                  },
                  "label": {
                    "en_US": "Max Seconds",
                    "zh_Hans": "最大秒数"
                  },
                  "llm_description": "The maximum number of seconds for the random wait",
                  "max": null,
                  "min": null,
                  "name": "max_seconds",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-13T16:35:23Z",
        "version_updated_at": "2025-04-13T16:35:23Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "The image generation API provided by FAL."
        },
        "category": "tool",
        "created_at": "2025-01-02T06:11:25Z",
        "endpoint": {},
        "icon": "langgenius/packages/fal/_assets/icon.svg",
        "index_id": "langgenius___fal",
        "install_count": 466,
        "introduction": "## Overview\n\n**FAL** is an advanced suite of tools designed for AI-powered image generation and audio transcription. In **Dify**, FAL provides multiple services, including image creation with models like **FLUX.1 [pro]** and **FLUX 1.1 [pro] ultra**, allowing users to generate high-quality visuals with customizable parameters. Additionally, FAL offers **Wizper**, a transcription tool that converts audio files into text with precision, supporting various languages and flexible chunk-level configurations.\n\n## Configuration\n\nTo start using FAL, follow these steps:\n\n1. **Install FAL Tool**\nDownload and install the FAL tool from the Plugin Marketplace to integrate it into your workflows.\n\n2. **Apply for FAL API Key**\nGo to the FAL API Keys page, create a new API Key, and ensure that your account is properly set up with the required access and balance.\n\n3. **Authorize FAL**\nNavigate to **Tools > FAL > To Authorize** in Dify, and input your API Key to enable the tool.\n\n![](./_assets/fal-01.png)\n\n## Tool Features\n\nThe FAL tool provides five actions for image generation and audio transcription.\n\n### FLUX.1 [PRO] NEW\n\nAn optimized version of **FLUX.1 [PRO]**, designed for faster processing while maintaining professional-grade image quality. Simply follow the UI instructions to input the required parameters and use the tool to generate high-quality images.\n\n<img src=\"./_assets/fal-02.png\" width=\"400\" />\n\n### FLUX 1.1 [PRO] ULTRA\n\nThe latest and most advanced version of FLUX.1 offers superior image quality and efficiency. Recommended for users seeking cutting-edge performance.\n\n<img src=\"./_assets/fal-03.png\" width=\"400\" />\n\n### FLUX.1 [DEV]\n\nA 12-billion parameter flow transformer model optimized for high-quality image generation from text. Best suited for experimental or custom use cases.\n\n<img src=\"./_assets/fal-04.png\" width=\"400\" />\n\n### FLUX 1.1 [PRO]\n\nAn enhanced version of FLUX.1 [pro], delivering improved image generation capabilities with exceptional detail and clarity. Ideal for professional projects.\n\n<img src=\"./_assets/fal-05.png\" width=\"400\" />\n\n### Wizper\n\nA transcription tool powered by the Whisper model, designed to convert audio files into text with high accuracy.\n\n<img src=\"./_assets/fal-06.png\" width=\"400\" />\n\n## Usage\n\n### Chatflow / Workflow Apps\n\n1. Add the FAL node into your Chatflow or Workflow pipeline.\n2. Select one of FAL's actions (e.g., FLUX.1 [pro] ultra for high-quality image generation).\n3. Input the required parameters, such as text prompts for image generation or audio files for transcription.\n4. Execute the pipeline to generate images or transcribe audio data.\n\n![](./_assets/fal-07.png)\n\n### Agent Apps\n\n1. Add the FAL tool to the Agent application.\n2. Send the desired text prompt or upload an audio file to generate an image or transcribe the content.\n3. Use the generated image or transcription in real-time applications to enhance user interaction and functionality.\n\n![](./_assets/fal-08.png)\n\nBy combining the capabilities of FAL's image generation and transcription tools, you can streamline workflows, enhance creativity, and optimize productivity.\n",
        "label": {
          "en_US": "FAL"
        },
        "latest_package_identifier": "langgenius/fal:0.0.3@8d19055ef7dad86c11610ad43d6b8d4726a20e3bf6f81277fa9414d1d17ad2ba",
        "latest_version": "0.0.3",
        "model": {},
        "name": "fal",
        "org": "langgenius",
        "plugin_id": "langgenius/fal",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/fal.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "image"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "FAL API Key"
              },
              "name": "fal_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your FAL API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://fal.ai/dashboard/keys"
            }
          ],
          "identity": {
            "author": "Kalo Chin",
            "description": {
              "en_US": "The image generation API provided by FAL."
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "FAL"
            },
            "name": "fal",
            "tags": [
              "image"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "FLUX.1 [pro] new is an accelerated version of FLUX.1 [pro], maintaining professional-grade image quality while delivering significantly faster generation speeds.",
                  "zh_Hans": "FLUX.1 [pro] new 是 FLUX.1 [pro] 的加速版本，在保持专业级图像质量的同时，大大提高了生成速度。"
                },
                "llm": "This tool generates images from prompts using FAL's FLUX.1 [pro] new model."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Kalo Chin",
                "label": {
                  "en_US": "FLUX.1 [pro] new",
                  "zh_Hans": "FLUX.1 [pro] new"
                },
                "name": "flux_1_pro_new"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The text prompt used to generate the image.",
                    "zh_Hans": "用于生成图像的文本提示。"
                  },
                  "label": {
                    "en_US": "Prompt",
                    "zh_Hans": "提示词"
                  },
                  "llm_description": "This prompt text will be used to generate the image.",
                  "max": null,
                  "min": null,
                  "name": "prompt",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "landscape_4_3",
                  "form": "form",
                  "human_description": {
                    "en_US": "The size of the generated image.",
                    "zh_Hans": "生成图像的尺寸。"
                  },
                  "label": {
                    "en_US": "Image Size",
                    "zh_Hans": "图像尺寸"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "image_size",
                  "options": [
                    {
                      "label": {
                        "en_US": "Square HD",
                        "zh_Hans": "正方形高清"
                      },
                      "value": "square_hd"
                    },
                    {
                      "label": {
                        "en_US": "Square",
                        "zh_Hans": "正方形"
                      },
                      "value": "square"
                    },
                    {
                      "label": {
                        "en_US": "Portrait 4:3",
                        "zh_Hans": "竖屏 4:3"
                      },
                      "value": "portrait_4_3"
                    },
                    {
                      "label": {
                        "en_US": "Portrait 16:9",
                        "zh_Hans": "竖屏 16:9"
                      },
                      "value": "portrait_16_9"
                    },
                    {
                      "label": {
                        "en_US": "Landscape 4:3",
                        "zh_Hans": "横屏 4:3"
                      },
                      "value": "landscape_4_3"
                    },
                    {
                      "label": {
                        "en_US": "Landscape 16:9",
                        "zh_Hans": "横屏 16:9"
                      },
                      "value": "landscape_16_9"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 1,
                  "form": "form",
                  "human_description": {
                    "en_US": "The number of images to generate.",
                    "zh_Hans": "要生成的图像数量。"
                  },
                  "label": {
                    "en_US": "Number of Images",
                    "zh_Hans": "图像数量"
                  },
                  "llm_description": "",
                  "max": 1,
                  "min": 1,
                  "name": "num_images",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 28,
                  "form": "form",
                  "human_description": {
                    "en_US": "The number of inference steps to perform. More steps produce higher quality but take longer.",
                    "zh_Hans": "执行的推理步数。步数越多，质量越高，但所需时间也更长。"
                  },
                  "label": {
                    "en_US": "Num Inference Steps",
                    "zh_Hans": "推理步数"
                  },
                  "llm_description": "",
                  "max": 50,
                  "min": 1,
                  "name": "num_inference_steps",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 3.5,
                  "form": "form",
                  "human_description": {
                    "en_US": "How closely the model should follow the prompt.",
                    "zh_Hans": "模型对提示词的遵循程度。"
                  },
                  "label": {
                    "en_US": "Guidance Scale",
                    "zh_Hans": "指导强度"
                  },
                  "llm_description": "",
                  "max": 20,
                  "min": 0,
                  "name": "guidance_scale",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "2",
                  "form": "form",
                  "human_description": {
                    "en_US": "The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive.\n",
                    "zh_Hans": "生成图像的安全容忍级别。1 是最严格，6 是最宽松。\n"
                  },
                  "label": {
                    "en_US": "Safety Tolerance",
                    "zh_Hans": "安全容忍度"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "safety_tolerance",
                  "options": [
                    {
                      "label": {
                        "en_US": "1 (Most strict)",
                        "zh_Hans": "1（最严格）"
                      },
                      "value": "1"
                    },
                    {
                      "label": {
                        "en_US": "2",
                        "zh_Hans": "2"
                      },
                      "value": "2"
                    },
                    {
                      "label": {
                        "en_US": "3",
                        "zh_Hans": "3"
                      },
                      "value": "3"
                    },
                    {
                      "label": {
                        "en_US": "4",
                        "zh_Hans": "4"
                      },
                      "value": "4"
                    },
                    {
                      "label": {
                        "en_US": "5",
                        "zh_Hans": "5"
                      },
                      "value": "5"
                    },
                    {
                      "label": {
                        "en_US": "6 (Most permissive)",
                        "zh_Hans": "6（最宽松）"
                      },
                      "value": "6"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The same seed and prompt can produce similar images.",
                    "zh_Hans": "相同的种子和提示词可以生成相似的图像。"
                  },
                  "label": {
                    "en_US": "Seed",
                    "zh_Hans": "种子"
                  },
                  "llm_description": "",
                  "max": 9999999999,
                  "min": 0,
                  "name": "seed",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "If set to true, the function will wait for the image to be generated and uploaded before returning the response. This will increase the latency but allows you to get the image directly in the response without going through the CDN.\n",
                    "zh_Hans": "如果设置为 true，函数将在生成并上传图像后才返回响应。 这将增加延迟，但允许您直接在响应中获取图像，而无需通过 CDN。\n"
                  },
                  "label": {
                    "en_US": "Sync Mode",
                    "zh_Hans": "同步模式"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "sync_mode",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "FLUX 1.1 [pro] ultra is the newest version of FLUX 1.1 [pro], maintaining professional-grade image quality while delivering up to 2K resolution with improved photo realism.",
                  "zh_Hans": "FLUX 1.1 [pro] ultra 是 FLUX 1.1 [pro] 的最新版本，保持了专业级的图像质量，同时以改进的照片真实感提供高达 2K 的分辨率。"
                },
                "llm": "This tool generates images from prompts using FAL's FLUX 1.1 [pro] ultra model."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Kalo Chin",
                "label": {
                  "en_US": "FLUX 1.1 [pro] ultra",
                  "zh_Hans": "FLUX 1.1 [pro] ultra"
                },
                "name": "flux_1_1_pro_ultra"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The text prompt used to generate the image.",
                    "zh_Hans": "用于生成图像的文本提示。"
                  },
                  "label": {
                    "en_US": "Prompt",
                    "zh_Hans": "提示词"
                  },
                  "llm_description": "This prompt text will be used to generate the image.",
                  "max": null,
                  "min": null,
                  "name": "prompt",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "16:9",
                  "form": "form",
                  "human_description": {
                    "en_US": "The aspect ratio of the generated image.",
                    "zh_Hans": "生成图像的宽高比。"
                  },
                  "label": {
                    "en_US": "Aspect Ratio",
                    "zh_Hans": "纵横比"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "aspect_ratio",
                  "options": [
                    {
                      "label": {
                        "en_US": "21:9",
                        "zh_Hans": "21:9"
                      },
                      "value": "21:9"
                    },
                    {
                      "label": {
                        "en_US": "16:9",
                        "zh_Hans": "16:9"
                      },
                      "value": "16:9"
                    },
                    {
                      "label": {
                        "en_US": "4:3",
                        "zh_Hans": "4:3"
                      },
                      "value": "4:3"
                    },
                    {
                      "label": {
                        "en_US": "1:1",
                        "zh_Hans": "1:1"
                      },
                      "value": "1:1"
                    },
                    {
                      "label": {
                        "en_US": "3:4",
                        "zh_Hans": "3:4"
                      },
                      "value": "3:4"
                    },
                    {
                      "label": {
                        "en_US": "9:16",
                        "zh_Hans": "9:16"
                      },
                      "value": "9:16"
                    },
                    {
                      "label": {
                        "en_US": "9:21",
                        "zh_Hans": "9:21"
                      },
                      "value": "9:21"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 1,
                  "form": "form",
                  "human_description": {
                    "en_US": "The number of images to generate.",
                    "zh_Hans": "要生成的图像数量。"
                  },
                  "label": {
                    "en_US": "Number of Images",
                    "zh_Hans": "图片数量"
                  },
                  "llm_description": "",
                  "max": 1,
                  "min": 1,
                  "name": "num_images",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "2",
                  "form": "form",
                  "human_description": {
                    "en_US": "The safety tolerance level for the generated image. 1 being the most strict and 6 being the most permissive.",
                    "zh_Hans": "生成图像的安全容忍级别，1 为最严格，6 为最宽松。"
                  },
                  "label": {
                    "en_US": "Safety Tolerance",
                    "zh_Hans": "安全容忍度"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "safety_tolerance",
                  "options": [
                    {
                      "label": {
                        "en_US": "1 (Most strict)",
                        "zh_Hans": "1（最严格）"
                      },
                      "value": "1"
                    },
                    {
                      "label": {
                        "en_US": "2",
                        "zh_Hans": "2"
                      },
                      "value": "2"
                    },
                    {
                      "label": {
                        "en_US": "3",
                        "zh_Hans": "3"
                      },
                      "value": "3"
                    },
                    {
                      "label": {
                        "en_US": "4",
                        "zh_Hans": "4"
                      },
                      "value": "4"
                    },
                    {
                      "label": {
                        "en_US": "5",
                        "zh_Hans": "5"
                      },
                      "value": "5"
                    },
                    {
                      "label": {
                        "en_US": "6 (Most permissive)",
                        "zh_Hans": "6（最宽松）"
                      },
                      "value": "6"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The same seed and prompt can produce similar images.",
                    "zh_Hans": "相同的种子和提示词可以生成相似的图像。"
                  },
                  "label": {
                    "en_US": "Seed",
                    "zh_Hans": "种子"
                  },
                  "llm_description": "",
                  "max": 9999999999,
                  "min": 0,
                  "name": "seed",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Generate less processed, more natural-looking images.",
                    "zh_Hans": "生成较少处理、更自然的图像。"
                  },
                  "label": {
                    "en_US": "Raw Mode",
                    "zh_Hans": "原始模式"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "raw",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "Enable or disable the safety checker.",
                    "zh_Hans": "启用或禁用安全检查器。"
                  },
                  "label": {
                    "en_US": "Enable Safety Checker",
                    "zh_Hans": "启用安全检查器"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "enable_safety_checker",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "If set to true, the function will wait for the image to be generated and uploaded before returning the response. This will increase the latency but allows you to get the image directly in the response without going through the CDN.\n",
                    "zh_Hans": "如果设置为 true，函数将在生成并上传图像后才返回响应。 这将增加延迟，但允许您直接在响应中获取图像，而无需通过 CDN。\n"
                  },
                  "label": {
                    "en_US": "Sync Mode",
                    "zh_Hans": "同步模式"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "sync_mode",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "FLUX.1 [dev] is a 12 billion parameter flow transformer that generates high-quality images from text. It is suitable for personal and commercial use.",
                  "zh_Hans": "FLUX.1 [dev] 是一个拥有120亿参数的流动变换模型，可以从文本生成高质量的图像。适用于个人和商业用途。"
                },
                "llm": "This tool generates images from prompts using FAL's FLUX.1 [dev] model."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Kalo Chin",
                "label": {
                  "en_US": "FLUX.1 [dev]",
                  "zh_Hans": "FLUX.1 [dev]"
                },
                "name": "flux_1_dev"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The text prompt used to generate the image.",
                    "zh_Hans": "用于生成图片的文字提示词。"
                  },
                  "label": {
                    "en_US": "Prompt",
                    "zh_Hans": "提示词"
                  },
                  "llm_description": "This prompt text will be used to generate the image.",
                  "max": null,
                  "min": null,
                  "name": "prompt",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "landscape_4_3",
                  "form": "form",
                  "human_description": {
                    "en_US": "The size of the generated image.",
                    "zh_Hans": "生成图像的尺寸。"
                  },
                  "label": {
                    "en_US": "Image Size",
                    "zh_Hans": "图片大小"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "image_size",
                  "options": [
                    {
                      "label": {
                        "en_US": "Square HD",
                        "zh_Hans": "方形高清"
                      },
                      "value": "square_hd"
                    },
                    {
                      "label": {
                        "en_US": "Square",
                        "zh_Hans": "方形"
                      },
                      "value": "square"
                    },
                    {
                      "label": {
                        "en_US": "Portrait 4:3",
                        "zh_Hans": "竖屏 4:3"
                      },
                      "value": "portrait_4_3"
                    },
                    {
                      "label": {
                        "en_US": "Portrait 16:9",
                        "zh_Hans": "竖屏 16:9"
                      },
                      "value": "portrait_16_9"
                    },
                    {
                      "label": {
                        "en_US": "Landscape 4:3",
                        "zh_Hans": "横屏 4:3"
                      },
                      "value": "landscape_4_3"
                    },
                    {
                      "label": {
                        "en_US": "Landscape 16:9",
                        "zh_Hans": "横屏 16:9"
                      },
                      "value": "landscape_16_9"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 1,
                  "form": "form",
                  "human_description": {
                    "en_US": "The number of images to generate.",
                    "zh_Hans": "要生成的图片数量。"
                  },
                  "label": {
                    "en_US": "Number of Images",
                    "zh_Hans": "图片数量"
                  },
                  "llm_description": "",
                  "max": 4,
                  "min": 1,
                  "name": "num_images",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 28,
                  "form": "form",
                  "human_description": {
                    "en_US": "The number of inference steps to perform. More steps produce higher quality but take longer.",
                    "zh_Hans": "执行的推理步骤数量。更多的步骤可以产生更高质量的结果，但需要更长的时间。"
                  },
                  "label": {
                    "en_US": "Num Inference Steps",
                    "zh_Hans": "推理步数"
                  },
                  "llm_description": "",
                  "max": 50,
                  "min": 1,
                  "name": "num_inference_steps",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 3.5,
                  "form": "form",
                  "human_description": {
                    "en_US": "How closely the model should follow the prompt.",
                    "zh_Hans": "模型对提示词的遵循程度。"
                  },
                  "label": {
                    "en_US": "Guidance Scale",
                    "zh_Hans": "指导强度"
                  },
                  "llm_description": "",
                  "max": 20,
                  "min": 0,
                  "name": "guidance_scale",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The same seed and prompt can produce similar images.",
                    "zh_Hans": "相同的种子和提示可以产生相似的图像。"
                  },
                  "label": {
                    "en_US": "Seed",
                    "zh_Hans": "种子"
                  },
                  "llm_description": "",
                  "max": 9999999999,
                  "min": 0,
                  "name": "seed",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "Enable or disable the safety checker.",
                    "zh_Hans": "启用或禁用安全检查器。"
                  },
                  "label": {
                    "en_US": "Enable Safety Checker",
                    "zh_Hans": "启用安全检查器"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "enable_safety_checker",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "If set to true, the function will wait for the image to be generated and uploaded before returning the response. This will increase the latency but allows you to get the image directly in the response without going through the CDN.\n",
                    "zh_Hans": "如果设置为 true，函数将在生成并上传图像后再返回响应。 这将增加函数的延迟，但可以让您直接在响应中获取图像，而无需通过 CDN。\n"
                  },
                  "label": {
                    "en_US": "Sync Mode",
                    "zh_Hans": "同步模式"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "sync_mode",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "FLUX 1.1 [pro] is an enhanced version of FLUX.1 [pro], improved image generation capabilities, delivering superior composition, detail, and artistic fidelity compared to its predecessor.",
                  "zh_Hans": "FLUX 1.1 [pro] 是 FLUX.1 [pro] 的增强版，改进了图像生成能力，与其前身相比，提供了更出色的构图、细节和艺术保真度。"
                },
                "llm": "This tool generates images from prompts using FAL's FLUX 1.1 [pro] model."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Kalo Chin",
                "label": {
                  "en_US": "FLUX 1.1 [pro]",
                  "zh_Hans": "FLUX 1.1 [pro]"
                },
                "name": "flux_1_1_pro"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The text prompt used to generate the image.",
                    "zh_Hans": "用于生成图片的文字提示词。"
                  },
                  "label": {
                    "en_US": "Prompt",
                    "zh_Hans": "提示词"
                  },
                  "llm_description": "This prompt text will be used to generate the image.",
                  "max": null,
                  "min": null,
                  "name": "prompt",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "landscape_4_3",
                  "form": "form",
                  "human_description": {
                    "en_US": "The size of the generated image.",
                    "zh_Hans": "生成图像的尺寸。"
                  },
                  "label": {
                    "en_US": "Image Size",
                    "zh_Hans": "图片大小"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "image_size",
                  "options": [
                    {
                      "label": {
                        "en_US": "Square HD",
                        "zh_Hans": "方形高清"
                      },
                      "value": "square_hd"
                    },
                    {
                      "label": {
                        "en_US": "Square",
                        "zh_Hans": "方形"
                      },
                      "value": "square"
                    },
                    {
                      "label": {
                        "en_US": "Portrait 4:3",
                        "zh_Hans": "竖屏 4:3"
                      },
                      "value": "portrait_4_3"
                    },
                    {
                      "label": {
                        "en_US": "Portrait 16:9",
                        "zh_Hans": "竖屏 16:9"
                      },
                      "value": "portrait_16_9"
                    },
                    {
                      "label": {
                        "en_US": "Landscape 4:3",
                        "zh_Hans": "横屏 4:3"
                      },
                      "value": "landscape_4_3"
                    },
                    {
                      "label": {
                        "en_US": "Landscape 16:9",
                        "zh_Hans": "横屏 16:9"
                      },
                      "value": "landscape_16_9"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 1,
                  "form": "form",
                  "human_description": {
                    "en_US": "The number of images to generate.",
                    "zh_Hans": "要生成的图片数量。"
                  },
                  "label": {
                    "en_US": "Number of Images",
                    "zh_Hans": "图片数量"
                  },
                  "llm_description": "",
                  "max": 1,
                  "min": 1,
                  "name": "num_images",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "2",
                  "form": "form",
                  "human_description": {
                    "en_US": "The safety tolerance level for the generated image. 1 being the most strict and 6 being the most permissive.",
                    "zh_Hans": "生成图像的安全容忍级别，1 为最严格，6 为最宽松。"
                  },
                  "label": {
                    "en_US": "Safety Tolerance",
                    "zh_Hans": "安全容忍度"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "safety_tolerance",
                  "options": [
                    {
                      "label": {
                        "en_US": "1 (Most strict)",
                        "zh_Hans": "1（最严格）"
                      },
                      "value": "1"
                    },
                    {
                      "label": {
                        "en_US": "2",
                        "zh_Hans": "2"
                      },
                      "value": "2"
                    },
                    {
                      "label": {
                        "en_US": "3",
                        "zh_Hans": "3"
                      },
                      "value": "3"
                    },
                    {
                      "label": {
                        "en_US": "4",
                        "zh_Hans": "4"
                      },
                      "value": "4"
                    },
                    {
                      "label": {
                        "en_US": "5",
                        "zh_Hans": "5"
                      },
                      "value": "5"
                    },
                    {
                      "label": {
                        "en_US": "6 (Most permissive)",
                        "zh_Hans": "6（最宽松）"
                      },
                      "value": "6"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The same seed and prompt can produce similar images.",
                    "zh_Hans": "相同的种子和提示词可以产生相似的图像。"
                  },
                  "label": {
                    "en_US": "Seed",
                    "zh_Hans": "种子"
                  },
                  "llm_description": "",
                  "max": 9999999999,
                  "min": 0,
                  "name": "seed",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "Enable or disable the safety checker.",
                    "zh_Hans": "启用或禁用安全检查器。"
                  },
                  "label": {
                    "en_US": "Enable Safety Checker",
                    "zh_Hans": "启用安全检查器"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "enable_safety_checker",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "If set to true, the function will wait for the image to be generated and uploaded before returning the response. This will increase the latency but allows you to get the image directly in the response without going through the CDN.\n",
                    "zh_Hans": "如果设置为 true，函数将在生成并上传图像后再返回响应。 这将增加函数的延迟，但可以让您直接在响应中获取图像，而无需通过 CDN。\n"
                  },
                  "label": {
                    "en_US": "Sync Mode",
                    "zh_Hans": "同步模式"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "sync_mode",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Transcribe an audio file using the Whisper model.",
                  "zh_Hans": "使用 Whisper 模型转录音频文件。"
                },
                "llm": "Transcribe an audio file using the Whisper model."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Kalo Chin",
                "label": {
                  "en_US": "Wizper",
                  "zh_Hans": "Wizper"
                },
                "name": "wizper"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Upload an audio file to transcribe. Supports mp3, mp4, mpeg, mpga, m4a, wav, or webm formats.",
                    "zh_Hans": "上传要转录的音频文件。支持 mp3、mp4、mpeg、mpga、m4a、wav 或 webm 格式。"
                  },
                  "label": {
                    "en_US": "Audio File",
                    "zh_Hans": "音频文件"
                  },
                  "llm_description": "Audio file to transcribe. Supported formats: mp3, mp4, mpeg, mpga, m4a, wav, or webm.",
                  "max": null,
                  "min": null,
                  "name": "audio_file",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "file"
                },
                {
                  "auto_generate": null,
                  "default": "transcribe",
                  "form": "form",
                  "human_description": {
                    "en_US": "Choose whether to transcribe the audio in its original language or translate it to English",
                    "zh_Hans": "选择是以原始语言转录音频还是将其翻译成英语"
                  },
                  "label": {
                    "en_US": "Task",
                    "zh_Hans": "任务"
                  },
                  "llm_description": "Task to perform on the audio file. Either transcribe or translate. Default value: 'transcribe'. If 'translate' is selected as the task, the audio will be translated to English, regardless of the language selected.",
                  "max": null,
                  "min": null,
                  "name": "task",
                  "options": [
                    {
                      "label": {
                        "en_US": "Transcribe",
                        "zh_Hans": "转录"
                      },
                      "value": "transcribe"
                    },
                    {
                      "label": {
                        "en_US": "Translate",
                        "zh_Hans": "翻译"
                      },
                      "value": "translate"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "en",
                  "form": "form",
                  "human_description": {
                    "en_US": "Select the primary language spoken in the audio file",
                    "zh_Hans": "选择音频文件中使用的主要语言"
                  },
                  "label": {
                    "en_US": "Language",
                    "zh_Hans": "语言"
                  },
                  "llm_description": "Language of the audio file.",
                  "max": null,
                  "min": null,
                  "name": "language",
                  "options": [
                    {
                      "label": {
                        "en_US": "Afrikaans",
                        "zh_Hans": "南非语"
                      },
                      "value": "af"
                    },
                    {
                      "label": {
                        "en_US": "Amharic",
                        "zh_Hans": "阿姆哈拉语"
                      },
                      "value": "am"
                    },
                    {
                      "label": {
                        "en_US": "Arabic",
                        "zh_Hans": "阿拉伯语"
                      },
                      "value": "ar"
                    },
                    {
                      "label": {
                        "en_US": "Assamese",
                        "zh_Hans": "阿萨姆语"
                      },
                      "value": "as"
                    },
                    {
                      "label": {
                        "en_US": "Azerbaijani",
                        "zh_Hans": "阿塞拜疆语"
                      },
                      "value": "az"
                    },
                    {
                      "label": {
                        "en_US": "Bashkir",
                        "zh_Hans": "巴什基尔语"
                      },
                      "value": "ba"
                    },
                    {
                      "label": {
                        "en_US": "Belarusian",
                        "zh_Hans": "白俄罗斯语"
                      },
                      "value": "be"
                    },
                    {
                      "label": {
                        "en_US": "Bulgarian",
                        "zh_Hans": "保加利亚语"
                      },
                      "value": "bg"
                    },
                    {
                      "label": {
                        "en_US": "Bengali",
                        "zh_Hans": "孟加拉语"
                      },
                      "value": "bn"
                    },
                    {
                      "label": {
                        "en_US": "Tibetan",
                        "zh_Hans": "藏语"
                      },
                      "value": "bo"
                    },
                    {
                      "label": {
                        "en_US": "Breton",
                        "zh_Hans": "布列塔尼语"
                      },
                      "value": "br"
                    },
                    {
                      "label": {
                        "en_US": "Bosnian",
                        "zh_Hans": "波斯尼亚语"
                      },
                      "value": "bs"
                    },
                    {
                      "label": {
                        "en_US": "Catalan",
                        "zh_Hans": "加泰罗尼亚语"
                      },
                      "value": "ca"
                    },
                    {
                      "label": {
                        "en_US": "Czech",
                        "zh_Hans": "捷克语"
                      },
                      "value": "cs"
                    },
                    {
                      "label": {
                        "en_US": "Welsh",
                        "zh_Hans": "威尔士语"
                      },
                      "value": "cy"
                    },
                    {
                      "label": {
                        "en_US": "Danish",
                        "zh_Hans": "丹麦语"
                      },
                      "value": "da"
                    },
                    {
                      "label": {
                        "en_US": "German",
                        "zh_Hans": "德语"
                      },
                      "value": "de"
                    },
                    {
                      "label": {
                        "en_US": "Greek",
                        "zh_Hans": "希腊语"
                      },
                      "value": "el"
                    },
                    {
                      "label": {
                        "en_US": "English",
                        "zh_Hans": "英语"
                      },
                      "value": "en"
                    },
                    {
                      "label": {
                        "en_US": "Spanish",
                        "zh_Hans": "西班牙语"
                      },
                      "value": "es"
                    },
                    {
                      "label": {
                        "en_US": "Estonian",
                        "zh_Hans": "爱沙尼亚语"
                      },
                      "value": "et"
                    },
                    {
                      "label": {
                        "en_US": "Basque",
                        "zh_Hans": "巴斯克语"
                      },
                      "value": "eu"
                    },
                    {
                      "label": {
                        "en_US": "Persian",
                        "zh_Hans": "波斯语"
                      },
                      "value": "fa"
                    },
                    {
                      "label": {
                        "en_US": "Finnish",
                        "zh_Hans": "芬兰语"
                      },
                      "value": "fi"
                    },
                    {
                      "label": {
                        "en_US": "Faroese",
                        "zh_Hans": "法罗语"
                      },
                      "value": "fo"
                    },
                    {
                      "label": {
                        "en_US": "French",
                        "zh_Hans": "法语"
                      },
                      "value": "fr"
                    },
                    {
                      "label": {
                        "en_US": "Galician",
                        "zh_Hans": "加利西亚语"
                      },
                      "value": "gl"
                    },
                    {
                      "label": {
                        "en_US": "Gujarati",
                        "zh_Hans": "古吉拉特语"
                      },
                      "value": "gu"
                    },
                    {
                      "label": {
                        "en_US": "Hausa",
                        "zh_Hans": "毫萨语"
                      },
                      "value": "ha"
                    },
                    {
                      "label": {
                        "en_US": "Hawaiian",
                        "zh_Hans": "夏威夷语"
                      },
                      "value": "haw"
                    },
                    {
                      "label": {
                        "en_US": "Hebrew",
                        "zh_Hans": "希伯来语"
                      },
                      "value": "he"
                    },
                    {
                      "label": {
                        "en_US": "Hindi",
                        "zh_Hans": "印地语"
                      },
                      "value": "hi"
                    },
                    {
                      "label": {
                        "en_US": "Croatian",
                        "zh_Hans": "克罗地亚语"
                      },
                      "value": "hr"
                    },
                    {
                      "label": {
                        "en_US": "Haitian Creole",
                        "zh_Hans": "海地克里奥尔语"
                      },
                      "value": "ht"
                    },
                    {
                      "label": {
                        "en_US": "Hungarian",
                        "zh_Hans": "匈牙利语"
                      },
                      "value": "hu"
                    },
                    {
                      "label": {
                        "en_US": "Armenian",
                        "zh_Hans": "亚美尼亚语"
                      },
                      "value": "hy"
                    },
                    {
                      "label": {
                        "en_US": "Indonesian",
                        "zh_Hans": "印度尼西亚语"
                      },
                      "value": "id"
                    },
                    {
                      "label": {
                        "en_US": "Icelandic",
                        "zh_Hans": "冰岛语"
                      },
                      "value": "is"
                    },
                    {
                      "label": {
                        "en_US": "Italian",
                        "zh_Hans": "意大利语"
                      },
                      "value": "it"
                    },
                    {
                      "label": {
                        "en_US": "Japanese",
                        "zh_Hans": "日语"
                      },
                      "value": "ja"
                    },
                    {
                      "label": {
                        "en_US": "Javanese",
                        "zh_Hans": "爪哇语"
                      },
                      "value": "jw"
                    },
                    {
                      "label": {
                        "en_US": "Georgian",
                        "zh_Hans": "格鲁吉亚语"
                      },
                      "value": "ka"
                    },
                    {
                      "label": {
                        "en_US": "Kazakh",
                        "zh_Hans": "哈萨克语"
                      },
                      "value": "kk"
                    },
                    {
                      "label": {
                        "en_US": "Khmer",
                        "zh_Hans": "高棉语"
                      },
                      "value": "km"
                    },
                    {
                      "label": {
                        "en_US": "Kannada",
                        "zh_Hans": "卡纳达语"
                      },
                      "value": "kn"
                    },
                    {
                      "label": {
                        "en_US": "Korean",
                        "zh_Hans": "韩语"
                      },
                      "value": "ko"
                    },
                    {
                      "label": {
                        "en_US": "Latin",
                        "zh_Hans": "拉丁语"
                      },
                      "value": "la"
                    },
                    {
                      "label": {
                        "en_US": "Luxembourgish",
                        "zh_Hans": "卢森堡语"
                      },
                      "value": "lb"
                    },
                    {
                      "label": {
                        "en_US": "Lingala",
                        "zh_Hans": "林加拉语"
                      },
                      "value": "ln"
                    },
                    {
                      "label": {
                        "en_US": "Lao",
                        "zh_Hans": "老挝语"
                      },
                      "value": "lo"
                    },
                    {
                      "label": {
                        "en_US": "Lithuanian",
                        "zh_Hans": "立陶宛语"
                      },
                      "value": "lt"
                    },
                    {
                      "label": {
                        "en_US": "Latvian",
                        "zh_Hans": "拉脱维亚语"
                      },
                      "value": "lv"
                    },
                    {
                      "label": {
                        "en_US": "Malagasy",
                        "zh_Hans": "马尔加什语"
                      },
                      "value": "mg"
                    },
                    {
                      "label": {
                        "en_US": "Maori",
                        "zh_Hans": "毛利语"
                      },
                      "value": "mi"
                    },
                    {
                      "label": {
                        "en_US": "Macedonian",
                        "zh_Hans": "马其顿语"
                      },
                      "value": "mk"
                    },
                    {
                      "label": {
                        "en_US": "Malayalam",
                        "zh_Hans": "马拉雅拉姆语"
                      },
                      "value": "ml"
                    },
                    {
                      "label": {
                        "en_US": "Mongolian",
                        "zh_Hans": "蒙古语"
                      },
                      "value": "mn"
                    },
                    {
                      "label": {
                        "en_US": "Marathi",
                        "zh_Hans": "马拉地语"
                      },
                      "value": "mr"
                    },
                    {
                      "label": {
                        "en_US": "Malay",
                        "zh_Hans": "马来语"
                      },
                      "value": "ms"
                    },
                    {
                      "label": {
                        "en_US": "Maltese",
                        "zh_Hans": "马耳他语"
                      },
                      "value": "mt"
                    },
                    {
                      "label": {
                        "en_US": "Burmese",
                        "zh_Hans": "缅甸语"
                      },
                      "value": "my"
                    },
                    {
                      "label": {
                        "en_US": "Nepali",
                        "zh_Hans": "尼泊尔语"
                      },
                      "value": "ne"
                    },
                    {
                      "label": {
                        "en_US": "Dutch",
                        "zh_Hans": "荷兰语"
                      },
                      "value": "nl"
                    },
                    {
                      "label": {
                        "en_US": "Norwegian Nynorsk",
                        "zh_Hans": "新挪威语"
                      },
                      "value": "nn"
                    },
                    {
                      "label": {
                        "en_US": "Norwegian",
                        "zh_Hans": "挪威语"
                      },
                      "value": "false"
                    },
                    {
                      "label": {
                        "en_US": "Occitan",
                        "zh_Hans": "奥克语"
                      },
                      "value": "oc"
                    },
                    {
                      "label": {
                        "en_US": "Punjabi",
                        "zh_Hans": "旁遮普语"
                      },
                      "value": "pa"
                    },
                    {
                      "label": {
                        "en_US": "Polish",
                        "zh_Hans": "波兰语"
                      },
                      "value": "pl"
                    },
                    {
                      "label": {
                        "en_US": "Pashto",
                        "zh_Hans": "普什图语"
                      },
                      "value": "ps"
                    },
                    {
                      "label": {
                        "en_US": "Portuguese",
                        "zh_Hans": "葡萄牙语"
                      },
                      "value": "pt"
                    },
                    {
                      "label": {
                        "en_US": "Romanian",
                        "zh_Hans": "罗马尼亚语"
                      },
                      "value": "ro"
                    },
                    {
                      "label": {
                        "en_US": "Russian",
                        "zh_Hans": "俄语"
                      },
                      "value": "ru"
                    },
                    {
                      "label": {
                        "en_US": "Sanskrit",
                        "zh_Hans": "梵语"
                      },
                      "value": "sa"
                    },
                    {
                      "label": {
                        "en_US": "Sindhi",
                        "zh_Hans": "信德语"
                      },
                      "value": "sd"
                    },
                    {
                      "label": {
                        "en_US": "Sinhala",
                        "zh_Hans": "僧伽罗语"
                      },
                      "value": "si"
                    },
                    {
                      "label": {
                        "en_US": "Slovak",
                        "zh_Hans": "斯洛伐克语"
                      },
                      "value": "sk"
                    },
                    {
                      "label": {
                        "en_US": "Slovenian",
                        "zh_Hans": "斯洛文尼亚语"
                      },
                      "value": "sl"
                    },
                    {
                      "label": {
                        "en_US": "Shona",
                        "zh_Hans": "修纳语"
                      },
                      "value": "sn"
                    },
                    {
                      "label": {
                        "en_US": "Somali",
                        "zh_Hans": "索马里语"
                      },
                      "value": "so"
                    },
                    {
                      "label": {
                        "en_US": "Albanian",
                        "zh_Hans": "阿尔巴尼亚语"
                      },
                      "value": "sq"
                    },
                    {
                      "label": {
                        "en_US": "Serbian",
                        "zh_Hans": "塞尔维亚语"
                      },
                      "value": "sr"
                    },
                    {
                      "label": {
                        "en_US": "Sundanese",
                        "zh_Hans": "巽他语"
                      },
                      "value": "su"
                    },
                    {
                      "label": {
                        "en_US": "Swedish",
                        "zh_Hans": "瑞典语"
                      },
                      "value": "sv"
                    },
                    {
                      "label": {
                        "en_US": "Swahili",
                        "zh_Hans": "斯瓦希里语"
                      },
                      "value": "sw"
                    },
                    {
                      "label": {
                        "en_US": "Tamil",
                        "zh_Hans": "泰米尔语"
                      },
                      "value": "ta"
                    },
                    {
                      "label": {
                        "en_US": "Telugu",
                        "zh_Hans": "泰卢固语"
                      },
                      "value": "te"
                    },
                    {
                      "label": {
                        "en_US": "Tajik",
                        "zh_Hans": "塔吉克语"
                      },
                      "value": "tg"
                    },
                    {
                      "label": {
                        "en_US": "Thai",
                        "zh_Hans": "泰语"
                      },
                      "value": "th"
                    },
                    {
                      "label": {
                        "en_US": "Turkmen",
                        "zh_Hans": "土库曼语"
                      },
                      "value": "tk"
                    },
                    {
                      "label": {
                        "en_US": "Tagalog",
                        "zh_Hans": "他加禄语"
                      },
                      "value": "tl"
                    },
                    {
                      "label": {
                        "en_US": "Turkish",
                        "zh_Hans": "土耳其语"
                      },
                      "value": "tr"
                    },
                    {
                      "label": {
                        "en_US": "Tatar",
                        "zh_Hans": "鞑靼语"
                      },
                      "value": "tt"
                    },
                    {
                      "label": {
                        "en_US": "Ukrainian",
                        "zh_Hans": "乌克兰语"
                      },
                      "value": "uk"
                    },
                    {
                      "label": {
                        "en_US": "Urdu",
                        "zh_Hans": "乌尔都语"
                      },
                      "value": "ur"
                    },
                    {
                      "label": {
                        "en_US": "Uzbek",
                        "zh_Hans": "乌兹别克语"
                      },
                      "value": "uz"
                    },
                    {
                      "label": {
                        "en_US": "Vietnamese",
                        "zh_Hans": "越南语"
                      },
                      "value": "vi"
                    },
                    {
                      "label": {
                        "en_US": "Yiddish",
                        "zh_Hans": "意第绪语"
                      },
                      "value": "yi"
                    },
                    {
                      "label": {
                        "en_US": "Yoruba",
                        "zh_Hans": "约鲁巴语"
                      },
                      "value": "yo"
                    },
                    {
                      "label": {
                        "en_US": "Cantonese",
                        "zh_Hans": "粤语"
                      },
                      "value": "yue"
                    },
                    {
                      "label": {
                        "en_US": "Chinese",
                        "zh_Hans": "中文"
                      },
                      "value": "zh"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "segment",
                  "form": "form",
                  "human_description": {
                    "en_US": "Choose how the transcription should be divided into chunks",
                    "zh_Hans": "选择如何将转录内容分成块"
                  },
                  "label": {
                    "en_US": "Chunk Level",
                    "zh_Hans": "分块级别"
                  },
                  "llm_description": "Level of the chunks to return.",
                  "max": null,
                  "min": null,
                  "name": "chunk_level",
                  "options": [
                    {
                      "label": {
                        "en_US": "Segment",
                        "zh_Hans": "段"
                      },
                      "value": "segment"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "3",
                  "form": "form",
                  "human_description": {
                    "en_US": "Select which version of the Whisper large model to use",
                    "zh_Hans": "选择要使用的 Whisper large 模型版本"
                  },
                  "label": {
                    "en_US": "Version",
                    "zh_Hans": "版本"
                  },
                  "llm_description": "Version of the model to use. All of the models are the Whisper large variant.",
                  "max": null,
                  "min": null,
                  "name": "version",
                  "options": [
                    {
                      "label": {
                        "en_US": "Version 3",
                        "zh_Hans": "版本 3"
                      },
                      "value": "3"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Upscale images with high fidelity using the Clarity Upscaler model.",
                  "zh_Hans": "使用 Clarity Upscaler 模型以高保真度提升图像分辨率。"
                },
                "llm": "Upscale images with high fidelity using the Clarity Upscaler model."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Kalo Chin",
                "label": {
                  "en_US": "Clarity Upscaler",
                  "zh_Hans": "Clarity Upscaler"
                },
                "name": "clarity_upscaler"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Upload an image file to upscale. Supports common image formats like jpeg, png, etc.",
                    "zh_Hans": "上传要提升分辨率的图像文件。支持常见图像格式如jpeg、png等。"
                  },
                  "label": {
                    "en_US": "Image File",
                    "zh_Hans": "图像文件"
                  },
                  "llm_description": "Image file to upscale. Supported formats include jpeg, png, etc.",
                  "max": null,
                  "min": null,
                  "name": "image_file",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "file"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "URL of the image to upscale if you don't want to upload a file.",
                    "zh_Hans": "如果不想上传文件，可以提供要提升分辨率的图像URL。"
                  },
                  "label": {
                    "en_US": "Image URL",
                    "zh_Hans": "图像URL"
                  },
                  "llm_description": "URL of the image to upscale. Can be used instead of uploading a file.",
                  "max": null,
                  "min": null,
                  "name": "image_url",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "masterpiece, best quality, highres",
                  "form": "llm",
                  "human_description": {
                    "en_US": "The prompt to guide image upscaling. Be as descriptive as possible for best results.",
                    "zh_Hans": "指导图像提升的提示词。尽可能详细描述以获得最佳效果。"
                  },
                  "label": {
                    "en_US": "Prompt",
                    "zh_Hans": "提示词"
                  },
                  "llm_description": "The prompt to use for generating the upscaled image. Be as descriptive as possible for best results.",
                  "max": null,
                  "min": null,
                  "name": "prompt",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 2,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The factor by which to upscale the image.",
                    "zh_Hans": "图像放大的倍数。"
                  },
                  "label": {
                    "en_US": "Upscale Factor",
                    "zh_Hans": "放大倍数"
                  },
                  "llm_description": "The factor by which to upscale the image.",
                  "max": null,
                  "min": null,
                  "name": "upscale_factor",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "(worst quality, low quality, normal quality:2)",
                  "form": "llm",
                  "human_description": {
                    "en_US": "The negative prompt to address details you don't want in the image.",
                    "zh_Hans": "负面提示词，用于指定您不希望在图像中出现的细节。"
                  },
                  "label": {
                    "en_US": "Negative Prompt",
                    "zh_Hans": "负面提示词"
                  },
                  "llm_description": "The negative prompt to use. Specify details that you don't want in the upscaled image.",
                  "max": null,
                  "min": null,
                  "name": "negative_prompt",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 0.35,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The creativity level. Higher values allow the model to deviate more from the prompt.",
                    "zh_Hans": "创造力水平。较高的值允许模型更多地偏离提示词。"
                  },
                  "label": {
                    "en_US": "Creativity",
                    "zh_Hans": "创造力"
                  },
                  "llm_description": "The creativity level of the model (denoise strength). Higher values allow the model to deviate more from the prompt.",
                  "max": null,
                  "min": null,
                  "name": "creativity",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 0.6,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The resemblance to the original image. Higher values make the model try to keep the original image.",
                    "zh_Hans": "与原始图像的相似度。较高的值使模型尝试保持原始图像的特征。"
                  },
                  "label": {
                    "en_US": "Resemblance",
                    "zh_Hans": "相似度"
                  },
                  "llm_description": "The resemblance of the upscaled image to the original image (ControlNet strength). Higher values make the model try to preserve the original image more.",
                  "max": null,
                  "min": null,
                  "name": "resemblance",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 4,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The CFG scale. Controls how closely the model sticks to your prompt.",
                    "zh_Hans": "CFG 比例。控制模型与提示词的贴合程度。"
                  },
                  "label": {
                    "en_US": "Guidance Scale",
                    "zh_Hans": "引导比例"
                  },
                  "llm_description": "The Classifier Free Guidance (CFG) scale. Controls how closely the model sticks to your prompt.",
                  "max": null,
                  "min": null,
                  "name": "guidance_scale",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 18,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The number of inference steps to perform.",
                    "zh_Hans": "执行的推理步骤数量。"
                  },
                  "label": {
                    "en_US": "Inference Steps",
                    "zh_Hans": "推理步骤"
                  },
                  "llm_description": "The number of inference steps to perform. Higher values may improve quality but increase processing time.",
                  "max": null,
                  "min": null,
                  "name": "num_inference_steps",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The random seed for deterministic generation. Same seed with same parameters produces same result.",
                    "zh_Hans": "用于确定性生成的随机种子。相同的种子和参数会产生相同的结果。"
                  },
                  "label": {
                    "en_US": "Seed",
                    "zh_Hans": "种子"
                  },
                  "llm_description": "The random seed for deterministic generation. Same seed with same parameters produces same result.",
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to enable the safety checker.",
                    "zh_Hans": "是否启用安全检查器。"
                  },
                  "label": {
                    "en_US": "Enable Safety Checker",
                    "zh_Hans": "启用安全检查器"
                  },
                  "llm_description": "If set to false, the safety checker will be disabled.",
                  "max": null,
                  "min": null,
                  "name": "enable_safety_checker",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-16T04:20:01Z",
        "version_updated_at": "2025-04-16T04:20:01Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "This tool utilizes large language models (LLMs) to analyze natural language data, generate interpretive reports, and create visualizations - enhancing enterprise decision-making efficiency.",
          "ja_JP": "This tool utilizes large language models (LLMs) to analyze natural language data, generate interpretive reports, and create visualizations - enhancing enterprise decision-making efficiency.",
          "pt_BR": "This tool utilizes large language models (LLMs) to analyze natural language data, generate interpretive reports, and create visualizations - enhancing enterprise decision-making efficiency.",
          "zh_Hans": "这是一款可以基于大模型进行自然语言数据分析、生成解读报告、进行可视化的工具，提升企业决策效率。"
        },
        "category": "tool",
        "created_at": "2025-04-10T13:52:46Z",
        "endpoint": {},
        "icon": "digitforce/packages/data_analysis/_assets/icon.svg",
        "index_id": "digitforce___data_analysis",
        "install_count": 449,
        "introduction": "## data_analysis\r\n**Author:** digitforce\r\n**Version:** 1.0.4\r\n**Type:** tool\r\n\r\n### Overview\r\nThis plugin includes three tools: a data analysis tool (data_analysis), a data interpretation tool (data_interpretation), and a data visualization tool (data_visualization). These tools can perform data queries, interpretation, and visualization on markdown text processed by the `Doc Extractor` from table files (csv/xls/xlsx).\r\n\r\n该插件包含三个工具：数据分析工具（data_analysis）、数据解读工具（data_interpretation）和数据可视化工具（data_visualization），可对表格（csv/xls/xlsx）等通过`文档提取器`处理后的markdown文本进行数据查询、解读和可视化。\r\n\r\nIt utilizes the API from `DigitForce`.  \r\n调用了`数势科技`的API接口。\r\n\r\nCurrently, it supports vertical tables (where a column from top to bottom represents the same type of information for different objects).  \r\n当前支持纵向表格（即从上到下一列代表不同对象的同类型信息）。\r\n\r\nFor example, a grade report table:  \r\n以成绩单表格为例：\r\n\r\n| Name       | Chinese | Math | English |\r\n|------------|---------|------|---------|\r\n| Xiao Ming  | 90      | 85   | 80      |\r\n| Xiao Hong  | 95      | 88   | 92      |\r\n| Xiao Qiang | 92      | 89   | 87      |\r\n\r\n### Configuration\r\n\r\n#### 1. Apply for an API Key\r\n\r\nPlease apply for an API Key on the https://www.digitforce.com/api/app?source=dify&intent=redect_api\r\n\r\n请通过 https://www.digitforce.com/api/app?source=dify&intent=redect_api 申请API Key。\r\n![apply_apikey.png](_assets/apply_apikey.png)\r\n\r\n#### 2. Configure the plugin\r\n\r\nGet tools from Plugin Marketplace.\r\nThe tools could be found at the Plugin Marketplace, please install it first. \r\n\r\n从插件市场获取工具。\r\n可在插件市场中查找本工具，请先完成安装。\r\n\r\n#### 3. Fill in the API key in Dify\r\nOn the Dify navigation page, click Tools > data_analysis > To authorize filling in the API Key.\r\n\r\n在Dify导航页面点击Tools > data_analysis > 进入授权填写API密钥。\r\n![set_apikey.png](_assets/set_apikey.png)\r\n\r\n#### Workflow Usage\r\n\r\n##### data_analysis\r\n\r\n| Parameter  | Required | Description                                                                 | Example                   |\r\n|------------|----------|-------------------------------------------------------------------------------|---------------------------|\r\n| `query`    | Yes      | Query statement                                                             | \"What is Xiao Ming's math score?\" |\r\n| `input_data` | Yes      | Table data in Markdown format<br/>(e.g., markdown text output by the `Doc Extractor` for tables) | As shown in the grade report table example |\r\n\r\n![data_analysis_1.png](_assets/data_analysis_1.png)\r\n![data_analysis_2.png](_assets/data_analysis_2.png)\r\n![data_analysis_3.png](_assets/data_analysis_3.png)\r\n![data_analysis_4.png](_assets/data_analysis_4.png)\r\n\r\n##### data_interpretation\r\n\r\n| Parameter  | Required | Description                                                                 | Example                   |\r\n|------------|----------|-------------------------------------------------------------------------------|---------------------------|\r\n| `query`    | No       | Query statement                                                             | \"What is Xiao Ming's math score?\" |\r\n| `input_data` | Yes      | Table data in Markdown format<br/>(e.g., markdown text output by the `Doc Extractor` for tables) | As shown in the grade report table example |\r\n\r\n![data_interpretation_1.png](_assets/data_interpretation_1.png)\r\n![data_interpretation_2.png](_assets/data_interpretation_2.png)\r\n![data_interpretation_3.png](_assets/data_interpretation_3.png)\r\n![data_interpretation_4.png](_assets/data_interpretation_4.png)\r\n\r\n##### data_visualization\r\n\r\n| Parameter  | Required | Description                                                                 | Example                   |\r\n|------------|----------|-------------------------------------------------------------------------------|---------------------------|\r\n| `query`    | Yes      | Query statement                                                             | \"What is Xiao Ming's math score?\" |\r\n| `input_data` | Yes      | Table data in Markdown format<br/>(e.g., markdown text output by the `Doc Extractor` for tables) | As shown in the grade report table example |\r\n\r\n![data_visualization_1.png](_assets/data_visualization_1.png)\r\n![data_visualization_2.png](_assets/data_visualization_2.png)\r\n![data_visualization_3.png](_assets/data_visualization_3.png)\r\n![data_visualization_4.png](_assets/data_visualization_4.png)\r\n![data_visualization_5.png](_assets/data_visualization_5.png)\r\n\r\n",
        "label": {
          "en_US": "data analysis",
          "ja_JP": "data analysis",
          "pt_BR": "data analysis",
          "zh_Hans": "数据分析"
        },
        "latest_package_identifier": "digitforce/data_analysis:1.0.4@86d2146a59ddc4144037778f3e345fdf12fb55731ae3d4d8adbdb2b03579b7b5",
        "latest_version": "1.0.4",
        "model": {},
        "name": "data_analysis",
        "org": "digitforce",
        "plugin_id": "digitforce/data_analysis",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/data_analysis.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Get your API key from www.digitforce.com",
                "zh_Hans": "从www.digitforce.com获取API key"
              },
              "label": {
                "en_US": "API key",
                "zh_Hans": "API key"
              },
              "name": "digitforce_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your API key",
                "zh_Hans": "请输入你的API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://www.digitforce.com/api/app?source=dify&intent=redect_api"
            }
          ],
          "identity": {
            "author": "digitforce",
            "description": {
              "en_US": "This tool utilizes large language models (LLMs) to analyze natural language data, generate interpretive reports, and create visualizations - enhancing enterprise decision-making efficiency.",
              "pt_BR": "This tool utilizes large language models (LLMs) to analyze natural language data, generate interpretive reports, and create visualizations - enhancing enterprise decision-making efficiency.",
              "zh_Hans": "这是一款可以基于大模型进行自然语言数据分析、生成解读报告、进行可视化的工具，提升企业决策效率。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "data_analysis",
              "pt_BR": "data_analysis",
              "zh_Hans": "数据分析"
            },
            "name": "digitforce",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "natural language based data analysis",
                  "pt_BR": "natural language based data analysis",
                  "zh_Hans": "通过自然语言执行精准数据检索"
                },
                "llm": "natural language based data analysis"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "digitforce",
                "label": {
                  "en_US": "data_analysis",
                  "pt_BR": "data_analysis",
                  "zh_Hans": "数据分析"
                },
                "name": "data_analysis"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Query string",
                    "pt_BR": "Query string",
                    "zh_Hans": "用户的查询语句"
                  },
                  "label": {
                    "en_US": "Query string",
                    "pt_BR": "Query string",
                    "zh_Hans": "用户的查询语句"
                  },
                  "llm_description": "Query string",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "markdown data",
                    "pt_BR": "markdown data",
                    "zh_Hans": "表格通过文档提取器输出的markdown文本"
                  },
                  "label": {
                    "en_US": "markdown data",
                    "pt_BR": "markdown data",
                    "zh_Hans": "表格通过文档提取器输出的markdown文本"
                  },
                  "llm_description": "markdown text output by the table through the Doc Extractor",
                  "max": null,
                  "min": null,
                  "name": "input_data",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Automated Insight Generation",
                  "pt_BR": "Automated Insight Generation",
                  "zh_Hans": "自动生成分析结论"
                },
                "llm": "Automated Insight Generation"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "digitforce",
                "label": {
                  "en_US": "data_interpretation",
                  "pt_BR": "data_interpretation",
                  "zh_Hans": "数据解读"
                },
                "name": "data_interpretation"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Query string",
                    "pt_BR": "Query string",
                    "zh_Hans": "用户的数据解读要求"
                  },
                  "label": {
                    "en_US": "Query string",
                    "pt_BR": "Query string",
                    "zh_Hans": "用户的数据解读要求"
                  },
                  "llm_description": "Query string",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "markdown data",
                    "pt_BR": "markdown data",
                    "zh_Hans": "表格通过文档提取器输出的markdown文本"
                  },
                  "label": {
                    "en_US": "markdown data",
                    "pt_BR": "markdown data",
                    "zh_Hans": "表格通过文档提取器输出的markdown文本"
                  },
                  "llm_description": "markdown text output by the table through the Doc Extractor",
                  "max": null,
                  "min": null,
                  "name": "input_data",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "natural language based data visualization",
                  "pt_BR": "natural language based data visualization",
                  "zh_Hans": "通过自然语言对数据进行可视化"
                },
                "llm": "natural language based data visualization"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "digitforce",
                "label": {
                  "en_US": "data_visualization",
                  "pt_BR": "data_visualization",
                  "zh_Hans": "数据可视化"
                },
                "name": "data_visualization"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Query string",
                    "pt_BR": "Query string",
                    "zh_Hans": "用户的查询语句"
                  },
                  "label": {
                    "en_US": "Query string",
                    "pt_BR": "Query string",
                    "zh_Hans": "用户的查询语句"
                  },
                  "llm_description": "Query string",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "markdown data",
                    "pt_BR": "markdown data",
                    "zh_Hans": "表格通过文档提取器输出的markdown文本"
                  },
                  "label": {
                    "en_US": "markdown data",
                    "pt_BR": "markdown data",
                    "zh_Hans": "表格通过文档提取器输出的markdown文本"
                  },
                  "llm_description": "markdown text output by the table through the Doc Extractor",
                  "max": null,
                  "min": null,
                  "name": "input_data",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-23T01:38:30Z",
        "version_updated_at": "2025-04-23T01:38:30Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Llama Parse, the world's first genAI-native document parsing platform - built with LLMs and for LLM use cases. https://docs.llamaindex.ai/en/stable/llama_cloud/Llama Parse/",
          "zh_Hans": "Llama Parse, the world's first genAI-native document parsing platform - built with LLMs and for LLM use cases. https://docs.llamaindex.ai/en/stable/llama_cloud/Llama Parse/"
        },
        "category": "tool",
        "created_at": "2025-02-24T03:29:44Z",
        "endpoint": {},
        "icon": "langgenius/packages/llama_parse/_assets/icon.svg",
        "index_id": "langgenius___llama_parse",
        "install_count": 441,
        "introduction": "# LlamaParse Dify Plugin\n\nLlamaParse is a GenAI-native document parser that can parse complex document data for any downstream LLM use case (RAG, agents). This plugin integrates LlamaParse capabilities into the Dify platform.\n\n![LlamaParse screenshot](./_assets/llama_parse.png)\n\n## Features\n\n✅ **Broad file type support**: Parse various unstructured file types (.pdf, .pptx, .docx, .xlsx, .html) with text, tables, visual elements, and complex layouts.\n\n✅ **Table recognition**: Accurately parse embedded tables into text and semi-structured representations.\n\n✅ **Multimodal parsing**: Extract visual elements (images/diagrams) into structured formats using the latest multimodal models.\n\n✅ **Custom parsing**: Customize output through custom prompt instructions.\n\n## Getting Started\n\n### API Key Setup\n\n1. Visit [https://cloud.llamaindex.ai/api-key](https://cloud.llamaindex.ai/api-key) to create an account\n2. Generate your API key\n3. Configure the API key in your Dify plugin settings\n\n### Usage Limits\n\n- Free plan: Up to 1000 pages per day\n- Paid plan: 7000 free pages per week + $0.003 per additional page\n\n## Parameters\n\n### Input Parameters\n\n| Parameter   | Type    | Required | Default  | Description                                              |\n| ----------- | ------- | -------- | -------- | -------------------------------------------------------- |\n| files       | files   | Yes      | -        | Files to be parsed                                       |\n| result_type | select  | No       | markdown | Output format (txt or md)                                |\n| num_workers | number  | No       | 4        | Number of parallel workers for processing multiple files |\n| verbose     | boolean | No       | false    | Enable detailed output logging                           |\n| language    | string  | No       | \"en\"     | Output language (e.g., \"en\" for English)                 |\n\n### Output Format\n\nThe plugin provides three types of output for each processed file:\n\n1. **Text Message**\n\n   - Plain text concatenation of all parsed documents, separated by \"---\"\n\n2. **JSON Message**\n\n   - Structure: `{ filename: [{ text: string, metadata: object }] }`\n   - Contains parsed text and associated metadata for each document\n\n3. **Blob Message**\n   - Binary content with appropriate MIME type:\n     - JSON: \"application/json\"\n     - Markdown: \"text/markdown\"\n     - Text: \"text/plain\"\n\n## Credits\n\nThis plugin is powered by [LlamaParse](https://github.com/run-llama/llama_cloud_services/tree/main/llama_parse), a powerful document parsing service by LlamaIndex.\n",
        "label": {
          "en_US": "Llama Parse",
          "zh_Hans": "Llama Parse"
        },
        "latest_package_identifier": "langgenius/llama_parse:0.0.2@700a0de09ac45965a60eb5f63b1e8f7e6bb8ea28aa58b0a07d955a9d6cce7c72",
        "latest_version": "0.0.2",
        "model": {},
        "name": "llama_parse",
        "org": "langgenius",
        "plugin_id": "langgenius/llama_parse",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/llama.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "utilities"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "Llama Cloud API key",
                "zh_Hans": "Llama Cloud API key"
              },
              "name": "llama_cloud_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your  Llama Cloud API key",
                "zh_Hans": "请输入你的 Llama Cloud API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://cloud.llamaindex.ai/"
            }
          ],
          "identity": {
            "author": "langgenius",
            "description": {
              "en_US": "Llama Cloud provides image extraction and data cleaning tools",
              "zh_Hans": "Llama Cloud提供的图片提取和数据清洗工具"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Llama Cloud",
              "zh_Hans": "Llama Cloud"
            },
            "name": "llama_cloud",
            "tags": [
              "utilities"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "a tool for parsing text, tables, and images, supporting multiple formats such as pdf, pptx, docx, etc. supporting multiple languages such as English, Chinese, etc.",
                  "zh_Hans": "一个用于解析文本，表格和图片的工具，支持pdf,pptx,docx等多种格式。支持英语，中文等多种语言"
                },
                "llm": "a tool for parsing text, tables, and images, supporting multiple formats such as pdf, pptx, docx, etc. supporting multiple languages such as English, Chinese, etc."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "llama parse",
                  "zh_Hans": "llama parse"
                },
                "name": "llama_parse"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "upload the file to be parsed",
                    "zh_Hans": "上传用于解析的文件"
                  },
                  "label": {
                    "en_US": "upload file",
                    "zh_Hans": "上传文件"
                  },
                  "llm_description": "upload the file to be parsed",
                  "max": null,
                  "min": null,
                  "name": "files",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "files"
                },
                {
                  "auto_generate": null,
                  "default": "markdown",
                  "form": "form",
                  "human_description": {
                    "en_US": "the type of the result",
                    "zh_Hans": "选择结果的格式类型"
                  },
                  "label": {
                    "en_US": "result form type",
                    "zh_Hans": "结果格式类型"
                  },
                  "llm_description": "the type of the result",
                  "max": null,
                  "min": null,
                  "name": "result_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "txt",
                        "zh_Hans": "txt"
                      },
                      "value": "text"
                    },
                    {
                      "label": {
                        "en_US": "md",
                        "zh_Hans": "md"
                      },
                      "value": "markdown"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 4,
                  "form": "form",
                  "human_description": {
                    "en_US": "if multiple files passed, split in `num_workers` API calls",
                    "zh_Hans": "如果传递了多个文件，则在`num_workers` API调用中拆分"
                  },
                  "label": {
                    "en_US": "number of workers",
                    "zh_Hans": "工作线程数"
                  },
                  "llm_description": "the number of workers",
                  "max": null,
                  "min": null,
                  "name": "num_workers",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "whether to output the verbose information",
                    "zh_Hans": "是否输出详细信息"
                  },
                  "label": {
                    "en_US": "verbose",
                    "zh_Hans": "详情"
                  },
                  "llm_description": "whether to output the verbose information",
                  "max": null,
                  "min": null,
                  "name": "verbose",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": "en",
                  "form": "form",
                  "human_description": {
                    "en_US": "Optionally you can define a language, default=en",
                    "zh_Hans": "可选地，您可以定义一种语言，默认=en"
                  },
                  "label": {
                    "en_US": "language",
                    "zh_Hans": "语言"
                  },
                  "llm_description": "the language of the output file",
                  "max": null,
                  "min": null,
                  "name": "language",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-05T04:45:03Z",
        "version_updated_at": "2025-03-05T04:45:03Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Lark cloud document, requires the following permissions: docx:document、drive:drive、docs:document.content:read.\n",
          "zh_Hans": "Lark 云文档，需要开通以下权限: docx:document、drive:drive、docs:document.content:read。\n"
        },
        "category": "tool",
        "created_at": "2025-02-26T10:45:11Z",
        "endpoint": {},
        "icon": "langgenius/packages/lark_document/_assets/icon.svg",
        "index_id": "langgenius___lark_document",
        "install_count": 435,
        "introduction": "",
        "label": {
          "en_US": "Lark Cloud Document",
          "zh_Hans": "Lark 云文档"
        },
        "latest_package_identifier": "langgenius/lark_document:0.0.1@22d50fb7c9bf0873ef487cfcf5cf1603548b7d7d82e0855e6b1e7154c282e7b4",
        "latest_version": "0.0.1",
        "model": {},
        "name": "lark_document",
        "org": "langgenius",
        "plugin_id": "langgenius/lark_document",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/lark_document.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "social"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "APP ID"
              },
              "name": "app_id",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Lark app id",
                "zh_Hans": "请输入你的 Lark app id"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": "https://open.larksuite.com/app"
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "APP Secret"
              },
              "name": "app_secret",
              "options": null,
              "placeholder": {
                "en_US": "Please input your app secret",
                "zh_Hans": "请输入你的 Lark app secret"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            }
          ],
          "identity": {
            "author": "langgenius",
            "description": {
              "en_US": "Lark cloud document, requires the following permissions: docx:document、drive:drive、docs:document.content:read.\n",
              "zh_Hans": "Lark 云文档，需要开通以下权限: docx:document、drive:drive、docs:document.content:read。\n"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Lark Cloud Document",
              "zh_Hans": "Lark 云文档"
            },
            "name": "lark_document",
            "tags": [
              "social",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Create Lark document",
                  "zh_Hans": "创建 Lark 文档，支持创建空文档和带内容的文档，支持 markdown 语法创建。应用需要开启机器人能力(https://open.larksuite.com/document/faq/trouble-shooting/how-to-enable-bot-ability)。"
                },
                "llm": "A tool for creating Lark documents."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Create Lark document",
                  "zh_Hans": "创建 Lark 文档"
                },
                "name": "create_document"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Document title, only supports plain text content.",
                    "zh_Hans": "文档标题，只支持纯文本内容。"
                  },
                  "label": {
                    "en_US": "Document title",
                    "zh_Hans": "文档标题"
                  },
                  "llm_description": "文档标题，只支持纯文本内容，可以为空。",
                  "max": null,
                  "min": null,
                  "name": "title",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Document content, supports markdown syntax, can be empty.",
                    "zh_Hans": "文档内容，支持 markdown 语法，可以为空。"
                  },
                  "label": {
                    "en_US": "Document content",
                    "zh_Hans": "文档内容"
                  },
                  "llm_description": "文档内容，支持 markdown 语法，可以为空。",
                  "max": null,
                  "min": null,
                  "name": "content",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The token of the folder where the document is located. If it is not passed or is empty, it means the root directory. For Example: https://lark-japan.jp.larksuite.com/drive/folder/Lf8uf6BoAlWkUfdGtpMjUV0PpZd\n",
                    "zh_Hans": "文档所在文件夹的 Token，不传或传空表示根目录。例如：https://lark-japan.jp.larksuite.com/drive/folder/Lf8uf6BoAlWkUfdGtpMjUV0PpZd。"
                  },
                  "label": {
                    "en_US": "folder_token",
                    "zh_Hans": "文档所在文件夹的 Token"
                  },
                  "llm_description": "文档所在文件夹的 Token，不传或传空表示根目录。例如：https://lark-japan.jp.larksuite.com/drive/folder/Lf8uf6BoAlWkUfdGtpMjUV0PpZd。",
                  "max": null,
                  "min": null,
                  "name": "folder_token",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get lark cloud document content",
                  "zh_Hans": "获取 Lark 云文档的内容"
                },
                "llm": "A tool for retrieving content from Lark cloud documents."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Get Lark Cloud Document Content",
                  "zh_Hans": "获取 Lark 云文档的内容"
                },
                "name": "get_document_content"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for a Lark document. You can also input the document's URL.",
                    "zh_Hans": "Lark 文档的唯一标识，支持输入文档的 URL。"
                  },
                  "label": {
                    "en_US": "document_id",
                    "zh_Hans": "Lark 文档的唯一标识"
                  },
                  "llm_description": "Lark 文档的唯一标识，支持输入文档的 URL。",
                  "max": null,
                  "min": null,
                  "name": "document_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "markdown",
                  "form": "form",
                  "human_description": {
                    "en_US": "Format of the document return, optional values are text, markdown, can be empty, default is markdown.",
                    "zh_Hans": "文档返回格式，可选值有 text、markdown，可以为空，默认值为 markdown。"
                  },
                  "label": {
                    "en_US": "mode",
                    "zh_Hans": "文档返回格式"
                  },
                  "llm_description": "文档返回格式，可选值有 text、markdown，可以为空，默认值为 markdown。",
                  "max": null,
                  "min": null,
                  "name": "mode",
                  "options": [
                    {
                      "label": {
                        "en_US": "text",
                        "zh_Hans": "text"
                      },
                      "value": "text"
                    },
                    {
                      "label": {
                        "en_US": "markdown",
                        "zh_Hans": "markdown"
                      },
                      "value": "markdown"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "0",
                  "form": "form",
                  "human_description": {
                    "en_US": "Specifies the language for MentionUser, optional values are [0, 1]. 0: User's default name, 1: User's English name, default is 0.\n",
                    "zh_Hans": "指定返回的 MentionUser，即@用户的语言，可选值有 [0,1]。0: 该用户的默认名称，1: 该用户的英文名称，默认值为 0。\n"
                  },
                  "label": {
                    "en_US": "lang",
                    "zh_Hans": "指定@用户的语言"
                  },
                  "llm_description": "指定返回的 MentionUser，即@用户的语言，可选值有 [0,1]。0: 该用户的默认名称，1: 该用户的英文名称，默认值为 0。\n",
                  "max": null,
                  "min": null,
                  "name": "lang",
                  "options": [
                    {
                      "label": {
                        "en_US": "User's default name",
                        "zh_Hans": "用户的默认名称"
                      },
                      "value": "0"
                    },
                    {
                      "label": {
                        "en_US": "User's English name",
                        "zh_Hans": "用户的英文名称"
                      },
                      "value": "1"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Adding new content to Lark documents",
                  "zh_Hans": "在 Lark 文档中新增内容"
                },
                "llm": "A tool for adding new content to Lark documents."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Write Document",
                  "zh_Hans": "在 Lark 文档中新增内容"
                },
                "name": "write_document"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for a Lark document. You can also input the document's URL.",
                    "zh_Hans": "Lark 文档的唯一标识，支持输入文档的 URL。"
                  },
                  "label": {
                    "en_US": "document_id",
                    "zh_Hans": "Lark 文档的唯一标识"
                  },
                  "llm_description": "Lark 文档的唯一标识，支持输入文档的 URL。",
                  "max": null,
                  "min": null,
                  "name": "document_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Plain text or Markdown content. Note that embedded tables in the document should not have merged cells.",
                    "zh_Hans": "纯文本或 Markdown 内容。注意文档的内嵌套表格不允许有单元格合并。"
                  },
                  "label": {
                    "en_US": "Plain text or Markdown content",
                    "zh_Hans": "纯文本或 Markdown 内容"
                  },
                  "llm_description": "纯文本或 Markdown 内容，注意文档的内嵌套表格不允许有单元格合并。",
                  "max": null,
                  "min": null,
                  "name": "content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "end",
                  "form": "form",
                  "human_description": {
                    "en_US": "Content insertion position, optional values are start, end. 'start' means adding content at the beginning of the document; 'end' means adding content at the end of the document. The default value is end.",
                    "zh_Hans": "内容添加位置，可选值有 start、end。start 表示在文档开头添加内容；end 表示在文档结尾添加内容，默认值为 end。"
                  },
                  "label": {
                    "en_US": "position",
                    "zh_Hans": "内容添加位置"
                  },
                  "llm_description": "内容添加位置，可选值有 start、end。start 表示在文档开头添加内容；end 表示在文档结尾添加内容，默认值为 end。",
                  "max": null,
                  "min": null,
                  "name": "position",
                  "options": [
                    {
                      "label": {
                        "en_US": "document start",
                        "zh_Hans": "文档开始"
                      },
                      "value": "start"
                    },
                    {
                      "label": {
                        "en_US": "document end",
                        "zh_Hans": "文档结束"
                      },
                      "value": "end"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "List lark document blocks",
                  "zh_Hans": "获取 Lark 文档所有块的富文本内容并分页返回"
                },
                "llm": "A tool to get all blocks of Lark documents"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "List Lark Document Blocks",
                  "zh_Hans": "获取 Lark 文档所有块"
                },
                "name": "list_document_blocks"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Unique identifier for a Lark document. You can also input the document's URL.",
                    "zh_Hans": "Lark 文档的唯一标识，支持输入文档的 URL。"
                  },
                  "label": {
                    "en_US": "document_id",
                    "zh_Hans": "Lark 文档的唯一标识"
                  },
                  "llm_description": "Lark 文档的唯一标识，支持输入文档的 URL。",
                  "max": null,
                  "min": null,
                  "name": "document_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "open_id",
                  "form": "form",
                  "human_description": {
                    "en_US": "User ID type, optional values are open_id, union_id, user_id, with a default value of open_id.",
                    "zh_Hans": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。"
                  },
                  "label": {
                    "en_US": "user_id_type",
                    "zh_Hans": "用户 ID 类型"
                  },
                  "llm_description": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。",
                  "max": null,
                  "min": null,
                  "name": "user_id_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "open_id",
                        "zh_Hans": "open_id"
                      },
                      "value": "open_id"
                    },
                    {
                      "label": {
                        "en_US": "union_id",
                        "zh_Hans": "union_id"
                      },
                      "value": "union_id"
                    },
                    {
                      "label": {
                        "en_US": "user_id",
                        "zh_Hans": "user_id"
                      },
                      "value": "user_id"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 500,
                  "form": "form",
                  "human_description": {
                    "en_US": "Paging size, the default and maximum value is 500.",
                    "zh_Hans": "分页大小, 默认值和最大值为 500。"
                  },
                  "label": {
                    "en_US": "page_size",
                    "zh_Hans": "分页大小"
                  },
                  "llm_description": "分页大小, 表示一次请求最多返回多少条数据，默认值和最大值为 500。",
                  "max": null,
                  "min": null,
                  "name": "page_size",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Pagination token used to navigate through query results, allowing retrieval of additional items in subsequent requests.",
                    "zh_Hans": "分页标记，用于分页查询结果，以便下次遍历时获取更多项。"
                  },
                  "label": {
                    "en_US": "page_token",
                    "zh_Hans": "分页标记"
                  },
                  "llm_description": "分页标记，第一次请求不填，表示从头开始遍历；分页查询结果还有更多项时会同时返回新的 page_token，下次遍历可采用该 page_token 获取查询结果。",
                  "max": null,
                  "min": null,
                  "name": "page_token",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-26T10:45:16Z",
        "version_updated_at": "2025-02-26T10:45:16Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Image-1X",
          "zh_Hans": "阶跃星辰绘画"
        },
        "category": "tool",
        "created_at": "2024-12-06T11:03:41Z",
        "endpoint": {},
        "icon": "langgenius/packages/stepfun_tool/_assets/icon.png",
        "index_id": "langgenius___stepfun_tool",
        "install_count": 433,
        "introduction": "## Overview\n\n**Image-1X** is a text-to-image generation tool powered by AI. With **step-1x**, a text-to-image tool, you can effortlessly transform text prompts into stunning visuals. This tool is ideal for creative projects, visual storytelling, and generating unique images based on textual descriptions.\n\n## Configuration\n\nTo start using **Image-1X**, follow these steps:\n\n1. **Install Image-1X Tool**\nAccess the Plugin Marketplace and install the Vectorizer.AI tool.\n\n2. **Apply for a Image-1X API Key**\nGo to the Image-1X API Keys page, create a new API Key, and ensure your account has sufficient balance.\n\n3. **Authorize Image-1X**\nNavigate to **Tools > Image-1X > To Authorize** in your application and provide API Key ID and Secret to activate the plugin.\n\n![](./_assets/stepfun-01.png)\n\nStepfun base URL:\n\n```text\nhttps://platform.stepfun.com/console-tools\n```\n\n## Tool Feature\n\nThe **step-1x** action generates an image from the provided text prompt using advanced AI capabilities.\n\n### step-1x Action\n\n**Prompt** (*String, Required*):\n* Description: A textual description of the desired image. This is the main input for generating the image.\n* Example: *\"A futuristic cityscape at sunset with flying cars.\"*\n\n**Image Size** (*String*):\n* Description: Specifies the dimensions of the output image.\n* Default: `1024x1024`\n* Options: Choose the size depending on your project needs (e.g., `512x512`, `1024x1024`).\n\n**Number of Generated Images** (*Integer, Required*):\n* Description: The number of images generated in a single run.\n* Default: `1`\n* Example: Set to `2` to generate two variations of the image from the same prompt.\n\n**Seed** (*Integer*):\n* Description: Sets the seed value for reproducibility. Using the same seed with the same prompt will produce identical results.\n* Default: `10`\n* Example: Change the seed value for diverse outputs.\n\n**Steps** (*Integer*):\n* Description: The number of inference steps used during image generation. Higher values improve image quality but increase processing time.\n* Default: `50`\n* Example: Use `25` for faster results or `100` for finer details.\n\n**Classifier-Free Guidance Scale** (*Float*):\n* Description: Controls how strongly the tool follows the given prompt. Higher values make the result more aligned with the prompt but may reduce creativity.\n* Default: `7.5`\n* Range: Adjust values between `1.0` (less focused) and `15.0` (highly focused).\n\n<img src=\"./_assets/stepfun-02.png\" width=\"400\" />\n\n## Usage\n\nImage-1X can seamlessly integrate **Chatflow / Workflow Apps** and **Agent Apps**.\n\n### Chatflow / Workflow Apps\n\n1. Add the Image-1X node to your Chatflow or Workflow pipeline.\n2. Input the text prompt into the node configuration.\n3. Execute the pipeline to generate the image, which can be used or displayed as part of your application's workflow.\n\n![](./_assets/stepfun-03.png)\n\n### Agent Apps\n\n1. Add the Image-1X tool to your Agent application.\n2. Send a text prompt via the chat interface to describe the image you want to create.\n3. The tool will process the prompt and return the generated image in real time.\n\n![](./_assets/stepfun-04.png)\n\n## Use Cases\n\n* **Creative Content**: Generate artwork, illustrations, or concept designs based on descriptive text.\n* **Storytelling**: Visualize scenes, characters, or settings for narratives or presentations.\n* **Marketing and Branding**: Create unique visual assets for campaigns or advertisements.\n* **Prototyping**: Quickly generate visual references for design or creative projects.\n\nImage-1X simplifies the process of image generation, allowing you to bring their ideas to life with just a text prompt.\n",
        "label": {
          "en_US": "Image-1X",
          "zh_Hans": "阶跃星辰绘画"
        },
        "latest_package_identifier": "langgenius/stepfun_tool:0.0.2@0a937eab4d67f9044e2a21c69fa0c64f347ae3ea6d304a87ddecdce4a1ad2adc",
        "latest_version": "0.0.2",
        "model": {},
        "name": "stepfun_tool",
        "org": "langgenius",
        "plugin_id": "langgenius/stepfun_tool",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/stepfun.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "image"
          },
          {
            "name": "productivity"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "Stepfun API key",
                "zh_Hans": "阶跃星辰API key"
              },
              "name": "stepfun_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Stepfun API key",
                "zh_Hans": "请输入你的阶跃星辰 API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://platform.stepfun.com/interface-key"
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "Stepfun base URL",
                "zh_Hans": "阶跃星辰 base URL"
              },
              "name": "stepfun_base_url",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Stepfun base URL",
                "zh_Hans": "请输入你的阶跃星辰 base URL"
              },
              "required": false,
              "scope": null,
              "type": "text-input",
              "url": null
            }
          ],
          "identity": {
            "author": "Stepfun",
            "description": {
              "en_US": "Image-1X",
              "zh_Hans": "阶跃星辰绘画"
            },
            "icon": "icon.png",
            "label": {
              "en_US": "Image-1X",
              "zh_Hans": "阶跃星辰绘画"
            },
            "name": "stepfun",
            "tags": [
              "image",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "step-1x is a text to image tool",
                  "pt_BR": "step-1x is a text to image tool",
                  "zh_Hans": "step-1x 是一个文本/图像到图像的工具"
                },
                "llm": "step-1x is a tool used to generate images from text or image"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Stepfun",
                "label": {
                  "en_US": "step-1x",
                  "pt_BR": "step-1x",
                  "zh_Hans": "阶跃星辰绘画"
                },
                "name": "stepfun"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Image prompt, you can check the official documentation of step-1x",
                    "pt_BR": "Image prompt, you can check the official documentation of step-1x",
                    "zh_Hans": "图像提示词，您可以查看 step-1x 的官方文档"
                  },
                  "label": {
                    "en_US": "Prompt",
                    "pt_BR": "Prompt",
                    "zh_Hans": "提示词"
                  },
                  "llm_description": "Image prompt of step-1x you should describe the image you want to generate as a list of words as possible as detailed",
                  "max": null,
                  "min": null,
                  "name": "prompt",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "1024x1024",
                  "form": "form",
                  "human_description": {
                    "en_US": "The size of the generated image",
                    "pt_BR": "The size of the generated image",
                    "zh_Hans": "生成的图片大小"
                  },
                  "label": {
                    "en_US": "Image size",
                    "pt_BR": "Image size",
                    "zh_Hans": "图像大小"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "size",
                  "options": [
                    {
                      "label": {
                        "en_US": "256x256",
                        "pt_BR": "256x256",
                        "zh_Hans": "256x256"
                      },
                      "value": "256x256"
                    },
                    {
                      "label": {
                        "en_US": "512x512",
                        "pt_BR": "512x512",
                        "zh_Hans": "512x512"
                      },
                      "value": "512x512"
                    },
                    {
                      "label": {
                        "en_US": "768x768",
                        "pt_BR": "768x768",
                        "zh_Hans": "768x768"
                      },
                      "value": "768x768"
                    },
                    {
                      "label": {
                        "en_US": "1024x1024",
                        "pt_BR": "1024x1024",
                        "zh_Hans": "1024x1024"
                      },
                      "value": "1024x1024"
                    },
                    {
                      "label": {
                        "en_US": "1280x800",
                        "pt_BR": "1280x800",
                        "zh_Hans": "1280x800"
                      },
                      "value": "1280x800"
                    },
                    {
                      "label": {
                        "en_US": "800x1280",
                        "pt_BR": "800x1280",
                        "zh_Hans": "800x1280"
                      },
                      "value": "800x1280"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 1,
                  "form": "form",
                  "human_description": {
                    "en_US": "Number of generated images, now only one image can be generated at a time",
                    "pt_BR": "Number of generated images, now only one image can be generated at a time",
                    "zh_Hans": "生成的图像数量，当前仅支持每次生成一张图片"
                  },
                  "label": {
                    "en_US": "Number of generated images",
                    "pt_BR": "Number of generated images",
                    "zh_Hans": "生成的图像数量"
                  },
                  "llm_description": "",
                  "max": 1,
                  "min": 1,
                  "name": "n",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 10,
                  "form": "form",
                  "human_description": {
                    "en_US": "seed",
                    "pt_BR": "seed",
                    "zh_Hans": "seed"
                  },
                  "label": {
                    "en_US": "seed",
                    "pt_BR": "seed",
                    "zh_Hans": "seed"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 50,
                  "form": "form",
                  "human_description": {
                    "en_US": "Steps, now support integers between 1 and 100",
                    "pt_BR": "Steps, now support integers between 1 and 100",
                    "zh_Hans": "Steps, 当前支持 1～100 之间整数"
                  },
                  "label": {
                    "en_US": "Steps",
                    "pt_BR": "Steps",
                    "zh_Hans": "Steps"
                  },
                  "llm_description": "",
                  "max": 100,
                  "min": 1,
                  "name": "steps",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 7.5,
                  "form": "form",
                  "human_description": {
                    "en_US": "classifier-free guidance scale",
                    "pt_BR": "classifier-free guidance scale",
                    "zh_Hans": "classifier-free guidance scale"
                  },
                  "label": {
                    "en_US": "classifier-free guidance scale",
                    "pt_BR": "classifier-free guidance scale",
                    "zh_Hans": "classifier-free guidance scale"
                  },
                  "llm_description": "",
                  "max": 10,
                  "min": 1,
                  "name": "cfg_scale",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:12:00Z",
        "version_updated_at": "2025-02-17T07:12:00Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Google Drive",
          "ja_JP": "Google Drive",
          "pt_BR": "Google Drive",
          "zh_Hans": "Google Drive"
        },
        "category": "tool",
        "created_at": "2025-03-14T11:45:25Z",
        "endpoint": {},
        "icon": "yoshiki-0428/packages/google_drive/_assets/icon.svg",
        "index_id": "yoshiki-0428___google_drive",
        "install_count": 432,
        "introduction": "# Google Drive Tools\n\n**Author:** yoshiki-0428  \n**Version:** 0.0.1  \n**Type:** tool  \n\n## Description\n\nThis plugin provides a set of tools for integrating Google Drive with Dify applications. It allows you to search, create, and manage files and folders in Google Drive directly from your Dify workflows and agents.\n\n## Tools Included\n\n1. **File Search** - Search for files in Google Drive by name\n2. **Folder Search** - Find folders in Google Drive by name\n3. **Create File** - Upload files to Google Drive\n4. **Create Folder** - Create new folders in Google Drive\n\n## Setup\n\n### Prerequisites\n\n- A Google Cloud Platform account\n- A Google Cloud project with the Google Drive API enabled\n- A service account with appropriate permissions for Google Drive\n\n### Creating a Service Account\n\n1. Go to the [Google Cloud Console](https://console.cloud.google.com/)\n2. Create a new project or select an existing one\n3. Enable the Google Drive API for your project\n4. Create a service account:\n   - Go to \"IAM & Admin\" > \"Service Accounts\"\n   - Click \"Create Service Account\"\n   - Give it a name and description\n   - Grant it appropriate roles (at least \"Drive File Creator\" and \"Drive Viewer\")\n   - Click \"Create\"\n5. Create a key for the service account:\n   - Click on the service account you just created\n   - Go to the \"Keys\" tab\n   - Click \"Add Key\" > \"Create new key\"\n   - Choose JSON format and click \"Create\"\n   - Save the downloaded JSON file securely\n\n### Configuration in Dify\n\n1. In your Dify application, go to the Plugins section\n2. Find and install the Google Drive plugin\n3. When configuring the plugin, you'll need to provide:\n   - **credentials_json**: The entire content of the service account JSON key file\n\n## Usage Examples\n\n### Search for Files\n\nUse the File Search tool to find files in Google Drive by name:\n\n```\nInput:\n{\n  \"query\": \"quarterly report\",\n  \"max_results\": 5,\n  \"parent_id\": \"optional_folder_id\"\n}\n\nOutput:\n{\n  \"file_count\": 2,\n  \"files\": [\n    {\n      \"id\": \"1AbCdEfGhIjKlMnOpQrStUvWxYz\",\n      \"name\": \"Q1 Quarterly Report.pdf\",\n      \"mime_type\": \"application/pdf\",\n      \"web_view_link\": \"https://drive.google.com/file/d/1AbCdEfGhIjKlMnOpQrStUvWxYz/view\"\n    },\n    {\n      \"id\": \"2BcDeFgHiJkLmNoPqRsTuVwXyZ\",\n      \"name\": \"Q2 Quarterly Report.docx\",\n      \"mime_type\": \"application/vnd.openxmlformats-officedocument.wordprocessingml.document\",\n      \"web_view_link\": \"https://drive.google.com/file/d/2BcDeFgHiJkLmNoPqRsTuVwXyZ/view\"\n    }\n  ]\n}\n```\n\n### Create a Folder\n\nUse the Create Folder tool to create a new folder in Google Drive:\n\n```\nInput:\n{\n  \"name\": \"Project Documents\",\n  \"parent_id\": \"optional_parent_folder_id\"\n}\n\nOutput:\n{\n  \"id\": \"3CdEfGhIjKlMnOpQrStUvWxYz\",\n  \"name\": \"Project Documents\",\n  \"web_view_link\": \"https://drive.google.com/drive/folders/3CdEfGhIjKlMnOpQrStUvWxYz\",\n  \"success\": true\n}\n```\n\n### Upload a File\n\nUse the Create File tool to upload a file to Google Drive:\n\n```\nInput:\n{\n  \"file\": {file_object},\n  \"name\": \"presentation.pptx\",\n  \"folder_name\": \"Project Presentations\"\n}\n\nOutput:\n{\n  \"id\": \"4DeFgHiJkLmNoPqRsTuVwXyZ\",\n  \"name\": \"presentation.pptx\",\n  \"parent_id\": \"5EfGhIjKlMnOpQrStUvWxYz\",\n  \"folder_name\": \"Project Presentations\",\n  \"mime_type\": \"application/vnd.openxmlformats-officedocument.presentationml.presentation\",\n  \"web_view_link\": \"https://drive.google.com/file/d/4DeFgHiJkLmNoPqRsTuVwXyZ/view\",\n  \"success\": true\n}\n```\n\n## Permissions and Security\n\n- The tools operate with the permissions of the service account you configured\n- To access user-specific files, you'll need to share those files with the service account email\n- For shared drives, the service account needs to be added as a member of the shared drive\n\n## Troubleshooting\n\nIf you encounter issues:\n\n1. Verify that the Google Drive API is enabled in your Google Cloud project\n2. Check that the service account has the necessary permissions\n3. Ensure the credentials JSON is correctly formatted and complete\n4. For \"File not found\" errors, verify that the file exists and is accessible to the service account\n\n## Support\n\nFor issues or feature requests, please open an issue in the [Dify Official Plugins repository](https://github.com/langgenius/dify-official-plugins).\n",
        "label": {
          "en_US": "Google Drive",
          "ja_JP": "Google Drive",
          "pt_BR": "Google Drive",
          "zh_Hans": "Google Drive"
        },
        "latest_package_identifier": "yoshiki-0428/google_drive:0.0.1@5c17eb6413e263c214a7c59e4581d528658d90d886319687033d59416eaef96e",
        "latest_version": "0.0.1",
        "model": {},
        "name": "google_drive",
        "org": "yoshiki-0428",
        "plugin_id": "yoshiki-0428/google_drive",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/google_drive.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {}
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Get your credentials JSON from Google",
                "pt_BR": "Get your credentials JSON from Google",
                "zh_Hans": "从 Google 获取您的 credentials JSON"
              },
              "label": {
                "en_US": "Credentials JSON",
                "pt_BR": "Credentials JSON",
                "zh_Hans": "Credentials JSON"
              },
              "name": "credentials_json",
              "options": null,
              "placeholder": {
                "en_US": "Please input your credentials JSON",
                "pt_BR": "Please input your credentials JSON",
                "zh_Hans": "请输入您的 credentials JSON"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            }
          ],
          "identity": {
            "author": "yoshiki-0428",
            "description": {
              "en_US": "Google Drive",
              "pt_BR": "Google Drive",
              "zh_Hans": "Google Drive"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Google Drive",
              "pt_BR": "Google Drive",
              "zh_Hans": "Google Drive"
            },
            "name": "google_drive",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Search for folders in Google Drive by name",
                  "pt_BR": "Pesquisar pastas no Google Drive por nome",
                  "zh_Hans": "按名称搜索 Google Drive 文件夹"
                },
                "llm": "Search for folders in Google Drive by name"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "yoshiki-0428",
                "label": {
                  "en_US": "Search for Google Drive folders",
                  "pt_BR": "Pesquisar pastas do Google Drive",
                  "zh_Hans": "搜索 Google Drive 文件夹"
                },
                "name": "google-drive-folder-search"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Text to search for in folder names",
                    "pt_BR": "Texto para pesquisar em nomes de pastas",
                    "zh_Hans": "在文件夹名称中搜索的文本"
                  },
                  "label": {
                    "en_US": "Search query",
                    "pt_BR": "Consulta de pesquisa",
                    "zh_Hans": "搜索查询"
                  },
                  "llm_description": "Text to search for in folder names",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 10,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Maximum number of folders to return",
                    "pt_BR": "Número máximo de pastas a retornar",
                    "zh_Hans": "返回的最大文件夹数"
                  },
                  "label": {
                    "en_US": "Maximum number of results",
                    "pt_BR": "Número máximo de resultados",
                    "zh_Hans": "最大结果数"
                  },
                  "llm_description": "Maximum number of folders to return",
                  "max": null,
                  "min": null,
                  "name": "max_results",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "ID of the parent folder to search in",
                    "pt_BR": "ID da pasta pai para pesquisar",
                    "zh_Hans": "要搜索的父文件夹 ID"
                  },
                  "label": {
                    "en_US": "Parent folder ID",
                    "pt_BR": "ID da pasta pai",
                    "zh_Hans": "父文件夹 ID"
                  },
                  "llm_description": "ID of the parent folder to search in",
                  "max": null,
                  "min": null,
                  "name": "parent_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Search for files in Google Drive by name",
                  "pt_BR": "Pesquisar arquivos no Google Drive por nome",
                  "zh_Hans": "按名称搜索 Google Drive 文件"
                },
                "llm": "Search for files in Google Drive by name"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "yoshiki-0428",
                "label": {
                  "en_US": "Search for Google Drive files",
                  "pt_BR": "Pesquisar arquivos do Google Drive",
                  "zh_Hans": "搜索 Google Drive 文件"
                },
                "name": "google-drive-file-search"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Text to search for in file names",
                    "pt_BR": "Texto para pesquisar em nomes de arquivos",
                    "zh_Hans": "在文件名称中搜索的文本"
                  },
                  "label": {
                    "en_US": "Search query",
                    "pt_BR": "Consulta de pesquisa",
                    "zh_Hans": "搜索查询"
                  },
                  "llm_description": "Text to search for in file names",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 10,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Maximum number of files to return",
                    "pt_BR": "Número máximo de arquivos a retornar",
                    "zh_Hans": "返回的最大文件数"
                  },
                  "label": {
                    "en_US": "Maximum number of results",
                    "pt_BR": "Número máximo de resultados",
                    "zh_Hans": "最大结果数"
                  },
                  "llm_description": "Maximum number of files to return",
                  "max": null,
                  "min": null,
                  "name": "max_results",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "ID of the parent folder to search in",
                    "pt_BR": "ID da pasta pai para pesquisar",
                    "zh_Hans": "要搜索的父文件夹ID"
                  },
                  "label": {
                    "en_US": "Parent folder ID",
                    "pt_BR": "ID da pasta pai",
                    "zh_Hans": "父文件夹ID"
                  },
                  "llm_description": "ID of the parent folder to search in. If not provided, will search in all accessible folders",
                  "max": null,
                  "min": null,
                  "name": "parent_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Filter by file type",
                    "pt_BR": "Filtrar por tipo de arquivo",
                    "zh_Hans": "按文件类型过滤"
                  },
                  "label": {
                    "en_US": "File type",
                    "pt_BR": "Tipo de arquivo",
                    "zh_Hans": "文件类型"
                  },
                  "llm_description": "Filter by file type. Options include 'document', 'spreadsheet', 'presentation', 'pdf', 'image', 'video', 'audio'",
                  "max": null,
                  "min": null,
                  "name": "file_type",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Create a new folder in Google Drive",
                  "pt_BR": "Criar uma nova pasta no Google Drive",
                  "zh_Hans": "在 Google Drive 中创建新文件夹"
                },
                "llm": "Create a new folder in Google Drive with a specified name and parent location"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "yoshiki-0428",
                "label": {
                  "en_US": "Create Google Drive folder",
                  "pt_BR": "Criar pasta no Google Drive",
                  "zh_Hans": "创建 Google Drive 文件夹"
                },
                "name": "google-drive-create-folder"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Name of the folder to create",
                    "pt_BR": "Nome da pasta a ser criada",
                    "zh_Hans": "要创建的文件夹名称"
                  },
                  "label": {
                    "en_US": "Folder name",
                    "pt_BR": "Nome da pasta",
                    "zh_Hans": "文件夹名称"
                  },
                  "llm_description": "Name of the folder to create",
                  "max": null,
                  "min": null,
                  "name": "name",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "root",
                  "form": "llm",
                  "human_description": {
                    "en_US": "ID of the parent folder where the new folder will be created (default is root)",
                    "pt_BR": "ID da pasta pai onde a nova pasta será criada (o padrão é a pasta raiz)",
                    "zh_Hans": "新文件夹将在其中创建的父文件夹的ID（默认为根文件夹）"
                  },
                  "label": {
                    "en_US": "Parent folder ID",
                    "pt_BR": "ID da pasta pai",
                    "zh_Hans": "父文件夹ID"
                  },
                  "llm_description": "ID of the parent folder where the new folder will be created. Use 'root' for the root folder.",
                  "max": null,
                  "min": null,
                  "name": "parent_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Create a new file in Google Drive",
                  "pt_BR": "Criar um novo arquivo no Google Drive",
                  "zh_Hans": "在Google Drive中创建新文件"
                },
                "llm": "Creates a new file in Google Drive. The file content can be uploaded directly from a URL. You can specify either a parent folder ID or a folder name to organize your file. If you use a folder name that doesn't exist, it will be automatically created."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "yoshiki-0428",
                "label": {
                  "en_US": "Create Google Drive file",
                  "pt_BR": "Criar arquivo no Google Drive",
                  "zh_Hans": "创建 Google Drive 文件"
                },
                "name": "google-drive-create-file"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "File to upload to Google Drive",
                    "pt_BR": "Arquivo para enviar ao Google Drive",
                    "zh_Hans": "要上传到 Google Drive 的文件"
                  },
                  "label": {
                    "en_US": "File",
                    "pt_BR": "Arquivo",
                    "zh_Hans": "文件"
                  },
                  "llm_description": "File to upload to Google Drive",
                  "max": null,
                  "min": null,
                  "name": "file",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "file"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Name of the file to create (if empty, will use the original filename)",
                    "pt_BR": "Nome do arquivo a ser criado (se vazio, usará o nome do arquivo original)",
                    "zh_Hans": "要创建的文件名称（如果为空，将使用原始文件名）"
                  },
                  "label": {
                    "en_US": "File name",
                    "pt_BR": "Nome do arquivo",
                    "zh_Hans": "文件名称"
                  },
                  "llm_description": "Name of the file to create. If not provided, the original filename will be used.",
                  "max": null,
                  "min": null,
                  "name": "name",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Name of the folder to save the file to. If it doesn't exist, it will be created.",
                    "pt_BR": "Nome da pasta para salvar o arquivo. Se não existir, será criada.",
                    "zh_Hans": "保存文件的文件夹名称。如果文件夹不存在，将会被创建。"
                  },
                  "label": {
                    "en_US": "Folder name",
                    "pt_BR": "Nome da pasta",
                    "zh_Hans": "文件夹名称"
                  },
                  "llm_description": "Name of the folder to save the file to. If the folder doesn't exist, it will be created automatically. You can use this parameter instead of parent_id for easier folder selection.",
                  "max": null,
                  "min": null,
                  "name": "folder_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "root",
                  "form": "llm",
                  "human_description": {
                    "en_US": "ID of the parent folder where the new file will be created (default is root)",
                    "pt_BR": "ID da pasta pai onde o novo arquivo será criado (o padrão é a pasta raiz)",
                    "zh_Hans": "新文件将在其中创建的父文件夹的ID（默认为根文件夹）"
                  },
                  "label": {
                    "en_US": "Parent folder ID",
                    "pt_BR": "ID da pasta pai",
                    "zh_Hans": "父文件夹ID"
                  },
                  "llm_description": "ID of the parent folder where the new file will be created. Use 'root' for the root folder. Note - if folder_name is provided, it will take precedence over parent_id.",
                  "max": null,
                  "min": null,
                  "name": "parent_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-14T11:45:31Z",
        "version_updated_at": "2025-03-14T11:45:31Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Self deployed model provider - Amazon SageMaker",
          "ja_JP": "Self deployed model provider - Amazon SageMaker",
          "pt_BR": "Self deployed model provider - Amazon SageMaker",
          "zh_Hans": "Self deployed model provider - Amazon SageMaker"
        },
        "category": "model",
        "created_at": "2024-12-06T10:43:27Z",
        "endpoint": {},
        "icon": "langgenius/packages/sagemaker/_assets/icon_s_en.png",
        "index_id": "langgenius___sagemaker",
        "install_count": 427,
        "introduction": "## Amazon Sagemaker\n\n**Author:** aws  \n**Type:** Model Provider\n\n\n\n## Overview | 概述\n\nThe [Amazon Sagemaker](https://aws.amazon.com/sagemaker/) is a fully managed service that brings together a broad set of tools to enable high-performance, low-cost ML for any use case. With SageMaker AI, you can build, train and deploy ML models at scale using tools like notebooks, debuggers, profilers, pipelines, MLOps, and more – all in one integrated development environment (IDE).\n\n[Amazon Sagemaker](https://aws.amazon.com/sagemaker/) 是一项完全托管的服务，它汇集了广泛的工具集，为任何用例提供高性能、低成本的机器学习能力。通过 SageMaker AI，您可以使用笔记本、调试器、性能分析器、管道、MLOps 等工具在一个集成开发环境 (IDE) 中大规模构建、训练和部署机器学习模型。\n\n\n\n## Configure | 配置\n\nAfter installing the plugin, configure the Sagemaker endpoint url within the Model Provider settings. Obtain your endpoint url from [here](https://console.aws.amazon.com/console/home?nc2=h_ct&src=header-signin). Once saved, you can begin using Sagemaker to build your AI agents and agentic workflows.\n\n安装插件后，在模型提供商设置中配置 Sagemaker 端点 URL。您可以从[这里](https://console.aws.amazon.com/console/home?nc2=h_ct&src=header-signin)获取端点 URL。保存后，您就可以开始使用 Sagemaker 构建 AI 代理和代理工作流。\n\n![](./_assets/sagemaker_model.PNG)\n\nYou could add model through the `settings -> model provider -> Sagemaker` page.\n\n您可以通过 `设置 -> 模型提供商 -> Sagemaker` 页面添加模型。\n\n![](./_assets/sagemaker_config.PNG)\n\n## Examples & Feedback | 示例 & 反馈\n\nFor more detailed information, please refer to [aws-sample/dify-aws-tool](https://github.com/aws-samples/dify-aws-tool/), which contains multiple workflows for reference.\n\nIf you have issues that need feedback, feel free to raise questions or look for answers in the [Issue](https://github.com/aws-samples/dify-aws-tool/issues) section.\n\n更多详细信息可以参考 [aws-sample/dify-aws-tool](https://github.com/aws-samples/dify-aws-tool/)，其中包含多个 workflow 供参考。\n\n如果存在问题需要反馈，欢迎到 [Issue](https://github.com/aws-samples/dify-aws-tool/issues) 去提出问题或者寻找答案。\n",
        "label": {
          "en_US": "Amazon SageMaker",
          "ja_JP": "Amazon SageMaker",
          "pt_BR": "Amazon SageMaker",
          "zh_Hans": "Amazon SageMaker"
        },
        "latest_package_identifier": "langgenius/sagemaker:0.0.6@f69820cffa1d29054b013012d7713d2c94fb0c42ebce9448132cfd9ef6a87568",
        "latest_version": "0.0.6",
        "model": {
          "background": "#ECE9E3",
          "configurate_methods": [
            "customizable-model"
          ],
          "description": {
            "en_US": "Customized model on SageMaker",
            "zh_Hans": "SageMaker上的私有化部署的模型"
          },
          "help": {
            "title": {
              "en_US": "How to deploy customized model on SageMaker",
              "zh_Hans": "如何在Sagemaker上的私有化部署的模型"
            },
            "url": {
              "en_US": "https://github.com/aws-samples/dify-aws-tool/blob/main/README.md#how-to-deploy-sagemaker-endpoint",
              "zh_Hans": "https://github.com/aws-samples/dify-aws-tool/blob/main/README_ZH.md#%E5%A6%82%E4%BD%95%E9%83%A8%E7%BD%B2sagemaker%E6%8E%A8%E7%90%86%E7%AB%AF%E7%82%B9"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.png"
          },
          "icon_small": {
            "en_US": "icon_s_en.png"
          },
          "label": {
            "en_US": "Amazon SageMaker"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": "chat",
                "label": {
                  "en_US": "Completion mode"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Chat",
                      "zh_Hans": "Chat"
                    },
                    "show_on": [],
                    "value": "chat"
                  }
                ],
                "placeholder": {
                  "en_US": "Select completion mode",
                  "zh_Hans": "选择对话类型"
                },
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "select",
                "variable": "mode"
              },
              {
                "default": null,
                "label": {
                  "en_US": "sagemaker endpoint"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Sagemaker Inference endpoint",
                  "zh_Hans": "请输出你的Sagemaker推理端点"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "sagemaker_endpoint"
              },
              {
                "default": "4096",
                "label": {
                  "en_US": "Model context size",
                  "zh_Hans": "模型上下文长度"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Model context size",
                  "zh_Hans": "在此输入您的模型上下文长度"
                },
                "required": true,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "text-input",
                "variable": "context_length"
              },
              {
                "default": null,
                "label": {
                  "en_US": "audio cache bucket(s3 bucket)",
                  "zh_Hans": "音频缓存桶(s3 bucket)"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "sagemaker-us-east-1-*******7838",
                  "zh_Hans": "sagemaker-us-east-1-******207838"
                },
                "required": true,
                "show_on": [
                  {
                    "value": "speech2text",
                    "variable": "__model_type"
                  }
                ],
                "type": "text-input",
                "variable": "audio_s3_cache_bucket"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Audio model type"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "preset voice",
                      "zh_Hans": "内置音色"
                    },
                    "show_on": [],
                    "value": "PresetVoice"
                  },
                  {
                    "label": {
                      "en_US": "clone voice",
                      "zh_Hans": "克隆音色"
                    },
                    "show_on": [],
                    "value": "CloneVoice"
                  },
                  {
                    "label": {
                      "en_US": "crosslingual clone voice",
                      "zh_Hans": "跨语种克隆音色"
                    },
                    "show_on": [],
                    "value": "CloneVoice_CrossLingual"
                  },
                  {
                    "label": {
                      "en_US": "Instruct voice",
                      "zh_Hans": "文字指令音色"
                    },
                    "show_on": [],
                    "value": "InstructVoice"
                  }
                ],
                "placeholder": {
                  "en_US": "Audio model type",
                  "zh_Hans": "语音模型类型"
                },
                "required": true,
                "show_on": [
                  {
                    "value": "tts",
                    "variable": "__model_type"
                  }
                ],
                "type": "select",
                "variable": "audio_model_type"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Mock Audio Source"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "source audio to be mocked",
                  "zh_Hans": "被模仿的音色音频"
                },
                "required": false,
                "show_on": [
                  {
                    "value": "tts",
                    "variable": "__model_type"
                  }
                ],
                "type": "text-input",
                "variable": "prompt_audio"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Prompt Audio Text"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "text for the mocked source audio",
                  "zh_Hans": "模仿音色的对应文本"
                },
                "required": false,
                "show_on": [
                  {
                    "value": "tts",
                    "variable": "__model_type"
                  }
                ],
                "type": "text-input",
                "variable": "prompt_text"
              },
              {
                "default": null,
                "label": {
                  "en_US": "instruct text for speaker"
                },
                "max_length": 0,
                "options": [],
                "placeholder": null,
                "required": false,
                "show_on": [
                  {
                    "value": "tts",
                    "variable": "__model_type"
                  }
                ],
                "type": "text-input",
                "variable": "instruct_text"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Access Key (If not provided, credentials are obtained from the running environment.)",
                  "zh_Hans": "Access Key (如果未提供，凭证将从运行环境中获取。)"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Access Key",
                  "zh_Hans": "在此输入您的 Access Key"
                },
                "required": false,
                "show_on": [],
                "type": "secret-input",
                "variable": "aws_access_key_id"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Secret Access Key",
                  "zh_Hans": "Secret Access Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Secret Access Key",
                  "zh_Hans": "在此输入您的 Secret Access Key"
                },
                "required": false,
                "show_on": [],
                "type": "secret-input",
                "variable": "aws_secret_access_key"
              },
              {
                "default": "us-east-1",
                "label": {
                  "en_US": "AWS Region",
                  "zh_Hans": "AWS 地区"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "US East (N. Virginia)",
                      "zh_Hans": "美国东部 (弗吉尼亚北部)"
                    },
                    "show_on": [],
                    "value": "us-east-1"
                  },
                  {
                    "label": {
                      "en_US": "US West (Oregon)",
                      "zh_Hans": "美国西部 (俄勒冈州)"
                    },
                    "show_on": [],
                    "value": "us-west-2"
                  },
                  {
                    "label": {
                      "en_US": "Asia Pacific (Singapore)",
                      "zh_Hans": "亚太地区 (新加坡)"
                    },
                    "show_on": [],
                    "value": "ap-southeast-1"
                  },
                  {
                    "label": {
                      "en_US": "Asia Pacific (Tokyo)",
                      "zh_Hans": "亚太地区 (东京)"
                    },
                    "show_on": [],
                    "value": "ap-northeast-1"
                  },
                  {
                    "label": {
                      "en_US": "Europe (Frankfurt)",
                      "zh_Hans": "欧洲 (法兰克福)"
                    },
                    "show_on": [],
                    "value": "eu-central-1"
                  },
                  {
                    "label": {
                      "en_US": "AWS GovCloud (US-West)",
                      "zh_Hans": "AWS GovCloud (US-West)"
                    },
                    "show_on": [],
                    "value": "us-gov-west-1"
                  },
                  {
                    "label": {
                      "en_US": "Asia Pacific (Sydney)",
                      "zh_Hans": "亚太地区 (悉尼)"
                    },
                    "show_on": [],
                    "value": "ap-southeast-2"
                  },
                  {
                    "label": {
                      "en_US": "AWS Beijing (cn-north-1)",
                      "zh_Hans": "中国北京 (cn-north-1)"
                    },
                    "show_on": [],
                    "value": "cn-north-1"
                  },
                  {
                    "label": {
                      "en_US": "AWS Ningxia (cn-northwest-1)",
                      "zh_Hans": "中国宁夏 (cn-northwest-1)"
                    },
                    "show_on": [],
                    "value": "cn-northwest-1"
                  }
                ],
                "placeholder": null,
                "required": false,
                "show_on": [],
                "type": "select",
                "variable": "aws_region"
              }
            ],
            "model": {
              "label": {
                "en_US": "Model Name",
                "zh_Hans": "模型名称"
              },
              "placeholder": {
                "en_US": "Enter your model name",
                "zh_Hans": "输入模型名称"
              }
            }
          },
          "models": [],
          "provider": "sagemaker",
          "provider_credential_schema": null,
          "supported_model_types": [
            "llm",
            "text-embedding",
            "rerank",
            "speech2text",
            "tts"
          ]
        },
        "name": "sagemaker",
        "org": "langgenius",
        "plugin_id": "langgenius/sagemaker",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/sagemaker.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-03-17T01:37:44Z",
        "version_updated_at": "2025-03-17T01:37:44Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Feishu calendar, requires the following permissions: calendar:calendar:read、calendar:calendar、contact:user.id:readonly.",
          "zh_Hans": "飞书日历，需要开通以下权限: calendar:calendar:read、calendar:calendar、contact:user.id:readonly。"
        },
        "category": "tool",
        "created_at": "2025-02-26T10:40:57Z",
        "endpoint": {},
        "icon": "langgenius/packages/feishu_calendar/_assets/icon.png",
        "index_id": "langgenius___feishu_calendar",
        "install_count": 425,
        "introduction": "",
        "label": {
          "en_US": "Feishu Calendar",
          "zh_Hans": "飞书日历"
        },
        "latest_package_identifier": "langgenius/feishu_calendar:0.0.1@6765351b342f4786065e82c26e2964411846c5944bf2081740034d11881d0fca",
        "latest_version": "0.0.1",
        "model": {},
        "name": "feishu_calendar",
        "org": "langgenius",
        "plugin_id": "langgenius/feishu_calendar",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/feishu_calendar.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "social"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "APP ID"
              },
              "name": "app_id",
              "options": null,
              "placeholder": {
                "en_US": "Please input your feishu app id",
                "zh_Hans": "请输入你的飞书 app id"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": "https://open.larkoffice.com/app"
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "APP Secret"
              },
              "name": "app_secret",
              "options": null,
              "placeholder": {
                "en_US": "Please input your app secret",
                "zh_Hans": "请输入你的飞书 app secret"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            }
          ],
          "identity": {
            "author": "Doug Lea",
            "description": {
              "en_US": "Feishu calendar, requires the following permissions: calendar:calendar:read、calendar:calendar、contact:user.id:readonly.\n",
              "zh_Hans": "飞书日历，需要开通以下权限: calendar:calendar:read、calendar:calendar、contact:user.id:readonly。\n"
            },
            "icon": "icon.png",
            "label": {
              "en_US": "Feishu Calendar",
              "zh_Hans": "飞书日历"
            },
            "name": "feishu_calendar",
            "tags": [
              "social",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Add Event Attendees",
                  "zh_Hans": "添加日程参会人"
                },
                "llm": "A tool for adding attendees to events in Feishu. (在飞书中添加日程参会人)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Add Event Attendees",
                  "zh_Hans": "添加日程参会人"
                },
                "name": "add_event_attendees"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the event, which will be returned when the event is created. For example: fb2a6406-26d6-4c8d-a487-6f0246c94d2f_0.\n",
                    "zh_Hans": "创建日程时会返回日程 ID。例如: fb2a6406-26d6-4c8d-a487-6f0246c94d2f_0。\n"
                  },
                  "label": {
                    "en_US": "Event ID",
                    "zh_Hans": "日程 ID"
                  },
                  "llm_description": "日程 ID，创建日程时会返回日程 ID。例如: fb2a6406-26d6-4c8d-a487-6f0246c94d2f_0。\n",
                  "max": null,
                  "min": null,
                  "name": "event_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to send a Bot notification to attendees. true: send, false: do not send.\n",
                    "zh_Hans": "是否给参与人发送 Bot 通知，true: 发送，false: 不发送。\n"
                  },
                  "label": {
                    "en_US": "Need Notification",
                    "zh_Hans": "是否需要通知"
                  },
                  "llm_description": "是否给参与人发送 Bot 通知，true: 发送，false: 不发送。\n",
                  "max": null,
                  "min": null,
                  "name": "need_notification",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The list of attendee emails or phone numbers, separated by commas.",
                    "zh_Hans": "日程参会人邮箱或者手机号列表，使用逗号分隔。"
                  },
                  "label": {
                    "en_US": "Attendee Phone or Email",
                    "zh_Hans": "参会人电话或邮箱"
                  },
                  "llm_description": "日程参会人邮箱或者手机号列表，使用逗号分隔。",
                  "max": null,
                  "min": null,
                  "name": "attendee_phone_or_email",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Search Events",
                  "zh_Hans": "搜索日程"
                },
                "llm": "A tool for searching events in Feishu.(在飞书中搜索日程)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Search Events",
                  "zh_Hans": "搜索日程"
                },
                "name": "search_events"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": "open_id",
                  "form": "form",
                  "human_description": {
                    "en_US": "User ID type, optional values are open_id, union_id, user_id, with a default value of open_id.",
                    "zh_Hans": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。"
                  },
                  "label": {
                    "en_US": "user_id_type",
                    "zh_Hans": "用户 ID 类型"
                  },
                  "llm_description": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。",
                  "max": null,
                  "min": null,
                  "name": "user_id_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "open_id",
                        "zh_Hans": "open_id"
                      },
                      "value": "open_id"
                    },
                    {
                      "label": {
                        "en_US": "union_id",
                        "zh_Hans": "union_id"
                      },
                      "value": "union_id"
                    },
                    {
                      "label": {
                        "en_US": "user_id",
                        "zh_Hans": "user_id"
                      },
                      "value": "user_id"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The search keyword used for fuzzy searching event names, with a maximum input of 200 characters.",
                    "zh_Hans": "用于模糊查询日程名称的搜索关键字，最大输入 200 字符。"
                  },
                  "label": {
                    "en_US": "Query",
                    "zh_Hans": "搜索关键字"
                  },
                  "llm_description": "用于模糊查询日程名称的搜索关键字，最大输入 200 字符。",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The start time, defaults to 0:00 of the current day if not provided, format: 2006-01-02 15:04:05.\n",
                    "zh_Hans": "开始时间，不传值时默认当天 0 点时间，格式为:2006-01-02 15:04:05。"
                  },
                  "label": {
                    "en_US": "Start Time",
                    "zh_Hans": "开始时间"
                  },
                  "llm_description": "开始时间，不传值时默认当天 0 点时间，格式为:2006-01-02 15:04:05。",
                  "max": null,
                  "min": null,
                  "name": "start_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The end time, defaults to 23:59 of the current day if not provided, format: 2006-01-02 15:04:05.\n",
                    "zh_Hans": "结束时间，不传值时默认当天 23:59 分时间，格式为:2006-01-02 15:04:05。"
                  },
                  "label": {
                    "en_US": "End Time",
                    "zh_Hans": "结束时间"
                  },
                  "llm_description": "结束时间，不传值时默认当天 23:59 分时间，格式为:2006-01-02 15:04:05。",
                  "max": null,
                  "min": null,
                  "name": "end_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 20,
                  "form": "form",
                  "human_description": {
                    "en_US": "The page size, i.e., the number of data entries returned in a single request. The default value is 20, and the value range is [10,100].",
                    "zh_Hans": "分页大小，即单次请求所返回的数据条目数。默认值为 20，取值范围为 [10,100]。"
                  },
                  "label": {
                    "en_US": "Page Size",
                    "zh_Hans": "分页大小"
                  },
                  "llm_description": "分页大小，即单次请求所返回的数据条目数。默认值为 20，取值范围为 [10,100]。",
                  "max": null,
                  "min": null,
                  "name": "page_size",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The pagination token. Leave it blank for the first request, indicating to start traversing from the beginning; when the pagination query result has more items, a new page_token will be returned simultaneously, which can be used to obtain the query result in the next traversal.",
                    "zh_Hans": "分页标记，第一次请求不填，表示从头开始遍历；分页查询结果还有更多项时会同时返回新的 page_token，下次遍历可采用该 page_token 获取查询结果。"
                  },
                  "label": {
                    "en_US": "Page Token",
                    "zh_Hans": "分页标记"
                  },
                  "llm_description": "分页标记，第一次请求不填，表示从头开始遍历；分页查询结果还有更多项时会同时返回新的 page_token，下次遍历可采用该 page_token 获取查询结果。",
                  "max": null,
                  "min": null,
                  "name": "page_token",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get Primary Calendar",
                  "zh_Hans": "查询主日历信息"
                },
                "llm": "A tool for querying primary calendar information in Feishu.(在飞书中查询主日历信息)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Get Primary Calendar",
                  "zh_Hans": "查询主日历信息"
                },
                "name": "get_primary_calendar"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": "open_id",
                  "form": "form",
                  "human_description": {
                    "en_US": "User ID type, optional values are open_id, union_id, user_id, with a default value of open_id.",
                    "zh_Hans": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。"
                  },
                  "label": {
                    "en_US": "user_id_type",
                    "zh_Hans": "用户 ID 类型"
                  },
                  "llm_description": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。",
                  "max": null,
                  "min": null,
                  "name": "user_id_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "open_id",
                        "zh_Hans": "open_id"
                      },
                      "value": "open_id"
                    },
                    {
                      "label": {
                        "en_US": "union_id",
                        "zh_Hans": "union_id"
                      },
                      "value": "union_id"
                    },
                    {
                      "label": {
                        "en_US": "user_id",
                        "zh_Hans": "user_id"
                      },
                      "value": "user_id"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Create Event",
                  "zh_Hans": "创建日程"
                },
                "llm": "A tool for creating events in Feishu.(创建飞书日程)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Create Event",
                  "zh_Hans": "创建日程"
                },
                "name": "create_event"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The title of the event. If not filled, the event title will display (No Subject).",
                    "zh_Hans": "日程标题，若不填则日程标题显示 (无主题)。"
                  },
                  "label": {
                    "en_US": "Summary",
                    "zh_Hans": "日程标题"
                  },
                  "llm_description": "日程标题，若不填则日程标题显示 (无主题)。",
                  "max": null,
                  "min": null,
                  "name": "summary",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The description of the event.",
                    "zh_Hans": "日程描述。"
                  },
                  "label": {
                    "en_US": "Description",
                    "zh_Hans": "日程描述"
                  },
                  "llm_description": "日程描述。",
                  "max": null,
                  "min": null,
                  "name": "description",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to send a bot message when the event is created, true: send, false: do not send.\n",
                    "zh_Hans": "创建日程时是否发送 bot 消息，true：发送，false：不发送。"
                  },
                  "label": {
                    "en_US": "Need Notification",
                    "zh_Hans": "是否发送通知"
                  },
                  "llm_description": "创建日程时是否发送 bot 消息，true：发送，false：不发送。",
                  "max": null,
                  "min": null,
                  "name": "need_notification",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The start time of the event, format: 2006-01-02 15:04:05.\n",
                    "zh_Hans": "日程开始时间，格式：2006-01-02 15:04:05。"
                  },
                  "label": {
                    "en_US": "Start Time",
                    "zh_Hans": "开始时间"
                  },
                  "llm_description": "日程开始时间，格式：2006-01-02 15:04:05。",
                  "max": null,
                  "min": null,
                  "name": "start_time",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The end time of the event, format: 2006-01-02 15:04:05.\n",
                    "zh_Hans": "日程结束时间，格式：2006-01-02 15:04:05。"
                  },
                  "label": {
                    "en_US": "End Time",
                    "zh_Hans": "结束时间"
                  },
                  "llm_description": "日程结束时间，格式：2006-01-02 15:04:05。",
                  "max": null,
                  "min": null,
                  "name": "end_time",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "none",
                  "form": "form",
                  "human_description": {
                    "en_US": "Attendee ability, optional values are none, can_see_others, can_invite_others, can_modify_event, with a default value of none.",
                    "zh_Hans": "参会人权限，可选值有无、可以查看参与人列表、可以邀请其它参与人、可以编辑日程，默认值为无。"
                  },
                  "label": {
                    "en_US": "attendee_ability",
                    "zh_Hans": "参会人权限"
                  },
                  "llm_description": "参会人权限，可选值有无、可以查看参与人列表、可以邀请其它参与人、可以编辑日程，默认值为无。",
                  "max": null,
                  "min": null,
                  "name": "attendee_ability",
                  "options": [
                    {
                      "label": {
                        "en_US": "none",
                        "zh_Hans": "无"
                      },
                      "value": "none"
                    },
                    {
                      "label": {
                        "en_US": "can_see_others",
                        "zh_Hans": "可以查看参与人列表"
                      },
                      "value": "can_see_others"
                    },
                    {
                      "label": {
                        "en_US": "can_invite_others",
                        "zh_Hans": "可以邀请其它参与人"
                      },
                      "value": "can_invite_others"
                    },
                    {
                      "label": {
                        "en_US": "can_modify_event",
                        "zh_Hans": "可以编辑日程"
                      },
                      "value": "can_modify_event"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to enable automatic recording, true: enabled, automatically record when the meeting starts; false: not enabled.\n",
                    "zh_Hans": "是否开启自动录制，true：开启，会议开始后自动录制；false：不开启。"
                  },
                  "label": {
                    "en_US": "Auto Record",
                    "zh_Hans": "自动录制"
                  },
                  "llm_description": "是否开启自动录制，true：开启，会议开始后自动录制；false：不开启。",
                  "max": null,
                  "min": null,
                  "name": "auto_record",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Delete Event",
                  "zh_Hans": "删除日程"
                },
                "llm": "A tool for deleting events in Feishu.(在飞书中删除日程)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Delete Event",
                  "zh_Hans": "删除日程"
                },
                "name": "delete_event"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the event, for example: e8b9791c-39ae-4908-8ad8-66b13159b9fb_0.\n",
                    "zh_Hans": "日程 ID，例如：e8b9791c-39ae-4908-8ad8-66b13159b9fb_0。"
                  },
                  "label": {
                    "en_US": "Event ID",
                    "zh_Hans": "日程 ID"
                  },
                  "llm_description": "日程 ID，例如：e8b9791c-39ae-4908-8ad8-66b13159b9fb_0。",
                  "max": null,
                  "min": null,
                  "name": "event_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "Indicates whether to send bot notifications to event participants upon deletion. true: send, false: do not send.\n",
                    "zh_Hans": "删除日程是否给日程参与人发送 bot 通知，true：发送，false：不发送。"
                  },
                  "label": {
                    "en_US": "Need Notification",
                    "zh_Hans": "是否需要通知"
                  },
                  "llm_description": "删除日程是否给日程参与人发送 bot 通知，true：发送，false：不发送。",
                  "max": null,
                  "min": null,
                  "name": "need_notification",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "List Events",
                  "zh_Hans": "获取日程列表"
                },
                "llm": "A tool for listing events in Feishu.(在飞书中获取日程列表)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "List Events",
                  "zh_Hans": "获取日程列表"
                },
                "name": "list_events"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The start time, defaults to 0:00 of the current day if not provided, format: 2006-01-02 15:04:05.\n",
                    "zh_Hans": "开始时间，不传值时默认当天 0 点时间，格式为:2006-01-02 15:04:05。"
                  },
                  "label": {
                    "en_US": "Start Time",
                    "zh_Hans": "开始时间"
                  },
                  "llm_description": "开始时间，不传值时默认当天 0 点时间，格式为:2006-01-02 15:04:05。",
                  "max": null,
                  "min": null,
                  "name": "start_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The end time, defaults to 23:59 of the current day if not provided, format: 2006-01-02 15:04:05.\n",
                    "zh_Hans": "结束时间，不传值时默认当天 23:59 分时间，格式为:2006-01-02 15:04:05。"
                  },
                  "label": {
                    "en_US": "End Time",
                    "zh_Hans": "结束时间"
                  },
                  "llm_description": "结束时间，不传值时默认当天 23:59 分时间，格式为:2006-01-02 15:04:05。",
                  "max": null,
                  "min": null,
                  "name": "end_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 50,
                  "form": "form",
                  "human_description": {
                    "en_US": "The page size, i.e., the number of data entries returned in a single request. The default value is 50, and the value range is [50,1000].",
                    "zh_Hans": "分页大小，即单次请求所返回的数据条目数。默认值为 50，取值范围为 [50,1000]。"
                  },
                  "label": {
                    "en_US": "Page Size",
                    "zh_Hans": "分页大小"
                  },
                  "llm_description": "分页大小，即单次请求所返回的数据条目数。默认值为 50，取值范围为 [50,1000]。",
                  "max": null,
                  "min": null,
                  "name": "page_size",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The pagination token. Leave it blank for the first request, indicating to start traversing from the beginning; when the pagination query result has more items, a new page_token will be returned simultaneously, which can be used to obtain the query result in the next traversal.",
                    "zh_Hans": "分页标记，第一次请求不填，表示从头开始遍历；分页查询结果还有更多项时会同时返回新的 page_token，下次遍历可采用该 page_token 获取查询结果。"
                  },
                  "label": {
                    "en_US": "Page Token",
                    "zh_Hans": "分页标记"
                  },
                  "llm_description": "分页标记，第一次请求不填，表示从头开始遍历；分页查询结果还有更多项时会同时返回新的 page_token，下次遍历可采用该 page_token 获取查询结果。",
                  "max": null,
                  "min": null,
                  "name": "page_token",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Update Event",
                  "zh_Hans": "更新日程"
                },
                "llm": "A tool for updating events in Feishu.(更新飞书中的日程)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Update Event",
                  "zh_Hans": "更新日程"
                },
                "name": "update_event"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the event, for example: e8b9791c-39ae-4908-8ad8-66b13159b9fb_0.\n",
                    "zh_Hans": "日程 ID，例如：e8b9791c-39ae-4908-8ad8-66b13159b9fb_0。"
                  },
                  "label": {
                    "en_US": "Event ID",
                    "zh_Hans": "日程 ID"
                  },
                  "llm_description": "日程 ID，例如：e8b9791c-39ae-4908-8ad8-66b13159b9fb_0。",
                  "max": null,
                  "min": null,
                  "name": "event_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The title of the event.",
                    "zh_Hans": "日程标题。"
                  },
                  "label": {
                    "en_US": "Summary",
                    "zh_Hans": "日程标题"
                  },
                  "llm_description": "日程标题。",
                  "max": null,
                  "min": null,
                  "name": "summary",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The description of the event.",
                    "zh_Hans": "日程描述。"
                  },
                  "label": {
                    "en_US": "Description",
                    "zh_Hans": "日程描述"
                  },
                  "llm_description": "日程描述。",
                  "max": null,
                  "min": null,
                  "name": "description",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to send a bot message when the event is updated, true: send, false: do not send.\n",
                    "zh_Hans": "更新日程时是否发送 bot 消息，true：发送，false：不发送。"
                  },
                  "label": {
                    "en_US": "Need Notification",
                    "zh_Hans": "是否发送通知"
                  },
                  "llm_description": "更新日程时是否发送 bot 消息，true：发送，false：不发送。",
                  "max": null,
                  "min": null,
                  "name": "need_notification",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The start time of the event, format: 2006-01-02 15:04:05.\n",
                    "zh_Hans": "日程开始时间，格式：2006-01-02 15:04:05。"
                  },
                  "label": {
                    "en_US": "Start Time",
                    "zh_Hans": "开始时间"
                  },
                  "llm_description": "日程开始时间，格式：2006-01-02 15:04:05。",
                  "max": null,
                  "min": null,
                  "name": "start_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The end time of the event, format: 2006-01-02 15:04:05.\n",
                    "zh_Hans": "日程结束时间，格式：2006-01-02 15:04:05。"
                  },
                  "label": {
                    "en_US": "End Time",
                    "zh_Hans": "结束时间"
                  },
                  "llm_description": "日程结束时间，格式：2006-01-02 15:04:05。",
                  "max": null,
                  "min": null,
                  "name": "end_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to enable automatic recording, true: enabled, automatically record when the meeting starts; false: not enabled.\n",
                    "zh_Hans": "是否开启自动录制，true：开启，会议开始后自动录制；false：不开启。"
                  },
                  "label": {
                    "en_US": "Auto Record",
                    "zh_Hans": "自动录制"
                  },
                  "llm_description": "是否开启自动录制，true：开启，会议开始后自动录制；false：不开启。",
                  "max": null,
                  "min": null,
                  "name": "auto_record",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-26T10:41:02Z",
        "version_updated_at": "2025-02-26T10:41:02Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Why not play Bad Apple with Dify?",
          "ja_JP": "Bad AppleをDifyで聴く",
          "pt_BR": "Por que não ouvir Bad Apple no Dify?",
          "zh_Hans": "为什么不在Dify上听Bad Apple？"
        },
        "category": "extension",
        "created_at": "2024-11-22T08:06:47Z",
        "endpoint": {
          "endpoints": [
            {
              "hidden": false,
              "method": "GET",
              "path": "/"
            },
            {
              "hidden": false,
              "method": "GET",
              "path": "/pathdata.json"
            }
          ],
          "settings": []
        },
        "icon": "langgenius/packages/badapple/_assets/icon.jpeg",
        "index_id": "langgenius___badapple",
        "install_count": 424,
        "introduction": "## Bad Apple\n\nWhy not just watch it?\n\n### Usage\n\n1. Install it\n2. Setup a endpoint\n3. Copy the first url you saw in the panel, and paste it in your browser.\n4. Enjoy!\n\n### Copyright\n\nFor original author, see [here](https://github.com/buzzbyte/BadApple.SVG), thanks for the great work!",
        "label": {
          "en_US": "Bad Apple",
          "ja_JP": "Bad Apple",
          "pt_BR": "Bad Apple",
          "zh_Hans": "Bad Apple"
        },
        "latest_package_identifier": "langgenius/badapple:0.0.1@21e771e293cc6120e9d3ef04ea8aad590171612cc8e816dbda187f93bff850db",
        "latest_version": "0.0.1",
        "model": {},
        "name": "badapple",
        "org": "langgenius",
        "plugin_id": "langgenius/badapple",
        "plugins": {
          "agent_strategies": null,
          "endpoints": [
            "group/badapple.yaml"
          ],
          "models": null,
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "endpoint": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-02-17T07:19:17Z",
        "version_updated_at": "2025-02-17T07:19:17Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Fireworks AI",
          "zh_Hans": "Fireworks AI"
        },
        "category": "model",
        "created_at": "2025-01-02T08:01:26Z",
        "endpoint": {},
        "icon": "langgenius/packages/fireworks/_assets/icon_s_en.svg",
        "index_id": "langgenius___fireworks",
        "install_count": 399,
        "introduction": "",
        "label": {
          "en_US": "Fireworks AI",
          "zh_Hans": "Fireworks AI"
        },
        "latest_package_identifier": "langgenius/fireworks:0.0.3@7c127ff75b8eddfe6d96f61144817960e937b4af68216d5c6b03ffe7f23af59d",
        "latest_version": "0.0.3",
        "model": {
          "background": "#FCFDFF",
          "configurate_methods": [
            "predefined-model",
            "customizable-model"
          ],
          "description": {
            "en_US": "Fireworks AI",
            "zh_Hans": "Fireworks AI"
          },
          "help": {
            "title": {
              "en_US": "Get your API Key from Fireworks AI",
              "zh_Hans": "从 Fireworks AI 获取 API Key"
            },
            "url": {
              "en_US": "https://fireworks.ai/account/api-keys"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.svg"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "Fireworks AI",
            "zh_Hans": "Fireworks AI"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "The zh_Hans of Model",
                  "zh_Hans": "模型中文名称"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your zh_Hans of Model",
                  "zh_Hans": "在此输入您的模型中文名称"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "model_label_zh_Hanns"
              },
              {
                "default": null,
                "label": {
                  "en_US": "The en_US of Model",
                  "zh_Hans": "模型英文名称"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your en_US of Model",
                  "zh_Hans": "在此输入您的模型英文名称"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "model_label_en_US"
              },
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "fireworks_api_key"
              },
              {
                "default": "4096",
                "label": {
                  "en_US": "Model context size",
                  "zh_Hans": "模型上下文长度"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Model context size",
                  "zh_Hans": "在此输入您的模型上下文长度"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "context_size"
              },
              {
                "default": "4096",
                "label": {
                  "en_US": "Upper bound for max tokens",
                  "zh_Hans": "最大 token 上限"
                },
                "max_length": 0,
                "options": [],
                "placeholder": null,
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "text-input",
                "variable": "max_tokens"
              },
              {
                "default": "no_call",
                "label": {
                  "en_US": "Function calling"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Not Support",
                      "zh_Hans": "不支持"
                    },
                    "show_on": [],
                    "value": "no_call"
                  },
                  {
                    "label": {
                      "en_US": "Support",
                      "zh_Hans": "支持"
                    },
                    "show_on": [],
                    "value": "function_call"
                  }
                ],
                "placeholder": null,
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "select",
                "variable": "function_calling_type"
              }
            ],
            "model": {
              "label": {
                "en_US": "Model URL",
                "zh_Hans": "模型URL"
              },
              "placeholder": {
                "en_US": "Enter your Model URL",
                "zh_Hans": "输入模型URL"
              }
            }
          },
          "models": [
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Firefunction V1",
                "zh_Hans": "Firefunction V1"
              },
              "model": "accounts/fireworks/models/firefunction-v1",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 64,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": "None",
                  "help": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "label": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "max": null,
                  "min": null,
                  "name": "context_length_exceeded_behavior",
                  "options": [
                    "None",
                    "truncate",
                    "error"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.5",
                "output": "0.5",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Firefunction V2",
                "zh_Hans": "Firefunction V2"
              },
              "model": "accounts/fireworks/models/firefunction-v2",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 64,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": "None",
                  "help": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "label": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "max": null,
                  "min": null,
                  "name": "context_length_exceeded_behavior",
                  "options": [
                    "None",
                    "truncate",
                    "error"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.9",
                "output": "0.9",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemma2 9B Instruct",
                "zh_Hans": "Gemma2 9B Instruct"
              },
              "model": "accounts/fireworks/models/gemma2-9b-it",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 64,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": "None",
                  "help": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "label": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "max": null,
                  "min": null,
                  "name": "context_length_exceeded_behavior",
                  "options": [
                    "None",
                    "truncate",
                    "error"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.2",
                "output": "0.2",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama3 70B Instruct(HF version)",
                "zh_Hans": "Llama3 70B Instruct(HF version)"
              },
              "model": "accounts/fireworks/models/llama-v3-70b-instruct-hf",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 64,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": "None",
                  "help": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "label": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "max": null,
                  "min": null,
                  "name": "context_length_exceeded_behavior",
                  "options": [
                    "None",
                    "truncate",
                    "error"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.9",
                "output": "0.9",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama3 70B Instruct",
                "zh_Hans": "Llama3 70B Instruct"
              },
              "model": "accounts/fireworks/models/llama-v3-70b-instruct",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 64,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": "None",
                  "help": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "label": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "max": null,
                  "min": null,
                  "name": "context_length_exceeded_behavior",
                  "options": [
                    "None",
                    "truncate",
                    "error"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.9",
                "output": "0.9",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama3 8B Instruct(HF version)",
                "zh_Hans": "Llama3 8B Instruct(HF version)"
              },
              "model": "accounts/fireworks/models/llama-v3-8b-instruct-hf",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 64,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": "None",
                  "help": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "label": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "max": null,
                  "min": null,
                  "name": "context_length_exceeded_behavior",
                  "options": [
                    "None",
                    "truncate",
                    "error"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.2",
                "output": "0.2",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama3 8B Instruct",
                "zh_Hans": "Llama3 8B Instruct"
              },
              "model": "accounts/fireworks/models/llama-v3-8b-instruct",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 64,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": "None",
                  "help": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "label": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "max": null,
                  "min": null,
                  "name": "context_length_exceeded_behavior",
                  "options": [
                    "None",
                    "truncate",
                    "error"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.2",
                "output": "0.2",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama3.1 405B Instruct",
                "zh_Hans": "Llama3.1 405B Instruct"
              },
              "model": "accounts/fireworks/models/llama-v3p1-405b-instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 64,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": "None",
                  "help": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "label": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "max": null,
                  "min": null,
                  "name": "context_length_exceeded_behavior",
                  "options": [
                    "None",
                    "truncate",
                    "error"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "3",
                "output": "3",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama3.1 70B Instruct",
                "zh_Hans": "Llama3.1 70B Instruct"
              },
              "model": "accounts/fireworks/models/llama-v3p1-70b-instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 64,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": "None",
                  "help": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "label": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "max": null,
                  "min": null,
                  "name": "context_length_exceeded_behavior",
                  "options": [
                    "None",
                    "truncate",
                    "error"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.2",
                "output": "0.2",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama3.1 8B Instruct",
                "zh_Hans": "Llama3.1 8B Instruct"
              },
              "model": "accounts/fireworks/models/llama-v3p1-8b-instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 64,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": "None",
                  "help": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "label": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "max": null,
                  "min": null,
                  "name": "context_length_exceeded_behavior",
                  "options": [
                    "None",
                    "truncate",
                    "error"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.2",
                "output": "0.2",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama 3.2 11B Vision Instruct",
                "zh_Hans": "Llama 3.2 11B Vision Instruct"
              },
              "model": "accounts/fireworks/models/llama-v3p2-11b-vision-instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 64,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": "None",
                  "help": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "label": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "max": null,
                  "min": null,
                  "name": "context_length_exceeded_behavior",
                  "options": [
                    "None",
                    "truncate",
                    "error"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.2",
                "output": "0.2",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama 3.2 1B Instruct",
                "zh_Hans": "Llama 3.2 1B Instruct"
              },
              "model": "accounts/fireworks/models/llama-v3p2-1b-instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 64,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": "None",
                  "help": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "label": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "max": null,
                  "min": null,
                  "name": "context_length_exceeded_behavior",
                  "options": [
                    "None",
                    "truncate",
                    "error"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.1",
                "output": "0.1",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama 3.2 3B Instruct",
                "zh_Hans": "Llama 3.2 3B Instruct"
              },
              "model": "accounts/fireworks/models/llama-v3p2-3b-instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 64,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": "None",
                  "help": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "label": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "max": null,
                  "min": null,
                  "name": "context_length_exceeded_behavior",
                  "options": [
                    "None",
                    "truncate",
                    "error"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.1",
                "output": "0.1",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama 3.2 90B Vision Instruct",
                "zh_Hans": "Llama 3.2 90B Vision Instruct"
              },
              "model": "accounts/fireworks/models/llama-v3p2-90b-vision-instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 64,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": "None",
                  "help": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "label": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "max": null,
                  "min": null,
                  "name": "context_length_exceeded_behavior",
                  "options": [
                    "None",
                    "truncate",
                    "error"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.9",
                "output": "0.9",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Mixtral MoE 8x22B Instruct",
                "zh_Hans": "Mixtral MoE 8x22B Instruct"
              },
              "model": "accounts/fireworks/models/mixtral-8x22b-instruct",
              "model_properties": {
                "context_size": 65536,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 64,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": "None",
                  "help": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "label": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "max": null,
                  "min": null,
                  "name": "context_length_exceeded_behavior",
                  "options": [
                    "None",
                    "truncate",
                    "error"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "1.2",
                "output": "1.2",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Mixtral MoE 8x7B Instruct(HF version)",
                "zh_Hans": "Mixtral MoE 8x7B Instruct(HF version)"
              },
              "model": "accounts/fireworks/models/mixtral-8x7b-instruct-hf",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 64,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": "None",
                  "help": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "label": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "max": null,
                  "min": null,
                  "name": "context_length_exceeded_behavior",
                  "options": [
                    "None",
                    "truncate",
                    "error"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.5",
                "output": "0.5",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Mixtral MoE 8x7B Instruct",
                "zh_Hans": "Mixtral MoE 8x7B Instruct"
              },
              "model": "accounts/fireworks/models/mixtral-8x7b-instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 64,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": "None",
                  "help": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "label": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "max": null,
                  "min": null,
                  "name": "context_length_exceeded_behavior",
                  "options": [
                    "None",
                    "truncate",
                    "error"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.5",
                "output": "0.5",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "MythoMax L2 13b",
                "zh_Hans": "MythoMax L2 13b"
              },
              "model": "accounts/fireworks/models/mythomax-l2-13b",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 64,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": "None",
                  "help": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "label": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "max": null,
                  "min": null,
                  "name": "context_length_exceeded_behavior",
                  "options": [
                    "None",
                    "truncate",
                    "error"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.2",
                "output": "0.2",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "vision"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Phi3.5 Vision Instruct",
                "zh_Hans": "Phi3.5 Vision Instruct"
              },
              "model": "accounts/fireworks/models/phi-3-vision-128k-instruct",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 64,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": "None",
                  "help": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "label": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "max": null,
                  "min": null,
                  "name": "context_length_exceeded_behavior",
                  "options": [
                    "None",
                    "truncate",
                    "error"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.2",
                "output": "0.2",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought",
                "tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen2.5 72B Instruct",
                "zh_Hans": "Qwen2.5 72B Instruct"
              },
              "model": "accounts/fireworks/models/qwen2p5-72b-instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 64,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": "None",
                  "help": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "label": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "max": null,
                  "min": null,
                  "name": "context_length_exceeded_behavior",
                  "options": [
                    "None",
                    "truncate",
                    "error"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.9",
                "output": "0.9",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Yi-Large",
                "zh_Hans": "Yi-Large"
              },
              "model": "accounts/yi-01-ai/models/yi-large",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": null,
                  "min": null,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 64,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": "None",
                  "help": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "label": {
                    "en_US": "Context Length Exceeded Behavior",
                    "zh_Hans": "上下文长度超出行为"
                  },
                  "max": null,
                  "min": null,
                  "name": "context_length_exceeded_behavior",
                  "options": [
                    "None",
                    "truncate",
                    "error"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": null
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "Set a response format, ensure the output from llm is a valid code block as possible, such as JSON, XML, etc.",
                    "ja_JP": "応答形式を設定します。llmの出力が可能な限り有効なコードブロックであることを確認します。",
                    "pt_BR": "Defina um formato de resposta para garantir que a saída do llm seja um bloco de código válido o mais possível, como JSON, XML, etc.",
                    "zh_Hans": "设置一个返回格式，确保llm的输出尽可能是有效的代码块，如JSON、XML等"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "応答形式",
                    "pt_BR": "Formato de resposta",
                    "zh_Hans": "回复格式"
                  },
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    "JSON",
                    "XML"
                  ],
                  "precision": null,
                  "required": false,
                  "type": "string",
                  "use_template": "response_format"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "3",
                "output": "3",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "UAE-Large-V1",
                "zh_Hans": "UAE-Large-V1"
              },
              "model": "WhereIsAI/UAE-Large-V1",
              "model_properties": {
                "context_size": 512,
                "max_chunks": 1
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.008",
                "output": null,
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "GTE-base",
                "zh_Hans": "GTE-base"
              },
              "model": "thenlper/gte-base",
              "model_properties": {
                "context_size": 512,
                "max_chunks": 1
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.008",
                "output": null,
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "GTE-large",
                "zh_Hans": "GTE-large"
              },
              "model": "thenlper/gte-large",
              "model_properties": {
                "context_size": 512,
                "max_chunks": 1
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.008",
                "output": null,
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "nomic-embed-text-v1.5",
                "zh_Hans": "nomic-embed-text-v1.5"
              },
              "model": "nomic-ai/nomic-embed-text-v1.5",
              "model_properties": {
                "context_size": 8192,
                "max_chunks": 16
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.008",
                "output": null,
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "nomic-embed-text-v1",
                "zh_Hans": "nomic-embed-text-v1"
              },
              "model": "nomic-ai/nomic-embed-text-v1",
              "model_properties": {
                "context_size": 8192,
                "max_chunks": 16
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.008",
                "output": null,
                "unit": "0.000001"
              }
            }
          ],
          "position": {},
          "provider": "fireworks",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "fireworks_api_key"
              }
            ]
          },
          "supported_model_types": [
            "llm",
            "text-embedding"
          ]
        },
        "name": "fireworks",
        "org": "langgenius",
        "plugin_id": "langgenius/fireworks",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/fireworks.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-02-28T04:05:29Z",
        "version_updated_at": "2025-02-28T04:05:29Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Quickly experience large models and explore the leading AI open source world",
          "zh_Hans": "快速体验大模型，领先探索 AI 开源世界"
        },
        "category": "tool",
        "created_at": "2025-02-27T05:43:15Z",
        "endpoint": {},
        "icon": "langgenius/packages/gitee_ai_tool/_assets/icon.svg",
        "index_id": "langgenius___gitee_ai_tool",
        "install_count": 395,
        "introduction": "",
        "label": {
          "en_US": "Gitee AI Tool",
          "zh_Hans": "Gitee AI Tool"
        },
        "latest_package_identifier": "langgenius/gitee_ai_tool:0.0.2@6b30f8bd751dc9e42913e51e051ba16dbb5fe6bd5c67a2e95bcf7d148a100686",
        "latest_version": "0.0.2",
        "model": {},
        "name": "gitee_ai_tool",
        "org": "langgenius",
        "plugin_id": "langgenius/gitee_ai_tool",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/gitee_ai_tool.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "image"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "API Key"
              },
              "name": "api_key",
              "options": null,
              "placeholder": {
                "en_US": "Enter your API Key",
                "zh_Hans": "在此输入您的 API Key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://ai.gitee.com/dashboard/settings/tokens"
            }
          ],
          "identity": {
            "author": "Gitee AI",
            "description": {
              "en_US": "Quickly experience large models and explore the leading AI open source world",
              "zh_Hans": "快速体验大模型，领先探索 AI 开源世界"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Gitee AI",
              "zh_Hans": "Gitee AI"
            },
            "name": "gitee_ai",
            "tags": [
              "image"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Generate word embeddings using Serverless-supported models (compatible with OpenAI)"
                },
                "llm": "This tool is used to generate word embeddings from text input."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "gitee_ai",
                "label": {
                  "en_US": "embedding"
                },
                "name": "embedding"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": "bge-m3",
                  "form": "form",
                  "human_description": {
                    "en_US": "Supported Embedding (compatible with OpenAI) interface models"
                  },
                  "label": {
                    "en_US": "Service Model",
                    "zh_Hans": "服务模型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The text input used to generate embeddings.",
                    "zh_Hans": "用于生成词向量的输入文本。"
                  },
                  "label": {
                    "en_US": "Input Text",
                    "zh_Hans": "输入文本"
                  },
                  "llm_description": "This text input will be used to generate embeddings.",
                  "max": null,
                  "min": null,
                  "name": "inputs",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "generate images using a variety of popular models"
                },
                "llm": "This tool is used to generate image from text."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "gitee_ai",
                "label": {
                  "en_US": "text to image"
                },
                "name": "text-to-image"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": "Kolors",
                  "form": "form",
                  "human_description": {
                    "en_US": "The model input used to generate the image.",
                    "zh_Hans": "用于生成图片的模型。"
                  },
                  "label": {
                    "en_US": "Choose Image Model",
                    "zh_Hans": "选择生成图片的模型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": [
                    {
                      "label": {
                        "en_US": "flux-1-schnell"
                      },
                      "value": "flux-1-schnell"
                    },
                    {
                      "label": {
                        "en_US": "Kolors"
                      },
                      "value": "Kolors"
                    },
                    {
                      "label": {
                        "en_US": "stable-diffusion-3-medium"
                      },
                      "value": "stable-diffusion-3-medium"
                    },
                    {
                      "label": {
                        "en_US": "stable-diffusion-xl-base-1.0"
                      },
                      "value": "stable-diffusion-xl-base-1.0"
                    },
                    {
                      "label": {
                        "en_US": "stable-diffusion-v1-4"
                      },
                      "value": "stable-diffusion-v1-4"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The text input used to generate the image.",
                    "zh_Hans": "用于生成图片的输入文本。"
                  },
                  "label": {
                    "en_US": "Input Text",
                    "zh_Hans": "输入文本"
                  },
                  "llm_description": "This text input will be used to generate image.",
                  "max": null,
                  "min": null,
                  "name": "inputs",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 720,
                  "form": "form",
                  "human_description": {
                    "en_US": "The width of the generated image.",
                    "zh_Hans": "生成图片的宽度。"
                  },
                  "label": {
                    "en_US": "Image Width",
                    "zh_Hans": "图片宽度"
                  },
                  "llm_description": "",
                  "max": 1024,
                  "min": 1,
                  "name": "width",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 720,
                  "form": "form",
                  "human_description": {
                    "en_US": "The height of the generated image.",
                    "zh_Hans": "生成图片的高度。"
                  },
                  "label": {
                    "en_US": "Image Height",
                    "zh_Hans": "图片高度"
                  },
                  "llm_description": "",
                  "max": 1024,
                  "min": 1,
                  "name": "height",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-28T10:32:12Z",
        "version_updated_at": "2025-02-28T10:32:12Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Introducing the Dify plugin version of Browser Use - a powerful tool that enables AI agents to control and interact with web browsers, providing seamless automation for web-based tasks.",
          "ja_JP": "Introducing the Dify plugin version of Browser Use - a powerful tool that enables AI agents to control and interact with web browsers, providing seamless automation for web-based tasks.",
          "pt_BR": "Introducing the Dify plugin version of Browser Use - a powerful tool that enables AI agents to control and interact with web browsers, providing seamless automation for web-based tasks.",
          "zh_Hans": "Introducing the Dify plugin version of Browser Use - a powerful tool that enables AI agents to control and interact with web browsers, providing seamless automation for web-based tasks."
        },
        "category": "tool",
        "created_at": "2025-04-14T03:16:28Z",
        "endpoint": {},
        "icon": "lysonober/packages/browser-use-cloud/_assets/icon.svg",
        "index_id": "lysonober___browser-use-cloud",
        "install_count": 393,
        "introduction": "# Browser Use Dify Plugin\n\n**Author:** lysonober  \n**Version:** 0.0.1  \n**Type:** tool  \n\n## Description\n\nThe Browser Use Dify Plugin provides a comprehensive integration between Dify AI agents and the Browser Use platform, enabling AI agents to control and interact with web browsers. This plugin allows AI agents to automate web tasks, retrieve browser session data, and manage browser automation workflows through a simple and consistent interface.\n\n## Available Tools\n\n| Tool Name | Description | Use Case Scenario |\n|-----------|-------------|-------------------|\n| ping | Checks server connection status to verify API availability | An AI agent needs to verify if the Browser Use service is operational before attempting to run web automation tasks |\n| me | Validates API key and returns user information | Before starting a session, an agent verifies that the provided API credentials are valid and have the necessary permissions |\n| check_balance | Retrieves user's API credit balance | A user wants to know how many credits they have remaining before running a potentially expensive automation task |\n| run_task | Creates and runs browser automation tasks | A marketing team uses an AI agent to automate competitor research by having it visit multiple websites and extract pricing information |\n| get_task_status | Retrieves current status of a specific task | A user wants to check if their web scraping task has completed without viewing the full details |\n| get_task | Retrieves comprehensive task details | After a task completes, a user needs to analyze the full output, including any errors or extracted data |\n| stop_task | Permanently stops a running task | A user notices their automation is visiting incorrect websites and wants to immediately terminate the process |\n| list_tasks | Lists all tasks with pagination support | A team manager wants to review all automation tasks run in the past week to analyze usage patterns |\n| pause_task | Temporarily pauses a running task | During a complex form-filling process, a user wants to pause the automation to manually verify some information before continuing |\n| resume_task | Resumes a previously paused task | After reviewing the paused automation state, the user is ready to continue the process from where it left off |\n| get_task_media | Retrieves media recordings from a task | A QA team wants to review the visual recording of an automated test to understand why a specific step failed |\n| get_task_gif | Gets an animated GIF of the task execution | A user wants to share a quick visual demonstration of their automation with colleagues without sharing the full recording |\n\n## Response Format\n\nAll tools in this plugin support two types of responses:\n\n1. **JSON Response**\n   - Contains complete structured information\n   - Maintains backward compatibility with existing integrations\n   - Includes all detailed information about the task or operation\n\n2. **Text Response**\n   - Provides quick access to key information\n   - Added for easier parameter passing and quick information retrieval\n   - Only available when relevant information exists\n\n### Text Response Availability\n\n- `get_task`: Outputs task result when available\n- `run_task`: Outputs task ID\n- `get_task_status`: Outputs task status\n- `check_balance`: Outputs balance value\n- `get_task_media`: Outputs recording URL when recordings exist\n\n## Tool Documentation\n\n### pingService\n\nChecks the Browser Use API server connection status.\n\n**Parameters:**\n\n*None required*\n\n**Response:**\n\n```json\n{\n  \"status\": \"success\",\n  \"message\": \"Browser Use API server is running and responding\",\n  \"response\": {\n    \"message\": \"Pong!\"\n  }\n}\n```\n\n### getUserInfo\n\nValidates the API key and returns user account information.\n\n**Parameters:**\n\n*None required*\n\n**Response:**\n\n```json\n{\n  \"status\": \"success\",\n  \"is_valid\": true,\n  \"message\": \"API key is valid and authenticated\"\n}\n```\n\n### check_balance\n\nRetrieves the current credit balance for the user's account.\n\n**Parameters:**\n\n*None required*\n\n**Response:**\n\n```json\n{\n  \"status\": \"success\",\n  \"balance\": 3000,\n  \"balance_usd\": 30.00,\n  \"message\": \"Your current balance is 3000 credits ($30.00 USD)\"\n}\n```\n\n### run_task\n\nCreates and executes a browser automation task based on natural language instructions.\n\n**Parameters:**\n\n| Parameter | Type | Required | Description |\n|-----------|------|----------|-------------|\n| task | string | Yes | Natural language description of the task to perform |\n| save_browser_data | boolean | No | Whether to save browser session data for future tasks (default: false) |\n\n**Success Response:**\n\n```json\n{\n  \"status\": \"success\",\n  \"message\": \"Task created successfully\",\n  \"task_id\": \"task_12345\",\n  \"task_info\": {\n    \"status\": \"created\",\n    \"created_at\": \"2025-04-13T20:15:30Z\",\n    \"live_url\": \"https://live.browser-use.com/task_12345\"\n  }\n}\n```\n\n**Error Response:**\n\n```json\n{\n  \"status\": \"error\",\n  \"message\": \"Failed to create task: Invalid task description\"\n}\n```\n\n### get_task_status\n\nRetrieves the current status of a specific task.\n\n**Parameters:**\n\n| Parameter | Type | Required | Description |\n|-----------|------|----------|-------------|\n| task_id | string | Yes | The unique identifier of the task |\n\n**Response:**\n\n```json\n{\n  \"status\": \"success\",\n  \"message\": \"Task status: Task is currently running\",\n  \"task_status\": \"running\"\n}\n```\n\n### get_task\n\nRetrieves comprehensive details about a specific task.\n\n**Parameters:**\n\n| Parameter | Type | Required | Description |\n|-----------|------|----------|-------------|\n| task_id | string | Yes | The unique identifier of the task |\n\n**Response:**\n\n```json\n{\n  \"status\": \"success\",\n  \"message\": \"Task 'Research educational programs...' is currently running. A live preview URL is available.\",\n  \"task_details\": {\n    \"created_at\": \"2025-04-13T20:10:35Z\",\n    \"finished_at\": null,\n    \"has_browser_data\": false,\n    \"id\": \"abc123de-4567-8f90-gh12-3456789ijklm\",\n    \"live_url\": \"https://live.example.com?sessionId=xyz987ab-6543-21cd-ef09-8765432hgfds\",\n    \"output\": null,\n    \"status\": \"running\",\n    \"steps_count\": 20,\n    \"task\": \"Research educational programs...\"\n  }\n}\n```\n\n### stop_task\n\nPermanently stops a running task. The task cannot be resumed after stopping.\n\n**Parameters:**\n\n| Parameter | Type | Required | Description |\n|-----------|------|----------|-------------|\n| task_id | string | Yes | The unique identifier of the task to stop |\n\n### list_tasks\n\nReturns a paginated list of all tasks belonging to the user, ordered by creation date.\n\n**Parameters:**\n\n| Parameter | Type | Required | Description |\n|-----------|------|----------|-------------|\n| page | number | No | The page number to retrieve (default: 1) |\n| limit | number | No | The number of tasks per page (default: 10) |\n\n**Response:**\n\n```json\n{\n  \"status\": \"success\",\n  \"message\": \"Found 1 tasks. Showing page 1 of 1 (1 tasks per page).\",\n  \"pagination\": {\n    \"current_page\": 1,\n    \"tasks_per_page\": 1,\n    \"total_pages\": 1,\n    \"total_tasks\": 1\n  },\n  \"tasks\": [\n    {\n      \"created_at\": \"2025-04-13T20:10:35Z\",\n      \"description\": \"Research educational programs...\",\n      \"id\": \"abc123de-4567-8f90-gh12-3456789ijklm\",\n      \"status\": \"running\"\n    }\n  ]\n}\n```\n\n### pause_task\n\nTemporarily pauses execution of a running task. The task can be resumed later.\n\n**Parameters:**\n\n| Parameter | Type | Required | Description |\n|-----------|------|----------|-------------|\n| task_id | string | Yes | The unique identifier of the task to pause |\n\n### resume_task\n\nResumes execution of a previously paused task. Cannot resume stopped tasks.\n\n**Parameters:**\n\n| Parameter | Type | Required | Description |\n|-----------|------|----------|-------------|\n| task_id | string | Yes | The unique identifier of the paused task to resume |\n\n### get_task_media\n\nRetrieves links to recordings or media generated during task execution.\n\n**Parameters:**\n\n| Parameter | Type | Required | Description |\n|-----------|------|----------|-------------|\n| task_id | string | Yes | The unique identifier of the task |\n\n### get_task_gif\n\nReturns a GIF URL generated from the screenshots of the task execution.\n\n**Parameters:**\n\n| Parameter | Type | Required | Description |\n|-----------|------|----------|-------------|\n| task_id | string | Yes | The unique identifier of the task |\n\n## Additional Tools\n\nThe following tools are also available in this plugin. Please explore them to discover their full capabilities:\n\n- stop_task\n- pause_task\n- resume_task\n- get_task_media\n- get_task_gif\n\n## Support\n\nIf you have any questions, please contact me at: lysonober@gmail.com\n\nFollow me on X (Twitter): [https://x.com/lyson_ober](https://x.com/lyson_ober)\n",
        "label": {
          "en_US": "browser-use-cloud",
          "ja_JP": "browser-use-cloud",
          "pt_BR": "browser-use-cloud",
          "zh_Hans": "browser-use-cloud"
        },
        "latest_package_identifier": "lysonober/browser-use-cloud:0.0.1@baefa6257632af9f71d3a3e50164f977b21c5fb5b67db49d9fb1f2eb849ac622",
        "latest_version": "0.0.1",
        "model": {},
        "name": "browser-use-cloud",
        "org": "lysonober",
        "plugin_id": "lysonober/browser-use-cloud",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/browser-use.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": true,
              "rerank": true,
              "speech2text": true,
              "text_embedding": true,
              "tts": true
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Get your Browser Use API key from cloud.browser-use.com/billing",
                "ja_JP": "cloud.browser-use.com/billing から Browser Use API キーを取得する",
                "pt_BR": "Obtenha sua chave de API do Browser Use em cloud.browser-use.com/billing",
                "zh_Hans": "从 cloud.browser-use.com/billing 获取您的 Browser Use API 密钥"
              },
              "label": {
                "en_US": "Browser Use API Key",
                "ja_JP": "Browser Use API キー",
                "pt_BR": "Chave de API do Browser Use",
                "zh_Hans": "Browser Use API 密钥"
              },
              "name": "browser_use_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Browser Use API key",
                "ja_JP": "Browser Use API キーを入力してください",
                "pt_BR": "Por favor, insira sua chave de API do Browser Use",
                "zh_Hans": "请输入您的 Browser Use API 密钥"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://cloud.browser-use.com/billing"
            }
          ],
          "identity": {
            "author": "lysonober",
            "description": {
              "en_US": "Introducing the Dify plugin version of Browser Use - a powerful tool that enables AI agents to control and interact with web browsers, providing seamless automation for web-based tasks.",
              "ja_JP": "Browser Use の Dify プラグインバージョン - AI エージェントがウェブブラウザを制御および操作できるようにする強力なツールで、ウェブベースのタスクのシームレスな自動化を提供します。",
              "pt_BR": "Apresentando a versão do plugin Dify do Browser Use - uma ferramenta poderosa que permite que agentes de IA controlem e interajam com navegadores da web, fornecendo automação perfeita para tarefas baseadas na web.",
              "zh_Hans": "Browser Use 的 Dify 插件版本 - 一个强大的工具，使 AI 代理能够控制和交互网页浏览器，为基于网络的任务提供无缝自动化。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Browser Use Cloud",
              "ja_JP": "Browser Use Cloud",
              "pt_BR": "Browser Use Cloud",
              "zh_Hans": "Browser Use Cloud"
            },
            "name": "browser-use-cloud",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Check if the Browser Use API server is running and responding. This is a simple health check endpoint.",
                  "ja_JP": "Browser Use API サーバーが実行中で応答しているかどうかを確認します。これは単純なヘルスチェックエンドポイントです。",
                  "pt_BR": "Verifique se o servidor da API Browser Use está em execução e respondendo. Este é um endpoint simples de verificação de integridade.",
                  "zh_Hans": "检查 Browser Use API 服务器是否正在运行和响应。这是一个简单的健康检查端点。"
                },
                "llm": "This tool checks if the Browser Use API server is running and responding. It makes a simple GET request to the /api/v1/ping endpoint and returns the response. This is useful for verifying connectivity to the Browser Use service before attempting more complex operations. No parameters are required."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "lysonober",
                "label": {
                  "en_US": "Ping Service",
                  "ja_JP": "サービスをPing",
                  "pt_BR": "Ping Serviço",
                  "zh_Hans": "测试连接"
                },
                "name": "ping"
              },
              "output_schema": null,
              "parameters": null
            },
            {
              "description": {
                "human": {
                  "en_US": "Check if your Browser Use API key is valid and you are properly authenticated.",
                  "ja_JP": "Browser Use API キーが有効であり、適切に認証されているかどうかを確認します。",
                  "pt_BR": "Verifique se sua chave de API do Browser Use é válida e se você está autenticado corretamente.",
                  "zh_Hans": "检查您的 Browser Use API 密钥是否有效，以及您是否已正确认证。"
                },
                "llm": "This tool checks if the provided Browser Use API key is valid and the user is properly authenticated. It makes a GET request to the /api/v1/me endpoint with the API key in the Authorization header. The response is a boolean value indicating if the API key is valid. This is useful for verifying API key validity before attempting operations that require authentication. No parameters are required as the API key is automatically used from the credentials."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "lysonober",
                "label": {
                  "en_US": "Get User Info",
                  "ja_JP": "ユーザー情報を取得",
                  "pt_BR": "Obter Informações do Usuário",
                  "zh_Hans": "获取用户信息"
                },
                "name": "me"
              },
              "output_schema": null,
              "parameters": null
            },
            {
              "description": {
                "human": {
                  "en_US": "Check your current Browser Use API credit balance, including both monthly subscription credits and any additional purchased credits.",
                  "ja_JP": "月額サブスクリプションクレジットと追加購入クレジットの両方を含む、現在の Browser Use API クレジット残高を確認します。",
                  "pt_BR": "Verifique seu saldo atual de créditos da API Browser Use, incluindo créditos de assinatura mensal e quaisquer créditos adicionais comprados.",
                  "zh_Hans": "查询您当前的 Browser Use API 积分余额，包括每月订阅积分和任何额外购买的积分。"
                },
                "llm": "This tool checks the user's current API credit balance with Browser Use. It makes a GET request to the /api/v1/balance endpoint with the API key in the Authorization header. The response includes the balance field which shows the number of API credits available (where 1 credit = $0.01 USD). This is useful for monitoring usage and ensuring sufficient credits for task execution. No parameters are required as the API key is automatically used from the credentials."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "lysonober",
                "label": {
                  "en_US": "Check Balance",
                  "ja_JP": "残高を確認",
                  "pt_BR": "Verificar Saldo",
                  "zh_Hans": "查询余额"
                },
                "name": "check_balance"
              },
              "output_schema": null,
              "parameters": null
            },
            {
              "description": {
                "human": {
                  "en_US": "Create and run a new browser automation task by providing instructions in natural language.",
                  "ja_JP": "自然言語での指示を提供して、新しいブラウザ自動化タスクを作成して実行します。",
                  "pt_BR": "Crie e execute uma nova tarefa de automação de navegador fornecendo instruções em linguagem natural.",
                  "zh_Hans": "通过提供自然语言指令来创建和运行新的浏览器自动化任务。"
                },
                "llm": "This tool creates and runs a new browser automation task with Browser Use. It makes a POST request to the /api/v1/run-task endpoint with the task description and optional configuration. The task parameter should be a natural language instruction describing what the browser should do (e.g., 'Go to google.com and search for Browser Use'). You can optionally specify whether to save browser data (cookies, etc.) for future use. The response includes a task ID that can be used with other tools to track progress, get status updates, or retrieve media from the task."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "lysonober",
                "label": {
                  "en_US": "Run Task",
                  "ja_JP": "タスクを実行",
                  "pt_BR": "Executar Tarefa",
                  "zh_Hans": "运行任务"
                },
                "name": "run_task"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Describe what the browser should do in natural language (e.g., 'Go to google.com and search for Browser Use').",
                    "ja_JP": "ブラウザが何をすべきかを自然言語で説明します（例：'google.com にアクセスして Browser Use を検索する'）。",
                    "pt_BR": "Descreva o que o navegador deve fazer em linguagem natural (por exemplo, 'Vá para google.com e pesquise por Browser Use').",
                    "zh_Hans": "用自然语言描述浏览器应该做什么（例如，'前往 google.com 并搜索 Browser Use'）。"
                  },
                  "label": {
                    "en_US": "Task Description",
                    "ja_JP": "タスクの説明",
                    "pt_BR": "Descrição da Tarefa",
                    "zh_Hans": "任务描述"
                  },
                  "llm_description": "A natural language instruction describing what the browser should do. Be specific and clear about the websites to visit and actions to perform. For example: 'Go to google.com and search for Browser Use', or 'Log into twitter.com with username X and password Y, then post a tweet saying Hello World'.",
                  "max": null,
                  "min": null,
                  "name": "task",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "If enabled, browser cookies and other data will be saved (safely encrypted) for future tasks. For example, if you log into a website in one task, enabling this option allows future tasks to remain logged in without re-authentication.",
                    "ja_JP": "有効にすると、ブラウザのクッキーやその他のデータが将来のタスクのために（安全に暗号化されて）保存されます。例えば、あるタスクでウェブサイトにログインした場合、このオプションを有効にすると、将来のタスクで再認証なしでログイン状態を維持できます。",
                    "pt_BR": "Se ativado, cookies do navegador e outros dados serão salvos (criptografados com segurança) para tarefas futuras. Por exemplo, se você fizer login em um site em uma tarefa, ativar esta opção permite que tarefas futuras permaneçam conectadas sem necessidade de reautenticação.",
                    "zh_Hans": "如果启用，浏览器 cookies 和其他数据将被保存（安全加密）以供将来的任务使用。例如，如果您在一个任务中登录了某个网站，启用此选项可以让未来的任务保持登录状态，无需重新认证。"
                  },
                  "label": {
                    "en_US": "Save Browser Data",
                    "ja_JP": "ブラウザデータを保存",
                    "pt_BR": "Salvar Dados do Navegador",
                    "zh_Hans": "保存浏览器数据"
                  },
                  "llm_description": "Boolean flag indicating whether to save browser cookies and other data. If set to true, the browser state (cookies, local storage, etc.) will be saved and can be reused in future tasks. This is useful for maintaining login sessions across multiple tasks. The data is safely encrypted before storing in the database.",
                  "max": null,
                  "min": null,
                  "name": "save_browser_data",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Check the current status of a browser automation task. Returns a simple status value (created, running, finished, stopped, paused, or failed).",
                  "ja_JP": "ブラウザ自動化タスクの現在のステータスを確認します。シンプルなステータス値（作成済み、実行中、完了、停止、一時停止、または失敗）を返します。",
                  "pt_BR": "Verifique o status atual de uma tarefa de automação do navegador. Retorna um valor de status simples (criado, em execução, concluído, parado, pausado ou falhou).",
                  "zh_Hans": "检查浏览器自动化任务的当前状态。返回一个简单的状态值（已创建、运行中、已完成、已停止、已暂停或失败）。"
                },
                "llm": "This tool checks the current status of a browser automation task by its ID. It makes a GET request to the /api/v1/task/{task_id}/status endpoint and returns a simple status string. The possible status values are: 'created' (initialized but not started), 'running' (currently executing), 'finished' (completed successfully), 'stopped' (manually stopped), 'paused' (temporarily paused), or 'failed' (encountered an error). This is more lightweight than getting the full task details when you only need to know the current execution state."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "lysonober",
                "label": {
                  "en_US": "Get Task Status",
                  "ja_JP": "タスクステータスを取得",
                  "pt_BR": "Obter Status da Tarefa",
                  "zh_Hans": "获取任务状态"
                },
                "name": "get_task_status"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The unique identifier of the task you want to check the status for. This is the ID returned when you created the task.",
                    "ja_JP": "ステータスを確認したいタスクの一意の識別子。これはタスク作成時に返された ID です。",
                    "pt_BR": "O identificador único da tarefa para a qual você deseja verificar o status. Este é o ID retornado quando você criou a tarefa.",
                    "zh_Hans": "您想要检查状态的任务的唯一标识符。这是您创建任务时返回的 ID。"
                  },
                  "label": {
                    "en_US": "Task ID",
                    "ja_JP": "タスク ID",
                    "pt_BR": "ID da Tarefa",
                    "zh_Hans": "任务 ID"
                  },
                  "llm_description": "The unique identifier (ID) of the task you want to check the status for. This is the ID string that was returned when you created the task using the run_task tool.",
                  "max": null,
                  "min": null,
                  "name": "task_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get comprehensive information about a browser automation task, including its status, steps completed, output, and live preview URL.",
                  "ja_JP": "ブラウザ自動化タスクのステータス、完了したステップ、出力、ライブプレビューURLなど、包括的な情報を取得します。",
                  "pt_BR": "Obtenha informações abrangentes sobre uma tarefa de automação do navegador, incluindo seu status, etapas concluídas, saída e URL de visualização ao vivo.",
                  "zh_Hans": "获取浏览器自动化任务的全面信息，包括其状态、已完成的步骤、输出和实时预览 URL。"
                },
                "llm": "This tool retrieves comprehensive information about a browser automation task by its ID. It makes a GET request to the /api/v1/task/{task_id} endpoint and returns detailed task information including current status, steps completed, output (if finished), creation and completion timestamps, and a live preview URL that can be embedded in an iframe to watch the task execution in real-time. If the task was created with save_browser_data=true, it will also include browser session data like cookies."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "lysonober",
                "label": {
                  "en_US": "Get Task Details",
                  "ja_JP": "タスク詳細を取得",
                  "pt_BR": "Obter Detalhes da Tarefa",
                  "zh_Hans": "获取任务详情"
                },
                "name": "get_task"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The unique identifier of the task you want to get details for. This is the ID returned when you created the task.",
                    "ja_JP": "詳細を取得したいタスクの一意の識別子。これはタスク作成時に返された ID です。",
                    "pt_BR": "O identificador único da tarefa para a qual você deseja obter detalhes. Este é o ID retornado quando você criou a tarefa.",
                    "zh_Hans": "您想要获取详情的任务的唯一标识符。这是您创建任务时返回的 ID。"
                  },
                  "label": {
                    "en_US": "Task ID",
                    "ja_JP": "タスク ID",
                    "pt_BR": "ID da Tarefa",
                    "zh_Hans": "任务 ID"
                  },
                  "llm_description": "The unique identifier (ID) of the task you want to get details for. This is the ID string that was returned when you created the task using the run_task tool.",
                  "max": null,
                  "min": null,
                  "name": "task_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Permanently stop a running browser automation task. Note that the task cannot be resumed after being stopped.",
                  "ja_JP": "実行中のブラウザ自動化タスクを永久に停止します。停止後はタスクを再開できないことに注意してください。",
                  "pt_BR": "Pare permanentemente uma tarefa de automação de navegador em execução. Observe que a tarefa não pode ser retomada após ser interrompida.",
                  "zh_Hans": "永久停止正在运行的浏览器自动化任务。请注意，任务停止后将无法恢复。"
                },
                "llm": "This tool permanently stops a running browser automation task. It makes a PUT request to the /api/v1/stop-task endpoint with the task ID as a query parameter. Once a task is stopped, it cannot be resumed - this is a permanent action. If you only want to temporarily halt execution with the ability to resume later, use the pause_task tool instead. The response is typically a simple confirmation message."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "lysonober",
                "label": {
                  "en_US": "Stop Task",
                  "ja_JP": "タスクを停止",
                  "pt_BR": "Parar Tarefa",
                  "zh_Hans": "停止任务"
                },
                "name": "stop_task"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The unique identifier of the task you want to stop. This is the ID returned when you created the task.",
                    "ja_JP": "停止したいタスクの一意の識別子。これはタスク作成時に返された ID です。",
                    "pt_BR": "O identificador único da tarefa que você deseja parar. Este é o ID retornado quando você criou a tarefa.",
                    "zh_Hans": "您想要停止的任务的唯一标识符。这是您创建任务时返回的 ID。"
                  },
                  "label": {
                    "en_US": "Task ID",
                    "ja_JP": "タスク ID",
                    "pt_BR": "ID da Tarefa",
                    "zh_Hans": "任务 ID"
                  },
                  "llm_description": "The unique identifier (ID) of the task you want to stop. This is the ID string that was returned when you created the task using the run_task tool. Be aware that stopping a task is permanent - the task cannot be resumed after being stopped.",
                  "max": null,
                  "min": null,
                  "name": "task_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get a paginated list of all your browser automation tasks, ordered by creation date. Each task includes basic information like status and creation time.",
                  "ja_JP": "作成日順に並べられた、すべてのブラウザ自動化タスクのページ分割されたリストを取得します。各タスクにはステータスや作成時間などの基本情報が含まれます。",
                  "pt_BR": "Obtenha uma lista paginada de todas as suas tarefas de automação de navegador, ordenadas por data de criação. Cada tarefa inclui informações básicas como status e hora de criação.",
                  "zh_Hans": "获取按创建日期排序的所有浏览器自动化任务的分页列表。每个任务包括状态和创建时间等基本信息。"
                },
                "llm": "This tool retrieves a paginated list of all browser automation tasks belonging to the user, ordered by creation date (newest first). It makes a GET request to the /api/v1/tasks endpoint with optional page and limit parameters for pagination control. Each task in the response includes basic information like ID, description, status, creation time, and live URL. This is useful for getting an overview of all tasks, both active and completed. For detailed information about a specific task, use the get_task tool with the task ID."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "lysonober",
                "label": {
                  "en_US": "List Tasks",
                  "ja_JP": "タスク一覧",
                  "pt_BR": "Listar Tarefas",
                  "zh_Hans": "列出任务"
                },
                "name": "list_tasks"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": 1,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The page number to retrieve (starts at 1). Use this for pagination when there are many tasks.",
                    "ja_JP": "取得するページ番号（1から始まる）。タスクが多い場合、ページ分割のためにこれを使用します。",
                    "pt_BR": "O número da página a ser recuperada (começa em 1). Use isso para paginação quando houver muitas tarefas.",
                    "zh_Hans": "要检索的页码（从 1 开始）。当有很多任务时，使用此参数进行分页。"
                  },
                  "label": {
                    "en_US": "Page Number",
                    "ja_JP": "ページ番号",
                    "pt_BR": "Número da Página",
                    "zh_Hans": "页码"
                  },
                  "llm_description": "The page number to retrieve, starting from 1. Used for pagination when there are many tasks. Default is 1 (first page).",
                  "max": null,
                  "min": null,
                  "name": "page",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 10,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The number of tasks to show per page (default: 10). Higher values return more tasks at once.",
                    "ja_JP": "1ページあたりに表示するタスクの数（デフォルト：10）。より高い値を設定すると、一度により多くのタスクが返されます。",
                    "pt_BR": "O número de tarefas a serem mostradas por página (padrão: 10). Valores mais altos retornam mais tarefas de uma vez.",
                    "zh_Hans": "每页显示的任务数量（默认值：10）。较高的值会一次返回更多任务。"
                  },
                  "label": {
                    "en_US": "Results Per Page",
                    "ja_JP": "1ページあたりの結果数",
                    "pt_BR": "Resultados Por Página",
                    "zh_Hans": "每页结果数"
                  },
                  "llm_description": "The number of tasks to show per page. Minimum value is 1. Default is 10. Higher values return more tasks at once but may increase response time.",
                  "max": null,
                  "min": null,
                  "name": "limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Pauses execution of a running task. The task can be resumed later using the resume_task tool. Useful for manual intervention or inspection.",
                  "ja_JP": "実行中のタスクの実行を一時停止します。タスクは後で resume_task ツールを使用して再開できます。手動での介入や検査に役立ちます。",
                  "pt_BR": "Pausa a execução de uma tarefa em execução. A tarefa pode ser retomada posteriormente usando a ferramenta resume_task. Útil para intervenção manual ou inspeção.",
                  "zh_Hans": "暂停正在运行的任务执行。该任务可以稍后使用 resume_task 工具恢复。适用于手动干预或检查。"
                },
                "llm": "This tool pauses the execution of a running browser automation task. It makes a PUT request to the /api/v1/pause-task endpoint with the task_id as a query parameter. The task will enter a 'paused' state and can be resumed later using the resume_task tool. This is useful when you need to temporarily halt a task for manual intervention, inspection, or to conserve resources. Only tasks in the 'running' state can be paused."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "lysonober",
                "label": {
                  "en_US": "Pause Task",
                  "ja_JP": "タスクを一時停止",
                  "pt_BR": "Pausar Tarefa",
                  "zh_Hans": "暂停任务"
                },
                "name": "pause_task"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The unique identifier of the task you want to pause. Must be a valid task ID from a previously created task.",
                    "ja_JP": "一時停止したいタスクの一意の識別子。以前に作成されたタスクの有効なタスク ID である必要があります。",
                    "pt_BR": "O identificador único da tarefa que você deseja pausar. Deve ser um ID de tarefa válido de uma tarefa criada anteriormente.",
                    "zh_Hans": "您要暂停的任务的唯一标识符。必须是先前创建的任务的有效任务 ID。"
                  },
                  "label": {
                    "en_US": "Task ID",
                    "ja_JP": "タスク ID",
                    "pt_BR": "ID da Tarefa",
                    "zh_Hans": "任务 ID"
                  },
                  "llm_description": "The unique identifier of the task to pause. This must be a valid task ID from a previously created task. Only tasks in the 'running' state can be paused.",
                  "max": null,
                  "min": null,
                  "name": "task_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Resumes execution of a previously paused task. The task will continue from where it was paused. You can't resume a stopped task.",
                  "ja_JP": "以前に一時停止されたタスクの実行を再開します。タスクは一時停止された場所から続行されます。停止されたタスクは再開できません。",
                  "pt_BR": "Retoma a execução de uma tarefa previamente pausada. A tarefa continuará de onde foi pausada. Não é possível retomar uma tarefa interrompida.",
                  "zh_Hans": "恢复先前暂停的任务的执行。任务将从暂停的位置继续。您无法恢复已停止的任务。"
                },
                "llm": "This tool resumes the execution of a previously paused browser automation task. It makes a PUT request to the /api/v1/resume-task endpoint with the task_id as a query parameter. The task will continue from where it was paused and return to the 'running' state. This is useful when you want to continue a task after manual intervention or inspection. Note that only tasks in the 'paused' state can be resumed - tasks that were stopped (using stop_task) cannot be resumed."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "lysonober",
                "label": {
                  "en_US": "Resume Task",
                  "ja_JP": "タスクを再開",
                  "pt_BR": "Retomar Tarefa",
                  "zh_Hans": "恢复任务"
                },
                "name": "resume_task"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The unique identifier of the task you want to resume. Must be a valid task ID from a previously paused task.",
                    "ja_JP": "再開したいタスクの一意の識別子。以前に一時停止されたタスクの有効なタスク ID である必要があります。",
                    "pt_BR": "O identificador único da tarefa que você deseja retomar. Deve ser um ID de tarefa válido de uma tarefa pausada anteriormente.",
                    "zh_Hans": "您要恢复的任务的唯一标识符。必须是先前暂停的任务的有效任务 ID。"
                  },
                  "label": {
                    "en_US": "Task ID",
                    "ja_JP": "タスク ID",
                    "pt_BR": "ID da Tarefa",
                    "zh_Hans": "任务 ID"
                  },
                  "llm_description": "The unique identifier of the task to resume. This must be a valid task ID from a previously paused task. Only tasks in the 'paused' state can be resumed - tasks that were stopped cannot be resumed.",
                  "max": null,
                  "min": null,
                  "name": "task_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Returns links to any recordings or media generated during task execution, such as browser session recordings. Only available for completed tasks.",
                  "ja_JP": "タスク実行中に生成された録画やメディアへのリンクを返します（ブラウザセッションの録画など）。完了したタスクでのみ利用可能です。",
                  "pt_BR": "Retorna links para quaisquer gravações ou mídia geradas durante a execução da tarefa, como gravações de sessão do navegador. Disponível apenas para tarefas concluídas.",
                  "zh_Hans": "返回任务执行期间生成的任何录制或媒体的链接，例如浏览器会话录制。仅适用于已完成的任务。"
                },
                "llm": "This tool retrieves links to recordings and other media files generated during a browser automation task's execution. It makes a GET request to the /api/v1/task/{task_id}/media endpoint. The response includes an array of URLs pointing to recordings of the browser session, which can be useful for reviewing what happened during task execution or for debugging purposes. This tool is most useful for completed tasks, as media may not be available for tasks that are still in progress or failed early."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "lysonober",
                "label": {
                  "en_US": "Get Task Media",
                  "ja_JP": "タスクメディアを取得",
                  "pt_BR": "Obter Mídia da Tarefa",
                  "zh_Hans": "获取任务媒体"
                },
                "name": "get_task_media"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The unique identifier of the task for which you want to retrieve media. Must be a valid task ID from a previously created task.",
                    "ja_JP": "メディアを取得したいタスクの一意の識別子。以前に作成されたタスクの有効なタスク ID である必要があります。",
                    "pt_BR": "O identificador único da tarefa para a qual você deseja recuperar mídia. Deve ser um ID de tarefa válido de uma tarefa criada anteriormente.",
                    "zh_Hans": "您要检索媒体的任务的唯一标识符。必须是先前创建的任务的有效任务 ID。"
                  },
                  "label": {
                    "en_US": "Task ID",
                    "ja_JP": "タスク ID",
                    "pt_BR": "ID da Tarefa",
                    "zh_Hans": "任务 ID"
                  },
                  "llm_description": "The unique identifier of the task for which to retrieve media files. This must be a valid task ID from a previously created task. Media is typically only available for tasks that have completed execution.",
                  "max": null,
                  "min": null,
                  "name": "task_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Returns a GIF URL generated from the screenshots of the task execution. Only available for completed tasks that have screenshots.",
                  "ja_JP": "タスク実行のスクリーンショットから生成された GIF URL を返します。スクリーンショットがある完了したタスクでのみ利用可能です。",
                  "pt_BR": "Retorna uma URL de GIF gerada a partir das capturas de tela da execução da tarefa. Disponível apenas para tarefas concluídas que possuem capturas de tela.",
                  "zh_Hans": "返回从任务执行截图生成的 GIF URL。仅适用于有截图的已完成任务。"
                },
                "llm": "This tool retrieves a URL to an animated GIF that shows the progression of a browser automation task. It makes a GET request to the /api/v1/task/{task_id}/gif endpoint. The GIF is automatically generated from screenshots taken during task execution, providing a visual replay of what happened in the browser. This is particularly useful for reviewing complex tasks or debugging issues. Note that this is only available for completed tasks that have screenshots captured during execution."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "lysonober",
                "label": {
                  "en_US": "Get Task GIF",
                  "ja_JP": "タスク GIF を取得",
                  "pt_BR": "Obter GIF da Tarefa",
                  "zh_Hans": "获取任务 GIF"
                },
                "name": "get_task_gif"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The unique identifier of the task for which you want to retrieve a GIF. Must be a valid task ID from a previously completed task.",
                    "ja_JP": "GIF を取得したいタスクの一意の識別子。以前に完了したタスクの有効なタスク ID である必要があります。",
                    "pt_BR": "O identificador único da tarefa para a qual você deseja recuperar um GIF. Deve ser um ID de tarefa válido de uma tarefa concluída anteriormente.",
                    "zh_Hans": "您要检索 GIF 的任务的唯一标识符。必须是先前完成的任务的有效任务 ID。"
                  },
                  "label": {
                    "en_US": "Task ID",
                    "ja_JP": "タスク ID",
                    "pt_BR": "ID da Tarefa",
                    "zh_Hans": "任务 ID"
                  },
                  "llm_description": "The unique identifier of the task for which to retrieve a GIF animation. This must be a valid task ID from a previously completed task. The task must have had screenshots captured during execution for a GIF to be available.",
                  "max": null,
                  "min": null,
                  "name": "task_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-14T03:16:35Z",
        "version_updated_at": "2025-04-14T03:16:35Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "This simple tool can be used to fix an invalid json string.",
          "ja_JP": "This simple tool can be used to fix an invalid json string.",
          "pt_BR": "This simple tool can be used to fix an invalid json string.",
          "zh_Hans": "本工具可以修复一个损坏的json字符串。"
        },
        "category": "tool",
        "created_at": "2025-03-31T08:13:52Z",
        "endpoint": {},
        "icon": "ivan97/packages/repair_json/_assets/icon.svg",
        "index_id": "ivan97___repair_json",
        "install_count": 390,
        "introduction": "## repair_json\n\n**Author:** ivan97\n**Version:** 0.0.2\n**Type:** tool\n\n### Description\n\nThis simple tool can be used to fix an invalid json string.\n\n\n### Usage\n\n1. Add the plugin to your workflow.\n![img.png](_assets/images/add_plugin.png)\n\n2. Use the `repair_json` function to fix the invalid json string.\n![img.png](_assets/images/config.png)\n\n3. Demo\n![img_2.png](_assets/images/demo.png)\n\n",
        "label": {
          "en_US": "repair_json",
          "ja_JP": "repair_json",
          "pt_BR": "repair_json",
          "zh_Hans": "Json修复"
        },
        "latest_package_identifier": "ivan97/repair_json:0.0.2@7e6f00591264920c7086bc90252a74f5189fe55133e918d63328b84d072490dd",
        "latest_version": "0.0.2",
        "model": {},
        "name": "repair_json",
        "org": "ivan97",
        "plugin_id": "ivan97/repair_json",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/repair_json.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {}
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "ivan97",
            "description": {
              "en_US": "This simple tool can be used to fix an invalid json string.",
              "pt_BR": "This simple tool can be used to fix an invalid json string.",
              "zh_Hans": "本工具可以修复一个损坏的json字符串。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "repair_json",
              "pt_BR": "repair_json",
              "zh_Hans": "Json修复"
            },
            "name": "repair_json",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "This simple tool can be used to fix an invalid json string.",
                  "pt_BR": "This simple tool can be used to fix an invalid json string.",
                  "zh_Hans": "本工具可以修复一个损坏的json字符串。"
                },
                "llm": "This simple tool can be used to fix an invalid json string."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "ivan97",
                "label": {
                  "en_US": "repair_json",
                  "pt_BR": "repair_json",
                  "zh_Hans": "Json修复"
                },
                "name": "repair_json"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "an invalid json string.",
                    "pt_BR": "an invalid json string.",
                    "zh_Hans": "损坏的json字符串。"
                  },
                  "label": {
                    "en_US": "Broken json",
                    "pt_BR": "Broken json",
                    "zh_Hans": "损坏的Json"
                  },
                  "llm_description": "This simple tool can be used to fix an invalid json string.",
                  "max": null,
                  "min": null,
                  "name": "input",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-31T11:54:49Z",
        "version_updated_at": "2025-03-31T11:54:49Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Triton Inference Server"
        },
        "category": "model",
        "created_at": "2024-12-05T12:28:38Z",
        "endpoint": {},
        "icon": "langgenius/packages/triton_inference_server/_assets/icon_s_en.svg",
        "index_id": "langgenius___triton_inference_server",
        "install_count": 386,
        "introduction": "",
        "label": {
          "en_US": "Triton Inference Server"
        },
        "latest_package_identifier": "langgenius/triton_inference_server:0.0.2@d0bd35d3ab9e62163081bc5ef0d36e9ebe886009fb3bd8915ab2b5bcd7645cd1",
        "latest_version": "0.0.2",
        "model": {
          "background": "#EFFDFD",
          "configurate_methods": [
            "customizable-model"
          ],
          "description": {
            "en_US": "Triton Inference Server"
          },
          "help": {
            "title": {
              "en_US": "How to deploy Triton Inference Server",
              "zh_Hans": "如何部署 Triton Inference Server"
            },
            "url": {
              "en_US": "https://github.com/triton-inference-server/server"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.png"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "Triton Inference Server"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "Server url",
                  "zh_Hans": "服务器URL"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter the url of your Triton Inference Server, e.g. http://192.168.1.100:8000",
                  "zh_Hans": "在此输入 Triton Inference Server 的服务器地址，如 http://192.168.1.100:8000"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "server_url"
              },
              {
                "default": "2048",
                "label": {
                  "en_US": "Context size",
                  "zh_Hans": "上下文大小"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter the context size",
                  "zh_Hans": "在此输入您的上下文大小"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "context_size"
              },
              {
                "default": "chat",
                "label": {
                  "en_US": "Model type",
                  "zh_Hans": "补全类型"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Completion model",
                      "zh_Hans": "补全模型"
                    },
                    "show_on": [],
                    "value": "completion"
                  },
                  {
                    "label": {
                      "en_US": "Chat model",
                      "zh_Hans": "对话模型"
                    },
                    "show_on": [],
                    "value": "chat"
                  }
                ],
                "placeholder": {
                  "en_US": "Enter the completion type",
                  "zh_Hans": "在此输入您的补全类型"
                },
                "required": true,
                "show_on": [],
                "type": "select",
                "variable": "completion_type"
              },
              {
                "default": "true",
                "label": {
                  "en_US": "Stream output",
                  "zh_Hans": "流式输出"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Yes",
                      "zh_Hans": "是"
                    },
                    "show_on": [],
                    "value": "true"
                  },
                  {
                    "label": {
                      "en_US": "No",
                      "zh_Hans": "否"
                    },
                    "show_on": [],
                    "value": "false"
                  }
                ],
                "placeholder": {
                  "en_US": "Whether to support stream output",
                  "zh_Hans": "是否支持流式输出"
                },
                "required": true,
                "show_on": [],
                "type": "select",
                "variable": "stream"
              }
            ],
            "model": {
              "label": {
                "en_US": "Model Name",
                "zh_Hans": "模型名称"
              },
              "placeholder": {
                "en_US": "Enter your model name",
                "zh_Hans": "输入模型名称"
              }
            }
          },
          "models": [],
          "position": {
            "llm": null
          },
          "provider": "triton_inference_server",
          "provider_credential_schema": null,
          "supported_model_types": [
            "llm"
          ]
        },
        "name": "triton_inference_server",
        "org": "langgenius",
        "plugin_id": "langgenius/triton_inference_server",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/triton_inference_server.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-02-17T06:57:47Z",
        "version_updated_at": "2025-02-17T06:57:47Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Two plugins，One is the Hallucination controllable Text2SQL component，the other is the fast response ChatBI.",
          "zh_Hans": "包含了一个幻觉可控的Text2SQL极速生成插件；以及一个可多轮问数的ChatBI插件。"
        },
        "category": "tool",
        "created_at": "2025-04-13T17:35:53Z",
        "endpoint": {},
        "icon": "joto/packages/datafocus/_assets/icon.svg",
        "index_id": "joto___datafocus",
        "install_count": 386,
        "introduction": "",
        "label": {
          "en_US": "DataFocus",
          "zh_Hans": "DataFocus"
        },
        "latest_package_identifier": "joto/datafocus:0.0.2@2e7cb6625fdd4c489a8a45be705ba9c695f51c6fe2d43f4af9279ca591141966",
        "latest_version": "0.0.2",
        "model": {},
        "name": "datafocus",
        "org": "joto",
        "plugin_id": "joto/datafocus",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/datafocus.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "https://www.datafocus.ai/user-registration-agreement",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": "https://cloud001.datafocus.ai",
              "help": null,
              "label": {
                "en_US": "DataFocus host",
                "zh_Hans": "DataFocus host"
              },
              "name": "datafocus_host",
              "options": null,
              "placeholder": {
                "en_US": "Please input your DataFocus host url",
                "zh_Hans": "请输入你的DataFocus应用地址"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "help": {
                "en_US": "Get your APP token from DataFocus",
                "zh_Hans": "从 DataFocus 获取您的 APP Token"
              },
              "label": {
                "en_US": "DataFocus APP Token",
                "zh_Hans": "DataFocus APP Token"
              },
              "name": "app_token",
              "options": null,
              "placeholder": {
                "en_US": "Please input your APP Token",
                "zh_Hans": "请输入你的 APP Token"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://www.datafocus.ai/infos/data-focus-token?from=dify"
            }
          ],
          "identity": {
            "author": "shaojk",
            "description": {
              "en_US": "Two plugins，One is the Hallucination controllable Text2SQL component，the other is the fast response ChatBI.",
              "zh_Hans": "包含了一个幻觉可控的Text2SQL极速生成插件；以及一个可多轮问数的ChatBI插件。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "DataFocus",
              "zh_Hans": "DataFocus"
            },
            "name": "datafocus",
            "tags": [
              "search"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A natural language to SQL plugin based on FocusSearch keyword parsing, more accurate, faster, and cheaper!",
                  "zh_Hans": "DataFocus旗下支持多轮对话的智能问数插件，提供即插即用的ChatBI能力"
                },
                "llm": "一款基于FocusSearch关键词解析的自然语言转SQL插件，更准，更快，更便宜！"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "joto",
                "label": {
                  "en_US": "FocusSQL",
                  "zh_Hans": "FocusSQL"
                },
                "name": "focus-sql"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": "chinese",
                  "form": "llm",
                  "human_description": {
                    "en_US": "Language environment",
                    "zh_Hans": "语言环境"
                  },
                  "label": {
                    "en_US": "Language",
                    "zh_Hans": "语言环境"
                  },
                  "llm_description": "Language environment",
                  "max": null,
                  "min": null,
                  "name": "language",
                  "options": [
                    {
                      "label": {
                        "en_US": "Chinese",
                        "zh_Hans": "中文"
                      },
                      "value": "chinese"
                    },
                    {
                      "label": {
                        "en_US": "English",
                        "zh_Hans": "英文"
                      },
                      "value": "english"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Natural language input",
                    "zh_Hans": "输入的自然语言"
                  },
                  "label": {
                    "en_US": "Query Statement",
                    "zh_Hans": "查询语句"
                  },
                  "llm_description": "Natural language input",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Select the name of the data table that you want to query",
                    "zh_Hans": "选择要查询的数据表名"
                  },
                  "label": {
                    "en_US": "Table Name",
                    "zh_Hans": "数据表名"
                  },
                  "llm_description": "Select the name of the data table that you want to query",
                  "max": null,
                  "min": null,
                  "name": "tableName",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The JSON string of the queried table model",
                    "zh_Hans": "查询的表模型的json字符串"
                  },
                  "label": {
                    "en_US": "Data Model",
                    "zh_Hans": "数据模型"
                  },
                  "llm_description": "The JSON string of the queried table model",
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "mysql",
                  "form": "llm",
                  "human_description": {
                    "en_US": "The dialect type of SQL output by the model",
                    "zh_Hans": "模型输出SQL的方言类型"
                  },
                  "label": {
                    "en_US": "Output SQL Type",
                    "zh_Hans": "输出SQL类型"
                  },
                  "llm_description": "The dialect type of SQL output by the model",
                  "max": null,
                  "min": null,
                  "name": "outputSqlType",
                  "options": [
                    {
                      "label": {
                        "en_US": "MySQL"
                      },
                      "value": "mysql"
                    },
                    {
                      "label": {
                        "en_US": "ClickHouse"
                      },
                      "value": "clickhouse"
                    },
                    {
                      "label": {
                        "en_US": "Impala"
                      },
                      "value": "impala"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Session unique identifier, which is used by the plug-in to identify the current session and can be passed in sys.conversation_id",
                    "zh_Hans": "会话唯一标识，用于插件识别当前会话，可传入sys.conversation_id"
                  },
                  "label": {
                    "en_US": "Conversation Id",
                    "zh_Hans": "Conversation Id"
                  },
                  "llm_description": "Session unique identifier, which is used by the plug-in to identify the current session and can be passed in sys.conversation_id",
                  "max": null,
                  "min": null,
                  "name": "conversation_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "chat",
                  "form": "llm",
                  "human_description": {
                    "en_US": "Action performed by plugins",
                    "zh_Hans": "插件执行的动作"
                  },
                  "label": {
                    "en_US": "Action",
                    "zh_Hans": "执行行为"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "action",
                  "options": [
                    {
                      "label": {
                        "en_US": "get table list",
                        "zh_Hans": "获取数据表列表"
                      },
                      "value": "listTables"
                    },
                    {
                      "label": {
                        "en_US": "chat and get data",
                        "zh_Hans": "对话互动"
                      },
                      "value": "chat"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Select database type",
                    "zh_Hans": "选择要连接的数据库类型"
                  },
                  "label": {
                    "en_US": "Datasource Type",
                    "zh_Hans": "数据源类型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "type",
                  "options": [
                    {
                      "label": {
                        "en_US": "MySQL",
                        "zh_Hans": "MySQL"
                      },
                      "value": "mysql"
                    },
                    {
                      "label": {
                        "en_US": "PostgreSQL",
                        "zh_Hans": "PostgreSQL"
                      },
                      "value": "postgresql"
                    },
                    {
                      "label": {
                        "en_US": "SQLServer",
                        "zh_Hans": "SQLServer"
                      },
                      "value": "sqlserver"
                    },
                    {
                      "label": {
                        "en_US": "Oracle",
                        "zh_Hans": "Oracle"
                      },
                      "value": "oracle"
                    },
                    {
                      "label": {
                        "en_US": "IBMDB2",
                        "zh_Hans": "IBMDB2"
                      },
                      "value": "ibmdb2"
                    },
                    {
                      "label": {
                        "en_US": "GaussDB100",
                        "zh_Hans": "GaussDB100"
                      },
                      "value": "gaussdb100"
                    },
                    {
                      "label": {
                        "en_US": "Sybase",
                        "zh_Hans": "Sybase"
                      },
                      "value": "sybase"
                    },
                    {
                      "label": {
                        "en_US": "Greenplum",
                        "zh_Hans": "Greenplum"
                      },
                      "value": "greenplum"
                    },
                    {
                      "label": {
                        "en_US": "Clickhouse",
                        "zh_Hans": "Clickhouse"
                      },
                      "value": "clickhouse"
                    },
                    {
                      "label": {
                        "en_US": "Teradata",
                        "zh_Hans": "Teradata"
                      },
                      "value": "teradata"
                    },
                    {
                      "label": {
                        "en_US": "Doris",
                        "zh_Hans": "Doris"
                      },
                      "value": "doris"
                    },
                    {
                      "label": {
                        "en_US": "TIDB",
                        "zh_Hans": "TIDB"
                      },
                      "value": "tidb"
                    },
                    {
                      "label": {
                        "en_US": "Hana",
                        "zh_Hans": "Hana"
                      },
                      "value": "hana"
                    },
                    {
                      "label": {
                        "en_US": "Clickzetta",
                        "zh_Hans": "Clickzetta"
                      },
                      "value": "clickzetta"
                    },
                    {
                      "label": {
                        "en_US": "Impala",
                        "zh_Hans": "Impala"
                      },
                      "value": "impala"
                    },
                    {
                      "label": {
                        "en_US": "DM8",
                        "zh_Hans": "DM8"
                      },
                      "value": "dameng"
                    },
                    {
                      "label": {
                        "en_US": "ArgoDB",
                        "zh_Hans": "ArgoDB"
                      },
                      "value": "argodb"
                    },
                    {
                      "label": {
                        "en_US": "Kudu",
                        "zh_Hans": "Kudu"
                      },
                      "value": "kudu"
                    },
                    {
                      "label": {
                        "en_US": "Elasticsearch",
                        "zh_Hans": "Elasticsearch"
                      },
                      "value": "elasticsearch"
                    },
                    {
                      "label": {
                        "en_US": "Mongodb",
                        "zh_Hans": "Mongodb"
                      },
                      "value": "mongodb"
                    },
                    {
                      "label": {
                        "en_US": "Prometheus",
                        "zh_Hans": "Prometheus"
                      },
                      "value": "prometheus"
                    },
                    {
                      "label": {
                        "en_US": "Hive",
                        "zh_Hans": "Hive"
                      },
                      "value": "hive"
                    },
                    {
                      "label": {
                        "en_US": "Delta-Lake",
                        "zh_Hans": "Delta-Lake"
                      },
                      "value": "delta_lake"
                    },
                    {
                      "label": {
                        "en_US": "Iceberg",
                        "zh_Hans": "Iceberg"
                      },
                      "value": "iceberg"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Host",
                    "zh_Hans": "Host地址"
                  },
                  "label": {
                    "en_US": "Host",
                    "zh_Hans": "Host地址"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "host",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Port",
                    "zh_Hans": "端口"
                  },
                  "label": {
                    "en_US": "Port",
                    "zh_Hans": "端口"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "port",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "DB user",
                    "zh_Hans": "数据库用户"
                  },
                  "label": {
                    "en_US": "DB user",
                    "zh_Hans": "数据库用户"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "user",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "DB Password",
                    "zh_Hans": "数据库密码"
                  },
                  "label": {
                    "en_US": "DB Password",
                    "zh_Hans": "数据库密码"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "password",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Database Name",
                    "zh_Hans": "数据库名"
                  },
                  "label": {
                    "en_US": "Database Name",
                    "zh_Hans": "数据库名"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "db",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "JDBC",
                    "zh_Hans": "JDBC"
                  },
                  "label": {
                    "en_US": "JDBC",
                    "zh_Hans": "JDBC"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "jdbc",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Schema Name",
                    "zh_Hans": "Schema Name"
                  },
                  "label": {
                    "en_US": "Schema",
                    "zh_Hans": "Schema"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "schema",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A natural language to SQL plugin based on FocusSearch keyword parsing, more accurate, faster, and cheaper!",
                  "zh_Hans": "一款基于FocusSearch关键词解析的自然语言转SQL插件，更准，更快，更便宜！"
                },
                "llm": "一款基于FocusSearch关键词解析的自然语言转SQL插件，更准，更快，更便宜！"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "joto",
                "label": {
                  "en_US": "FocusGPT",
                  "zh_Hans": "FocusGPT"
                },
                "name": "focus-gpt"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": "chinese",
                  "form": "llm",
                  "human_description": {
                    "en_US": "Language environment",
                    "zh_Hans": "语言环境"
                  },
                  "label": {
                    "en_US": "Language",
                    "zh_Hans": "语言环境"
                  },
                  "llm_description": "Language environment",
                  "max": null,
                  "min": null,
                  "name": "language",
                  "options": [
                    {
                      "label": {
                        "en_US": "Chinese",
                        "zh_Hans": "中文"
                      },
                      "value": "chinese"
                    },
                    {
                      "label": {
                        "en_US": "English",
                        "zh_Hans": "英文"
                      },
                      "value": "english"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Natural language input",
                    "zh_Hans": "输入的自然语言"
                  },
                  "label": {
                    "en_US": "Query string",
                    "zh_Hans": "查询语句"
                  },
                  "llm_description": "Natural language input",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Select the name of the data table that you want to query",
                    "zh_Hans": "选择要查询的数据表名"
                  },
                  "label": {
                    "en_US": "table",
                    "zh_Hans": "数据表"
                  },
                  "llm_description": "Select the name of the data table that you want to query",
                  "max": null,
                  "min": null,
                  "name": "tableName",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Session unique identifier, which is used by the plug-in to identify the current session and can be passed in sys.conversation_id",
                    "zh_Hans": "会话唯一标识，用于插件识别当前会话，可传入sys.conversation_id"
                  },
                  "label": {
                    "en_US": "Conversation Id",
                    "zh_Hans": "Conversation Id"
                  },
                  "llm_description": "Session unique identifier, which is used by the plug-in to identify the current session and can be passed in sys.conversation_id",
                  "max": null,
                  "min": null,
                  "name": "conversation_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "chat",
                  "form": "form",
                  "human_description": {
                    "en_US": "Action performed by plugins",
                    "zh_Hans": "插件执行的动作"
                  },
                  "label": {
                    "en_US": "action",
                    "zh_Hans": "执行行为"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "action",
                  "options": [
                    {
                      "label": {
                        "en_US": "get table list",
                        "zh_Hans": "获取数据表列表"
                      },
                      "value": "listTables"
                    },
                    {
                      "label": {
                        "en_US": "chat and get data",
                        "zh_Hans": "对话互动"
                      },
                      "value": "chat"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Select database type",
                    "zh_Hans": "选择要连接的数据库类型"
                  },
                  "label": {
                    "en_US": "Datasource Type",
                    "zh_Hans": "数据源类型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "type",
                  "options": [
                    {
                      "label": {
                        "en_US": "MySQL",
                        "zh_Hans": "MySQL"
                      },
                      "value": "mysql"
                    },
                    {
                      "label": {
                        "en_US": "PostgreSQL",
                        "zh_Hans": "PostgreSQL"
                      },
                      "value": "postgresql"
                    },
                    {
                      "label": {
                        "en_US": "SQLServer",
                        "zh_Hans": "SQLServer"
                      },
                      "value": "sqlserver"
                    },
                    {
                      "label": {
                        "en_US": "Oracle",
                        "zh_Hans": "Oracle"
                      },
                      "value": "oracle"
                    },
                    {
                      "label": {
                        "en_US": "IBMDB2",
                        "zh_Hans": "IBMDB2"
                      },
                      "value": "ibmdb2"
                    },
                    {
                      "label": {
                        "en_US": "GaussDB100",
                        "zh_Hans": "GaussDB100"
                      },
                      "value": "gaussdb100"
                    },
                    {
                      "label": {
                        "en_US": "Sybase",
                        "zh_Hans": "Sybase"
                      },
                      "value": "sybase"
                    },
                    {
                      "label": {
                        "en_US": "Greenplum",
                        "zh_Hans": "Greenplum"
                      },
                      "value": "greenplum"
                    },
                    {
                      "label": {
                        "en_US": "Clickhouse",
                        "zh_Hans": "Clickhouse"
                      },
                      "value": "clickhouse"
                    },
                    {
                      "label": {
                        "en_US": "Teradata",
                        "zh_Hans": "Teradata"
                      },
                      "value": "teradata"
                    },
                    {
                      "label": {
                        "en_US": "Doris",
                        "zh_Hans": "Doris"
                      },
                      "value": "doris"
                    },
                    {
                      "label": {
                        "en_US": "TIDB",
                        "zh_Hans": "TIDB"
                      },
                      "value": "tidb"
                    },
                    {
                      "label": {
                        "en_US": "Hana",
                        "zh_Hans": "Hana"
                      },
                      "value": "hana"
                    },
                    {
                      "label": {
                        "en_US": "Clickzetta",
                        "zh_Hans": "Clickzetta"
                      },
                      "value": "clickzetta"
                    },
                    {
                      "label": {
                        "en_US": "Impala",
                        "zh_Hans": "Impala"
                      },
                      "value": "impala"
                    },
                    {
                      "label": {
                        "en_US": "DM8",
                        "zh_Hans": "DM8"
                      },
                      "value": "dameng"
                    },
                    {
                      "label": {
                        "en_US": "ArgoDB",
                        "zh_Hans": "ArgoDB"
                      },
                      "value": "argodb"
                    },
                    {
                      "label": {
                        "en_US": "Kudu",
                        "zh_Hans": "Kudu"
                      },
                      "value": "kudu"
                    },
                    {
                      "label": {
                        "en_US": "Elasticsearch",
                        "zh_Hans": "Elasticsearch"
                      },
                      "value": "elasticsearch"
                    },
                    {
                      "label": {
                        "en_US": "Mongodb",
                        "zh_Hans": "Mongodb"
                      },
                      "value": "mongodb"
                    },
                    {
                      "label": {
                        "en_US": "Prometheus",
                        "zh_Hans": "Prometheus"
                      },
                      "value": "prometheus"
                    },
                    {
                      "label": {
                        "en_US": "Hive",
                        "zh_Hans": "Hive"
                      },
                      "value": "hive"
                    },
                    {
                      "label": {
                        "en_US": "Delta-Lake",
                        "zh_Hans": "Delta-Lake"
                      },
                      "value": "delta_lake"
                    },
                    {
                      "label": {
                        "en_US": "Iceberg",
                        "zh_Hans": "Iceberg"
                      },
                      "value": "iceberg"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Host",
                    "zh_Hans": "Host地址"
                  },
                  "label": {
                    "en_US": "Host",
                    "zh_Hans": "Host地址"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "host",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Port",
                    "zh_Hans": "端口"
                  },
                  "label": {
                    "en_US": "Port",
                    "zh_Hans": "端口"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "port",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "DB user",
                    "zh_Hans": "数据库用户"
                  },
                  "label": {
                    "en_US": "DB User",
                    "zh_Hans": "数据库用户"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "user",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "DB Password",
                    "zh_Hans": "数据库密码"
                  },
                  "label": {
                    "en_US": "DB Password",
                    "zh_Hans": "数据库密码"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "password",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Database Name",
                    "zh_Hans": "数据库名"
                  },
                  "label": {
                    "en_US": "Database Name",
                    "zh_Hans": "数据库名"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "db",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "JDBC",
                    "zh_Hans": "JDBC"
                  },
                  "label": {
                    "en_US": "JDBC",
                    "zh_Hans": "JDBC"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "jdbc",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Schema Name",
                    "zh_Hans": "Schema Name"
                  },
                  "label": {
                    "en_US": "Schema",
                    "zh_Hans": "Schema"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "schema",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-17T15:32:47Z",
        "version_updated_at": "2025-04-17T15:32:47Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Novita AI provides an LLM API that matches various application scenarios with high cost-effectiveness.",
          "zh_Hans": "适配多种海外应用场景的高性价比 LLM API"
        },
        "category": "model",
        "created_at": "2025-02-17T06:56:30Z",
        "endpoint": {},
        "icon": "langgenius/packages/novita/_assets/icon_s_en.svg",
        "index_id": "langgenius___novita",
        "install_count": 385,
        "introduction": "",
        "label": {
          "en_US": "Novita"
        },
        "latest_package_identifier": "langgenius/novita:0.0.4@a4c6a07d8ec9f91f2e27c6e68e88abb819023bfd108de829f40858ee45d99096",
        "latest_version": "0.0.4",
        "model": {
          "background": "#c7fce2",
          "configurate_methods": [
            "predefined-model"
          ],
          "description": {
            "en_US": "An LLM API that matches various application scenarios with high cost-effectiveness.",
            "zh_Hans": "适配多种海外应用场景的高性价比 LLM API"
          },
          "help": {
            "title": {
              "en_US": "Get your API key from Novita AI",
              "zh_Hans": "从 Novita AI 获取 API Key"
            },
            "url": {
              "en_US": "https://novita.ai/settings/key-management?utm_source=dify&utm_medium=ch&utm_campaign=api"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.svg"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "Novita AI"
          },
          "model_credential_schema": null,
          "models": [
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "L3 8B Stheno V3.2",
                "zh_Hans": "L3 8B Stheno V3.2"
              },
              "model": "Sao10K/L3-8B-Stheno-v3.2",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0005",
                "output": "0.0005",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Airoboros L2 70B",
                "zh_Hans": "Airoboros L2 70B"
              },
              "model": "jondurbin/airoboros-l2-70b",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.005",
                "output": "0.005",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "DeepSeek R1 Distill LLama 70B",
                "zh_Hans": "DeepSeek R1 Distill LLama 70B"
              },
              "model": "deepseek/deepseek-r1-distill-llama-70b",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.008",
                "output": "0.008",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "DeepSeek: DeepSeek R1 Distill Llama 8B",
                "zh_Hans": "DeepSeek: DeepSeek R1 Distill Llama 8B"
              },
              "model": "deepseek/deepseek-r1-distill-llama-8b",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0004",
                "output": "0.0004",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "DeepSeek: DeepSeek R1 Distill Qwen 14B",
                "zh_Hans": "DeepSeek: DeepSeek R1 Distill Qwen 14B"
              },
              "model": "deepseek/deepseek-r1-distill-qwen-14b",
              "model_properties": {
                "context_size": 64000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0015",
                "output": "0.0015",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "DeepSeek: DeepSeek R1 Distill Qwen 32B",
                "zh_Hans": "DeepSeek: DeepSeek R1 Distill Qwen 32B"
              },
              "model": "deepseek/deepseek-r1-distill-qwen-32b",
              "model_properties": {
                "context_size": 64000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.003",
                "output": "0.003",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "DeepSeek R1",
                "zh_Hans": "DeepSeek R1"
              },
              "model": "deepseek/deepseek-r1",
              "model_properties": {
                "context_size": 64000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.04",
                "output": "0.04",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "DeepSeek V3",
                "zh_Hans": "DeepSeek V3"
              },
              "model": "deepseek/deepseek_v3",
              "model_properties": {
                "context_size": 64000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0089",
                "output": "0.0089",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Dolphin Mixtral 8x22B",
                "zh_Hans": "Dolphin Mixtral 8x22B"
              },
              "model": "cognitivecomputations/dolphin-mixtral-8x22b",
              "model_properties": {
                "context_size": 16000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.009",
                "output": "0.009",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Gemma 2 9B",
                "zh_Hans": "Gemma 2 9B"
              },
              "model": "google/gemma-2-9b-it",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0008",
                "output": "0.0008",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Hermes 2 Pro Llama 3 8B",
                "zh_Hans": "Hermes 2 Pro Llama 3 8B"
              },
              "model": "nousresearch/hermes-2-pro-llama-3-8b",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0014",
                "output": "0.0014",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "L3 70B Euryale V2.1",
                "zh_Hans": "L3 70B Euryale V2.1"
              },
              "model": "sao10k/l3-70b-euryale-v2.1",
              "model_properties": {
                "context_size": 16000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0148",
                "output": "0.0148",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Sao10k L3 8B Lunaris",
                "zh_Hans": "Sao10k L3 8B Lunaris"
              },
              "model": "sao10k/l3-8b-lunaris",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0005",
                "output": "0.0005",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "L31 70B Euryale V2.2",
                "zh_Hans": "L31 70B Euryale V2.2"
              },
              "model": "sao10k/l31-70b-euryale-v2.2",
              "model_properties": {
                "context_size": 16000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0148",
                "output": "0.0148",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama3 70b Instruct",
                "zh_Hans": "Llama3 70b Instruct"
              },
              "model": "meta-llama/llama-3-70b-instruct",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0051",
                "output": "0.0074",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama 3 8B Instruct",
                "zh_Hans": "Llama 3 8B Instruct"
              },
              "model": "meta-llama/llama-3-8b-instruct",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0004",
                "output": "0.0004",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama 3.1 70B Instruct",
                "zh_Hans": "Llama 3.1 70B Instruct"
              },
              "model": "meta-llama/llama-3.1-70b-instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0034",
                "output": "0.0039",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama 3.1 8B Instruct BF16",
                "zh_Hans": "Llama 3.1 8B Instruct BF16"
              },
              "model": "meta-llama/llama-3.1-8b-instruct-bf16",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0006",
                "output": "0.0006",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama3.1 8B Instruct Max",
                "zh_Hans": "Llama3.1 8B Instruct Max"
              },
              "model": "meta-llama/llama-3.1-8b-instruct-max",
              "model_properties": {
                "context_size": 16384,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0005",
                "output": "0.0005",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama 3.1 8B Instruct",
                "zh_Hans": "Llama 3.1 8B Instruct"
              },
              "model": "meta-llama/llama-3.1-8b-instruct",
              "model_properties": {
                "context_size": 16384,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0005",
                "output": "0.0005",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama 3.2 11B Vision Instruct",
                "zh_Hans": "Llama 3.2 11B Vision Instruct"
              },
              "model": "meta-llama/llama-3.2-11b-vision-instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0006",
                "output": "0.0006",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama 3.2 1B Instruct",
                "zh_Hans": "Llama 3.2 1B Instruct"
              },
              "model": "meta-llama/llama-3.2-1b-instruct",
              "model_properties": {
                "context_size": 131000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0002",
                "output": "0.0002",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama 3.2 3B Instruct",
                "zh_Hans": "Llama 3.2 3B Instruct"
              },
              "model": "meta-llama/llama-3.2-3b-instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0003",
                "output": "0.0005",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama 3.3 70B Instruct",
                "zh_Hans": "Llama 3.3 70B Instruct"
              },
              "model": "meta-llama/llama-3.3-70b-instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0039",
                "output": "0.0039",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Midnight Rose 70B",
                "zh_Hans": "Midnight Rose 70B"
              },
              "model": "sophosympatheia/midnight-rose-70b",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.008",
                "output": "0.008",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Mistral 7B Instruct",
                "zh_Hans": "Mistral 7B Instruct"
              },
              "model": "mistralai/mistral-7b-instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.00059",
                "output": "0.00059",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Mistral Nemo",
                "zh_Hans": "Mistral Nemo"
              },
              "model": "mistralai/mistral-nemo",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0017",
                "output": "0.0017",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Mythomax L2 13B",
                "zh_Hans": "Mythomax L2 13B"
              },
              "model": "gryphe/mythomax-l2-13b",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0009",
                "output": "0.0009",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Nous Hermes Llama2 13B",
                "zh_Hans": "Nous Hermes Llama2 13B"
              },
              "model": "nousresearch/nous-hermes-llama2-13b",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0017",
                "output": "0.0017",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "OpenChat 7B",
                "zh_Hans": "OpenChat 7B"
              },
              "model": "openchat/openchat-7b",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0006",
                "output": "0.0006",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Openhermes2.5 Mistral 7B",
                "zh_Hans": "Openhermes2.5 Mistral 7B"
              },
              "model": "teknium/openhermes-2.5-mistral-7b",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0017",
                "output": "0.0017",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen 2 7B Instruct",
                "zh_Hans": "Qwen 2 7B Instruct"
              },
              "model": "qwen/qwen-2-7b-instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.00054",
                "output": "0.00054",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen 2 VL 72B Instruct",
                "zh_Hans": "Qwen 2 VL 72B Instruct"
              },
              "model": "qwen/qwen-2-vl-72b-instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0045",
                "output": "0.0045",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen 2.5 72B Instruct",
                "zh_Hans": "Qwen 2.5 72B Instruct"
              },
              "model": "qwen/qwen-2.5-72b-instruct",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0038",
                "output": "0.004",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Wizardlm 2 8x22B",
                "zh_Hans": "Wizardlm 2 8x22B"
              },
              "model": "microsoft/wizardlm-2-8x22b",
              "model_properties": {
                "context_size": 65535,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2048,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "frequency_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequency_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "presence_penalty"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presence_penalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0062",
                "output": "0.0062",
                "unit": "0.0001"
              }
            }
          ],
          "position": {},
          "provider": "novita",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              }
            ]
          },
          "supported_model_types": [
            "llm"
          ]
        },
        "name": "novita",
        "org": "langgenius",
        "plugin_id": "langgenius/novita",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/novita.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-07T04:51:25Z",
        "version_updated_at": "2025-04-07T04:51:25Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Visualizing structured data as charts",
          "ja_JP": "Visualizing structured data as charts",
          "pt_BR": "Visualizing structured data as charts",
          "zh_Hans": "Visualizing structured data as charts"
        },
        "category": "tool",
        "created_at": "2025-04-21T21:26:14Z",
        "endpoint": {},
        "icon": "jaguarliuu/packages/rookie_data_alchemy/_assets/analyze.svg",
        "index_id": "jaguarliuu___rookie_data_alchemy",
        "install_count": 375,
        "introduction": "## rookie_data_alchemy\n\n**Author:** jaguarliuu\n**Version:** 0.0.3-snapshot\n**Type:** tool\n\n### Description\n\nTransform JSON data into interactive charts effortlessly using AI. Supports all major ECharts visualization types with customizable styling.\n\n\n### Basic Usage\n\n1. ​**​Install from Marketplace​**​  \n   Visit your platform's plugin marketplace and search for \"rookie_data_alchemy\".  \n   Click ​**​Install​**​ to add the plugin to your dify.\n\n2. Launch the plugin after installation.\n\n3. Provide the following parameters:\n   - ​**​Data (JSON):​**​  \n     Your structured dataset in valid JSON format  \n     *Example:*  \n     ```json\n     {\n       \"categories\": [\"Mon\", \"Tue\", \"Wed\", \"Thu\", \"Fri\"],\n       \"values\": [120, 200, 150, 80, 70]\n     }\n     ```\n   - ​**​Chart Type:​**​  \n     Enter the ​**​Chinese name​**​ of your desired visualization (e.g. 柱状图, 折线图, 饼图)\n   - ​**​Custom Prompts (Optional):​**​  \n     Specify styling preferences:  \n     `\"Use blue theme with data labels\"`  \n     `\"Show horizontal bar chart with gradient fills\"`\n\n4. Click ​**​Start Execution​**​ to generate your chart\n\n## 📌 Parameter Details\n\n### 1. Data Requirements\n- Strictly formatted JSON\n- Supports nested structures for complex charts\n- Maximum file size: 5MB\n\n### 2. Supported Chart Types\n| Chinese Name | English Equivalent       |\n|--------------|--------------------------|\n| 柱状图        | Bar Chart                |\n| 折线图        | Line Chart               |\n| 饼图          | Pie Chart                |\n| 散点图        | Scatter Plot             |\n| 雷达图        | Radar Chart              |\n| 漏斗图        | Funnel Chart             |\n| *[Full list in documentation]* | |\n\n### 3. Custom Prompts\nUse natural language to request:\n- Color schemes\n- Component modifications\n- Layout adjustments\n- Animation preferences\n\n---\n\n## 🎯 Example Use Case\n\n​**​Input Parameters:​**​\n```json\nData:\n{\n  \"sales\": {\n    \"Q1\": 45000,\n    \"Q2\": 52000,\n    \"Q3\": 48000,\n    \"Q4\": 61000\n  }\n}\n\nChart Type: 饼图\n\nCustom Prompt: \"Show percentage values with goldenrod colors\"\n```\n\n**​Output:​​**\nInteractive pie chart with annotated percentages in goldenrod palette.",
        "label": {
          "en_US": "rookie_data_alchemy",
          "ja_JP": "rookie_data_alchemy",
          "pt_BR": "rookie_data_alchemy",
          "zh_Hans": "rookie_data_alchemy"
        },
        "latest_package_identifier": "jaguarliuu/rookie_data_alchemy:0.0.3-snapshot@cf591329396ef657087b68df43366a96304873c8bdc49056f3de6ad195cba258",
        "latest_version": "0.0.3-snapshot",
        "model": {},
        "name": "rookie_data_alchemy",
        "org": "jaguarliuu",
        "plugin_id": "jaguarliuu/rookie_data_alchemy",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/rookie_data_alchemy.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "jaguarliuu",
            "description": {
              "en_US": "Visualizing structured data as charts",
              "pt_BR": "Visualizing structured data as charts",
              "zh_Hans": "Visualizing structured data as charts"
            },
            "icon": "analyze.svg",
            "label": {
              "en_US": "rookie_data_alchemy",
              "pt_BR": "rookie_data_alchemy",
              "zh_Hans": "rookie_data_alchemy"
            },
            "name": "rookie_data_alchemy",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Visualizing structured data as charts",
                  "pt_BR": "Visualizing structured data as charts",
                  "zh_Hans": "Visualizing structured data as charts"
                },
                "llm": "Visualizing structured data as charts"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "jaguarliuu",
                "label": {
                  "en_US": "rookie_data_alchemy",
                  "pt_BR": "rookie_data_alchemy",
                  "zh_Hans": "rookie_data_alchemy"
                },
                "name": "rookie_data_alchemy"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "LLM model for rookie_data_alchemy.",
                    "pt_BR": "LLM model for rookie_data_alchemy.",
                    "zh_Hans": "LLM model for rookie_data_alchemy."
                  },
                  "label": {
                    "en_US": "Model",
                    "pt_BR": "Model",
                    "zh_Hans": "模型"
                  },
                  "llm_description": "LLM model for text2data.",
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": "llm",
                  "template": null,
                  "type": "model-selector"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "wait for data",
                    "pt_BR": "wait for data",
                    "zh_Hans": "待处理的数据，需要标准json格式"
                  },
                  "label": {
                    "en_US": "data",
                    "pt_BR": "data",
                    "zh_Hans": "待处理的数据，需要标准json格式"
                  },
                  "llm_description": "wait for data",
                  "max": null,
                  "min": null,
                  "name": "data",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "csv data",
                    "pt_BR": "csv data",
                    "zh_Hans": "csv数据"
                  },
                  "label": {
                    "en_US": "csv data",
                    "pt_BR": "csv data",
                    "zh_Hans": "csv数据"
                  },
                  "llm_description": "csv data",
                  "max": null,
                  "min": null,
                  "name": "csv_data",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "file"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "chart type",
                    "pt_BR": "chart type",
                    "zh_Hans": "图表类型"
                  },
                  "label": {
                    "en_US": "chart type",
                    "pt_BR": "chart type",
                    "zh_Hans": "图表类型"
                  },
                  "llm_description": "chart type",
                  "max": null,
                  "min": null,
                  "name": "chart_type",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "custom requirements",
                    "pt_BR": "custom requirements",
                    "zh_Hans": "自定义需求"
                  },
                  "label": {
                    "en_US": "custom requirements",
                    "pt_BR": "custom requirements",
                    "zh_Hans": "自定义需求"
                  },
                  "llm_description": "custom requirements",
                  "max": null,
                  "min": null,
                  "name": "custom_requirements",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-23T01:38:37Z",
        "version_updated_at": "2025-04-23T01:38:37Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Dify integration for mem0",
          "ja_JP": "mem0のDify統合",
          "pt_BR": "Integração Dify para mem0",
          "zh_Hans": "mem0 的 Dify 集成"
        },
        "category": "tool",
        "created_at": "2025-02-26T09:33:49Z",
        "endpoint": {},
        "icon": "yevanchen/packages/mem0/_assets/mem0.png",
        "index_id": "yevanchen___mem0",
        "install_count": 365,
        "introduction": "## mem0\n\n**Author:** yevanchen\n**Version:** 0.0.1\n**Type:** tool\n\n### Description\n\nmem0 is a memory management plugin that enables conversation history storage and retrieval for LLM applications.\n\n![workflow](./_assets/workflow.png)\n\n\n\n### Setup\n\n1. Get your API key from [mem0 dashboard](https://app.mem0.ai/dashboard/api-keys)\n2. Install the package:\n```bash\npip install mem0ai\n```\n\n3. Initialize the client:\n```python\nfrom mem0 import MemoryClient\nclient = MemoryClient(api_key=\"your-api-key\")\n```\n\n![dashboard](./_assets/dashboard.png)\n\n### Memory Actions\n\n#### add_memory\nStores conversation history and context for users.\n\n```python\nmessages = [\n    {\"role\": \"user\", \"content\": \"Hi, I'm Alex. I'm a vegetarian and I'm allergic to nuts.\"},\n    {\"role\": \"assistant\", \"content\": \"Hello Alex! I've noted your dietary preferences.\"}\n]\nclient.add(messages, user_id=\"alex\")\n```\n\nBackend logic:\n- Messages are stored in user-specific partitions using `user_id`\n- Supports conversation history and context storage\n- Handles message format validation and processing\n- Optimizes storage for efficient retrieval\n\n#### retrieve_memory\nRetrieves relevant conversation history based on queries.\n\n```python\nquery = \"What can I cook for dinner tonight?\"\nmemories = client.search(query, user_id=\"alex\")\n```\n\nBackend logic:\n- Semantic search across user's memory partition\n- Returns relevant conversation snippets\n- Handles context ranking and relevance scoring\n- Optimizes query performance\n\n### Usage in Dify\n\n1. In Dify workflows, place `retrieve_memory` before LLM calls to provide context\n2. Add `add_memory` after LLM responses to store new interactions\n3. `user_id` can be customized in workflow run API\n4. Note: iframe and webapp modes currently don't support user_id due to lack of access control\n\n### Maybe Future Features\n- Multimodal Support\n- Memory Customization\n- Custom Categories & Instructions\n- Direct Import\n- Async Client\n- Memory Export\n- Webhooks\n- Graph Memory\n- REST API Server\n- OpenAI Compatibility\n- Custom Prompts\n\nFor feature requests or discussions, contact evanchen@dify.ai\n\n",
        "label": {
          "en_US": "mem0",
          "ja_JP": "mem0",
          "pt_BR": "mem0",
          "zh_Hans": "mem0"
        },
        "latest_package_identifier": "yevanchen/mem0:0.0.2@6d85c46b80b7944cce5625cee7946228346dd15718646ae90d6bf179d8925d60",
        "latest_version": "0.0.2",
        "model": {},
        "name": "mem0",
        "org": "yevanchen",
        "plugin_id": "yevanchen/mem0",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/mem0.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "Mem0 API key",
                "pt_BR": "Mem0 API key",
                "zh_Hans": "Mem0 API Key"
              },
              "name": "mem0_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Mem0 API key",
                "pt_BR": "Please input your Mem0 API key",
                "zh_Hans": "请输入你的 Mem0 API Key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://app.mem0.ai/dashboard/api-keys"
            }
          ],
          "identity": {
            "author": "yevanchen",
            "description": {
              "en_US": "mem0",
              "pt_BR": "mem0",
              "zh_Hans": "mem0"
            },
            "icon": "mem0.png",
            "label": {
              "en_US": "mem0",
              "pt_BR": "mem0",
              "zh_Hans": "mem0"
            },
            "name": "mem0ai",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Add memory support",
                  "pt_BR": "Adicionar suporte à memória",
                  "zh_Hans": "添加内存支持"
                },
                "llm": "Add memory support"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "yevanchen",
                "label": {
                  "en_US": "Add Memory",
                  "pt_BR": "Adicionar Memória",
                  "zh_Hans": "添加内存"
                },
                "name": "add_mem0ai_memory"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The message from the user in the conversation.",
                    "pt_BR": "A mensagem do usuário na conversa.",
                    "zh_Hans": "对话中的用户消息。"
                  },
                  "label": {
                    "en_US": "User Message",
                    "pt_BR": "Mensagem do Usuário",
                    "zh_Hans": "用户消息"
                  },
                  "llm_description": "The message from the user in the conversation.",
                  "max": null,
                  "min": null,
                  "name": "user",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The response from the assistant in the conversation.",
                    "pt_BR": "A resposta do assistente na conversa.",
                    "zh_Hans": "对话中的助手回应。"
                  },
                  "label": {
                    "en_US": "Assistant Response",
                    "pt_BR": "Resposta do Assistente",
                    "zh_Hans": "助手回应"
                  },
                  "llm_description": "The response from the assistant in the conversation.",
                  "max": null,
                  "min": null,
                  "name": "assistant",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "User ID",
                    "pt_BR": "ID do Usuário",
                    "zh_Hans": "用户ID"
                  },
                  "label": {
                    "en_US": "User ID",
                    "pt_BR": "ID do Usuário",
                    "zh_Hans": "用户ID"
                  },
                  "llm_description": "User ID",
                  "max": null,
                  "min": null,
                  "name": "user_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Search and retrieve memory",
                  "pt_BR": "Pesquisar e recuperar memória",
                  "zh_Hans": "搜索和检索内存"
                },
                "llm": "Search and retrieve memory"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "yevanchen",
                "label": {
                  "en_US": "Retrieve Memory",
                  "pt_BR": "Recuperar Memória",
                  "zh_Hans": "检索内存"
                },
                "name": "retrieve_mem0ai_memory"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The query string is used to search for specific memories within the system. It can be a keyword, phrase, or sentence that describes the memory you're looking for.",
                    "pt_BR": "A string de consulta é usada para buscar memórias específicas dentro do sistema. Ela pode ser uma palavra-chave, frase ou sentença que descreve a memória que você está procurando.",
                    "zh_Hans": "查询语句用于在系统中搜索特定的记忆。它可以是一个关键词、短语或描述你正在寻找的记忆的句子。"
                  },
                  "label": {
                    "en_US": "Query string",
                    "pt_BR": "Query string",
                    "zh_Hans": "查询语句"
                  },
                  "llm_description": "The query string is used to search for specific memories within the system. It can be a keyword, phrase, or sentence that describes the memory you're looking for.",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "User ID",
                    "pt_BR": "ID do Usuário",
                    "zh_Hans": "用户ID"
                  },
                  "label": {
                    "en_US": "User ID",
                    "pt_BR": "ID do Usuário",
                    "zh_Hans": "用户ID"
                  },
                  "llm_description": "User ID",
                  "max": null,
                  "min": null,
                  "name": "user_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-04T14:29:58Z",
        "version_updated_at": "2025-03-04T14:29:58Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "AList is a file listing program that supports multiple storage providers including Dropbox, Alibaba Cloud Disk, OneDrive, Google Drive, etc., and is easy to expand.",
          "ja_JP": "AList is a file listing program that supports multiple storage providers including Dropbox, Alibaba Cloud Disk, OneDrive, Google Drive, etc., and is easy to expand.",
          "pt_BR": "AList is a file listing program that supports multiple storage providers including Dropbox, Alibaba Cloud Disk, OneDrive, Google Drive, etc., and is easy to expand.",
          "zh_Hans": "AList是一个文件列表程序，支持包括Dropbox、阿里云盘、OneDrive、Google Drive等多种存储提供商，并且易于扩展"
        },
        "category": "tool",
        "created_at": "2025-03-19T19:00:26Z",
        "endpoint": {},
        "icon": "kurolz/packages/alist/_assets/icon.svg",
        "index_id": "kurolz___alist",
        "install_count": 360,
        "introduction": "## alist\n\n**Author:** kurolz\n**Version:** 0.0.1\n**Type:** tool\n\n### Description\n\nAList is the popular github project that has 46.8k star. AList is a file listing program that supports multiple storage providers including Dropbox, Alibaba Cloud Disk, OneDrive, Google Drive, etc., and is easy to expand. This plugin provides operations for querying file lists, writing file contents, and deleting files for Alist\n\n### Configuration\n\n1. You need to Install alist and configure alist storage, please refer to the [AList Installation Documentation](https://alist.nn.ci/guide/install/script.html).\n\n2. In the authorization settings interface, enter the AList base URL and save them.\n![img.png](img.png)\n\n3. Now you can freely use the tool.",
        "label": {
          "en_US": "alist",
          "ja_JP": "alist",
          "pt_BR": "alist",
          "zh_Hans": "alist"
        },
        "latest_package_identifier": "kurolz/alist:0.0.1@d414b25ffb0fdcc99c3559d73604e1e838767de16fc940c2402c68bb9e489765",
        "latest_version": "0.0.1",
        "model": {},
        "name": "alist",
        "org": "kurolz",
        "plugin_id": "kurolz/alist",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/alist.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "AList base URL",
                "pt_BR": "AList base URL",
                "zh_Hans": "AList base URL"
              },
              "name": "alist_base_url",
              "options": null,
              "placeholder": {
                "en_US": "Please input your AList base URL",
                "pt_BR": "Please input your AList base URL",
                "zh_Hans": "请输入您的 AList base URL"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            }
          ],
          "identity": {
            "author": "kurolz",
            "description": {
              "en_US": "AList is a file listing program that supports multiple storage providers including Dropbox, Alibaba Cloud Disk, OneDrive, Google Drive, etc., and is easy to expand.",
              "pt_BR": "AList is a file listing program that supports multiple storage providers including Dropbox, Alibaba Cloud Disk, OneDrive, Google Drive, etc., and is easy to expand.",
              "zh_Hans": "AList是一个文件列表程序，支持包括Dropbox、阿里云盘、OneDrive、Google Drive等多种存储提供商，并且易于扩展"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "alist",
              "pt_BR": "alist",
              "zh_Hans": "alist"
            },
            "name": "alist",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "List alist file or directory",
                  "pt_BR": "List alist file or directory",
                  "zh_Hans": "获取AList所有文件或目录并分页返回"
                },
                "llm": "A tool to get all file or directory of AList"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "iceyao",
                "label": {
                  "en_US": "List alist file or directory",
                  "pt_BR": "List alist file or directory",
                  "zh_Hans": "获取AList文件或目录"
                },
                "name": "list_file"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The username of AList",
                    "pt_BR": "The username of AList",
                    "zh_Hans": "AList用户名"
                  },
                  "label": {
                    "en_US": "username",
                    "pt_BR": "username",
                    "zh_Hans": "AList用户名"
                  },
                  "llm_description": "AList用户名，用于获取AList token",
                  "max": null,
                  "min": null,
                  "name": "username",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The user password of AList",
                    "pt_BR": "The user password of AList",
                    "zh_Hans": "AList用户密码"
                  },
                  "label": {
                    "en_US": "password",
                    "pt_BR": "password",
                    "zh_Hans": "AList用户密码"
                  },
                  "llm_description": "AList用户密码，用于获取AList token",
                  "max": null,
                  "min": null,
                  "name": "password",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The directory of AList",
                    "pt_BR": "The directory of AList",
                    "zh_Hans": "AList目录路径"
                  },
                  "label": {
                    "en_US": "path",
                    "pt_BR": "path",
                    "zh_Hans": "AList目录路径"
                  },
                  "llm_description": "AList目录路径，用于获取文件列表",
                  "max": null,
                  "min": null,
                  "name": "path",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 1,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Paging number, the default value is 1.",
                    "pt_BR": "Paging number, the default value is 1.",
                    "zh_Hans": "页数, 默认值为第1页。"
                  },
                  "label": {
                    "en_US": "page",
                    "pt_BR": "page",
                    "zh_Hans": "页数"
                  },
                  "llm_description": "页数, 表示获取第几页的的数据，默认值为1。",
                  "max": null,
                  "min": 1,
                  "name": "page",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 500,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Paging size, the default and maximum value is 500.",
                    "pt_BR": "Paging size, the default and maximum value is 500.",
                    "zh_Hans": "分页大小, 默认值和最大值为 500。"
                  },
                  "label": {
                    "en_US": "page_size",
                    "pt_BR": "page_size",
                    "zh_Hans": "分页大小"
                  },
                  "llm_description": "分页大小, 表示一次请求最多返回多少条数据，默认值和最大值为500。",
                  "max": 500,
                  "min": 1,
                  "name": "page_size",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Remove alist file",
                  "pt_BR": "Remove alist file",
                  "zh_Hans": "删除AList文件"
                },
                "llm": "A tool to remove alist file"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "iceyao",
                "label": {
                  "en_US": "Remove alist file",
                  "pt_BR": "Remove alist file",
                  "zh_Hans": "删除AList文件"
                },
                "name": "remove_file"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The username of AList",
                    "pt_BR": "The username of AList",
                    "zh_Hans": "AList用户名"
                  },
                  "label": {
                    "en_US": "username",
                    "pt_BR": "username",
                    "zh_Hans": "AList用户名"
                  },
                  "llm_description": "AList用户名，用于获取AList token",
                  "max": null,
                  "min": null,
                  "name": "username",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The user password of AList",
                    "pt_BR": "The user password of AList",
                    "zh_Hans": "AList用户密码"
                  },
                  "label": {
                    "en_US": "password",
                    "pt_BR": "password",
                    "zh_Hans": "AList用户密码"
                  },
                  "llm_description": "AList用户密码，用于获取AList token",
                  "max": null,
                  "min": null,
                  "name": "password",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The file path of AList",
                    "pt_BR": "The file path of AList",
                    "zh_Hans": "AList文件路径，文件的唯一标识"
                  },
                  "label": {
                    "en_US": "path",
                    "pt_BR": "path",
                    "zh_Hans": "AList文件路径"
                  },
                  "llm_description": "AList文件路径，文件的唯一标识",
                  "max": null,
                  "min": null,
                  "name": "path",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Adding new content to AList file",
                  "pt_BR": "Adding new content to AList file",
                  "zh_Hans": "写内容保存到AList文件"
                },
                "llm": "A tool for adding new content to alist file."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "iceyao",
                "label": {
                  "en_US": "Write alist file",
                  "pt_BR": "Write alist file",
                  "zh_Hans": "写内容到AList文件"
                },
                "name": "write_file"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The username of AList",
                    "pt_BR": "The username of AList",
                    "zh_Hans": "AList用户名"
                  },
                  "label": {
                    "en_US": "username",
                    "pt_BR": "username",
                    "zh_Hans": "AList用户名"
                  },
                  "llm_description": "AList用户名，用于获取AList token",
                  "max": null,
                  "min": null,
                  "name": "username",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The user password of AList",
                    "pt_BR": "The user password of AList",
                    "zh_Hans": "AList用户密码"
                  },
                  "label": {
                    "en_US": "password",
                    "pt_BR": "password",
                    "zh_Hans": "AList用户密码"
                  },
                  "llm_description": "AList用户密码，用于获取AList token",
                  "max": null,
                  "min": null,
                  "name": "password",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The path of AList",
                    "pt_BR": "The path of AList",
                    "zh_Hans": "AList文件路径，文件的唯一标识"
                  },
                  "label": {
                    "en_US": "path",
                    "pt_BR": "path",
                    "zh_Hans": "AList文件路径"
                  },
                  "llm_description": "AList文件路径，文件的唯一标识",
                  "max": null,
                  "min": null,
                  "name": "path",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "File content, supports markdown syntax, can be empty.",
                    "pt_BR": "File content, supports markdown syntax, can be empty.",
                    "zh_Hans": "文件内容，支持markdown语法，可以为空。"
                  },
                  "label": {
                    "en_US": "file content",
                    "pt_BR": "file content",
                    "zh_Hans": "文件内容"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-19T19:00:32Z",
        "version_updated_at": "2025-03-19T19:00:32Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Welcome to Financial Datasets, a developer-friendly stock market API.",
          "pt_BR": "Bem-vindo ao Financial Datasets, uma API de mercado de ações amigável para desenvolvedores.",
          "zh_Hans": "欢迎使用金融数据集，这是一个开发人员友好的股票市场 API。"
        },
        "category": "tool",
        "created_at": "2025-03-17T12:20:03Z",
        "endpoint": {},
        "icon": "financialai/packages/financialdatasets/_assets/favicon.ico",
        "index_id": "financialai___financialdatasets",
        "install_count": 358,
        "introduction": "# Dify Plugin: FinancialDatasets.ai - Access Powerful Financial Data\n\n[![Dify Plugin](https://img.shields.io/badge/Dify-Plugin-blueviolet)](https://dify.ai)\n[![FinancialDatasets.ai](https://img.shields.io/badge/FinancialDatasets.ai-API-brightgreen)](https://financialdatasets.ai)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n![GitHub Release](https://img.shields.io/github/v/release/FinancialAI/dify-plugin-financial-datasets)\n\n## Overview\n\nThis Dify plugin empowers your AI applications with seamless access to the vast and reliable financial data provided by [FinancialDatasets.ai](https://financialdatasets.ai). FinancialDatasets.ai offers a comprehensive API for retrieving real-time and historical financial data across various asset classes, including stocks, cryptocurrencies, and more.\n\n**With this plugin, you can:**\n\n- **Enrich your Dify applications with real-time market data.**\n- **Analyze historical trends and patterns using historical financial data.**\n- **Build sophisticated financial analysis tools and dashboards within Dify.**\n- **Integrate financial insights into your conversational AI agents and workflows.**\n\nThis plugin acts as a bridge, allowing you to leverage the power of FinancialDatasets.ai's API directly within the Dify platform, simplifying the process of data integration and empowering you to build data-driven AI solutions for finance.\n\n**Visit the official [FinancialDatasets.ai documentation](https://docs.financialdatasets.ai/) to explore the full capabilities of their API.**\n\n## Configuration\n\nBefore using this plugin, you'll need to configure it with your FinancialDatasets.ai API key. Here's how:\n\n1. **Sign up for a FinancialDatasets.ai account:** If you don't already have one, create an account at [https://financialdatasets.ai](https://financialdatasets.ai).\n2. **Obtain your API Key:** Log in to your FinancialDatasets.ai dashboard and locate your API key. This is usually found in your account settings or API documentation section.\n3. **Configure the Dify Plugin:**\n   - In your Dify project, navigate to the \"Plugins\" section.\n   - Find and enable the \"FinancialDatasets.ai\" plugin.\n   - In the plugin configuration settings, you will find a field to enter your **FinancialDatasets.ai API Key**.\n   - Paste your API key into the designated field.\n   - **Save the plugin configuration.**\n\n**Important:** Keep your API key secure and do not expose it in public code repositories.\n\n<div align=\"center\">\n    <img src=\"_assets/plugin_configuration.png\" alt=\"Plugin Configuration\" width=\"95%\"/>\n</div>\n\n## Tool Features\n\nThis plugin exposes the following tools, allowing you to access specific functionalities of the FinancialDatasets.ai API within Dify. The specific tools available depend on the capabilities of the FinancialDatasets.ai API. Please refer to the [FinancialDatasets.ai documentation](https://docs.financialdatasets.ai/) for a complete list of endpoints and data available.\n\n- **Company Facts**: Get company facts for a ticker. Company facts includes data like name, CIK, market cap, total employees, website URL, and more.\n- **Crypto Prices**: Get ranged price data for a cryptocurrency to power price charts and analyze price movements.\n- **Crypto Snapshot**: Get the real-time price snapshot for a cryptocurrency.\n- **Earnings Press Releases**: Get earnings press releases for a ticker. The data returned from the API includes the URL, publish date, and full text of the press release.\n- **Historical Financial Metrics**: Get financial metrics for a ticker, including valuation, profitability, efficiency, liquidity, leverage, growth, and per share metrics.\n- **Financial Metrics Snapshot**: Get a real-time snapshot of key financial metrics and ratios for a ticker, including valuation, profitability, efficiency, liquidity, leverage, growth, and per share metrics.\n- **Financial Statements**: Get all financial statements for a ticker, including income statements, balance sheets, and cash flow statements.\n- **Insider Trades**: Get insider trades like buys and sells for a ticker by a company insider such as a CEO, CFO, or Director.\n- **Institutional Ownership**: Get institutional ownership by investor or ticker. This quarterly data comes directly from Form 13F filings and includes tickers, share quantities, estimated holding prices, and market values.\n- **Company News**: Get real-time and historical news for a ticker.\n- **Stock Prices**: Get ranged price data for a ticker to power stock charts and analyze price movements.\n- **Stock Snapshot**: Get the real-time price snapshot for a ticker.\n- **SEC Filings**: Get SEC filings for a company. This includes 10-Ks, 10-Qs, 8-Ks, and more.\n- **SEC Filing Items**: Get SEC filing items for a company. The Items endpoint allows you to extract specific sections (called items) from a given 10-K or 10-Q filing.\n\n**Important:** When using these tools in Dify, ensure you provide the correct parameters. Refer to the FinancialDatasets.ai API documentation for accurate parameter names and data formats.\n\n## Use Cases\n\nHere are some examples of how you can utilize this FinancialDatasets.ai plugin in your Dify applications:\n\n- **Financial Dashboard Assistant:** Build a Dify application that can answer user queries about current stock prices, historical trends, and market news, creating a personalized financial dashboard experience.\n- **Automated Financial Reporting:** Create workflows that automatically fetch financial data using this plugin and generate reports for portfolio performance, market analysis, or investment insights.\n- **AI-Powered Trading Bot (Informational):** Integrate real-time market data into a Dify-powered AI agent that can provide users with trading signals, market analysis, and risk assessments (Note: This plugin focuses on data retrieval and does not execute trades).\n- **Financial News Summarization:** Combine this plugin with other Dify tools (like text summarization models) to fetch financial news headlines and provide concise summaries to users.\n- **Educational Financial Applications:** Develop interactive educational applications that use real-world financial data to teach users about investing, market dynamics, and financial analysis concepts.\n- **Personalized Financial Alerts:** Set up Dify workflows that monitor specific financial instruments and trigger alerts based on price movements or other data points retrieved via this plugin.\n\n**Example Dify Chatflow Scenario:**\n\n1. **User Input:** User asks \"What is the current price of Bitcoin (ticker: BTC-USD)?\"\n2. **Dify Orchestration:** Dify identifies the intent and routes the request to the \"Crypto Snapshot\" tool from the FinancialDatasets.ai plugin.\n3. **Plugin Execution:** The plugin uses the `symbol: BTC-USD` parameter to call the FinancialDatasets.ai API.\n4. **API Response:** FinancialDatasets.ai API returns the real-time price of Bitcoin.\n5. **Dify Output:** Dify presents the retrieved Bitcoin price to the user in a user-friendly format.\n\n<div align=\"center\">\n    <img src=\"_assets/tool_call_example.png\" alt=\"Dify Chatflow\" width=\"95%\"/>\n</div>\n\n## Further Information\n\n- **FinancialDatasets.ai Documentation:** [https://docs.financialdatasets.ai/](https://docs.financialdatasets.ai/) - Refer to the official API documentation for detailed information about available endpoints, data formats, rate limits, and more.\n- **Dify Platform:** [https://dify.ai](https://dify.ai) - Learn more about the Dify platform and its capabilities for building AI applications.\n\n## License\n\nThis Dify plugin is released under the [MIT License](LICENSE).\n\n---\n\n**Disclaimer:** This plugin provides access to financial data from FinancialDatasets.ai. Please be aware of the terms of service and data usage policies of FinancialDatasets.ai. Financial data is for informational purposes only and should not be considered financial advice. Always consult with a qualified financial advisor before making any investment decisions.\n",
        "label": {
          "en_US": "FinancialDatasets.ai",
          "pt_BR": "FinancialDatasets.ai",
          "zh_Hans": "FinancialDatasets.ai"
        },
        "latest_package_identifier": "financialai/financialdatasets:1.0.0@ef57edf1e0710845780d6f9eb13aea8be4de58161d6f33762286486bce4f4ef7",
        "latest_version": "1.0.0",
        "model": {},
        "name": "financialdatasets",
        "org": "financialai",
        "plugin_id": "financialai/financialdatasets",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/financialdatasets.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Get your Financial Datasets API key from financialdatasets.ai",
                "pt_BR": "Obtenha sua chave da API do Financial Datasets em financialdatasets.ai",
                "zh_Hans": "从 financialdatasets.ai 获取您的金融数据集 API 密钥"
              },
              "label": {
                "en_US": "Financial Datasets API key",
                "pt_BR": "Chave da API do Financial Datasets",
                "zh_Hans": "金融数据集 API 密钥"
              },
              "name": "financial_datasets_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Financial Datasets API key",
                "pt_BR": "Por favor, insira sua chave da API do Financial Datasets",
                "zh_Hans": "请输入您的金融数据集 API 密钥"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://www.financialdatasets.ai"
            }
          ],
          "identity": {
            "author": "financialai",
            "description": {
              "en_US": "Welcome to Financial Datasets, a developer-friendly stock market API.",
              "pt_BR": "Bem-vindo ao Financial Datasets, uma API de mercado de ações amigável para desenvolvedores.",
              "zh_Hans": "欢迎使用金融数据集，这是一个开发人员友好的股票市场 API。"
            },
            "icon": "favicon.ico",
            "label": {
              "en_US": "FinancialDatasets.ai",
              "pt_BR": "FinancialDatasets.ai",
              "zh_Hans": "FinancialDatasets.ai"
            },
            "name": "financialdatasets",
            "tags": [
              "finance"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Get company facts for a ticker. Company facts includes data like name, CIK, market cap, total employees, website URL, and more.",
                  "pt_BR": "Obtenha informações da empresa para um ticker. As informações da empresa incluem dados como nome, CIK, valor de mercado, total de funcionários, URL do site e muito mais.",
                  "zh_Hans": "获取股票代码的公司信息。公司信息包括名称、CIK、市值、员工总数、网站网址等数据。"
                },
                "llm": "Get company facts for a ticker. Company facts includes data like name, CIK, market cap, total employees, website URL, and more."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "financialai",
                "label": {
                  "en_US": "Company Facts",
                  "pt_BR": "Dados da Empresa",
                  "zh_Hans": "公司概况"
                },
                "name": "company_facts"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ticker symbol of the company you want to get facts for.",
                    "pt_BR": "O símbolo do ticker da empresa para a qual você deseja obter informações.",
                    "zh_Hans": "您想获取公司信息的公司的股票代码。"
                  },
                  "label": {
                    "en_US": "Ticker symbol",
                    "pt_BR": "Símbolo do ticker",
                    "zh_Hans": "股票代码"
                  },
                  "llm_description": "The ticker symbol of the company you want to get facts for.",
                  "max": null,
                  "min": null,
                  "name": "ticker",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get ranged price data for a cryptocurrency to power price charts and analyze price movements.",
                  "pt_BR": "Obtenha dados de preço variados para uma criptomoeda para alimentar gráficos de preços e analisar movimentos de preços.",
                  "zh_Hans": "获取加密货币的价格范围数据，以支持价格图表和分析价格走势。"
                },
                "llm": "Get ranged price data for a cryptocurrency to power price charts and analyze price movements."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "financialai",
                "label": {
                  "en_US": "Crypto Prices",
                  "pt_BR": "Preços de Criptomoedas",
                  "zh_Hans": "加密货币价格"
                },
                "name": "crypto_prices"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ticker symbol of the cryptocurrency you want to get price data for.",
                    "pt_BR": "O símbolo do ticker da criptomoeda para a qual você deseja obter dados de preço.",
                    "zh_Hans": "您想获取价格数据的加密货币的股票代码。"
                  },
                  "label": {
                    "en_US": "Ticker symbol",
                    "pt_BR": "Símbolo do ticker da criptomoeda",
                    "zh_Hans": "加密货币代码"
                  },
                  "llm_description": "The ticker symbol of the cryptocurrency you want to get price data for.",
                  "max": null,
                  "min": null,
                  "name": "ticker",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The time interval for the price data.",
                    "pt_BR": "O intervalo de tempo para os dados de preço.",
                    "zh_Hans": "价格数据的时间间隔。"
                  },
                  "label": {
                    "en_US": "Time interval",
                    "pt_BR": "Intervalo de tempo",
                    "zh_Hans": "时间间隔"
                  },
                  "llm_description": "The time interval for the price data.",
                  "max": null,
                  "min": null,
                  "name": "interval",
                  "options": [
                    {
                      "label": {
                        "en_US": "Minute",
                        "pt_BR": "Minuto",
                        "zh_Hans": "分钟"
                      },
                      "value": "minute"
                    },
                    {
                      "label": {
                        "en_US": "Day",
                        "pt_BR": "Dia",
                        "zh_Hans": "天"
                      },
                      "value": "day"
                    },
                    {
                      "label": {
                        "en_US": "Week",
                        "pt_BR": "Semana",
                        "zh_Hans": "周"
                      },
                      "value": "week"
                    },
                    {
                      "label": {
                        "en_US": "Month",
                        "pt_BR": "Mês",
                        "zh_Hans": "月"
                      },
                      "value": "month"
                    },
                    {
                      "label": {
                        "en_US": "Year",
                        "pt_BR": "Ano",
                        "zh_Hans": "年"
                      },
                      "value": "year"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 1,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The multiplier for the time interval.",
                    "pt_BR": "O multiplicador para o intervalo de tempo.",
                    "zh_Hans": "时间间隔的倍增器。"
                  },
                  "label": {
                    "en_US": "Interval multiplier",
                    "pt_BR": "Multiplicador de intervalo",
                    "zh_Hans": "时间间隔倍增器"
                  },
                  "llm_description": "The multiplier for the time interval.",
                  "max": null,
                  "min": 1,
                  "name": "interval_multiplier",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The start date for the price data (format: YYYY-MM-DD).",
                    "pt_BR": "A data de início para os dados de preço (formato: AAAA-MM-DD).",
                    "zh_Hans": "价格数据的开始日期（格式：YYYY-MM-DD）。"
                  },
                  "label": {
                    "en_US": "Start date (YYYY-MM-DD)",
                    "pt_BR": "Data de início (AAAA-MM-DD)",
                    "zh_Hans": "开始日期 (YYYY-MM-DD)"
                  },
                  "llm_description": "The start date for the price data (format: YYYY-MM-DD).",
                  "max": null,
                  "min": null,
                  "name": "start_date",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The end date for the price data (format: YYYY-MM-DD).",
                    "pt_BR": "A data final para os dados de preço (formato: AAAA-MM-DD).",
                    "zh_Hans": "价格数据的结束日期（格式：YYYY-MM-DD）。"
                  },
                  "label": {
                    "en_US": "End date (YYYY-MM-DD)",
                    "pt_BR": "Data final (AAAA-MM-DD)",
                    "zh_Hans": "结束日期 (YYYY-MM-DD)"
                  },
                  "llm_description": "The end date for the price data (format: YYYY-MM-DD).",
                  "max": null,
                  "min": null,
                  "name": "end_date",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 5000,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The maximum number of price records to return (default: 5000, max: 5000).",
                    "pt_BR": "O número máximo de registros de preço a serem retornados (padrão: 5000, máximo: 5000).",
                    "zh_Hans": "要返回的价格记录的最大数量（默认值：5000，最大值：5000）。"
                  },
                  "label": {
                    "en_US": "Limit",
                    "pt_BR": "Limite",
                    "zh_Hans": "限制"
                  },
                  "llm_description": "The maximum number of price records to return (default: 5000, max: 5000).",
                  "max": 5000,
                  "min": 1,
                  "name": "limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get the real-time price snapshot for a cryptocurrency.",
                  "pt_BR": "Obtenha o instantâneo de preço em tempo real para uma criptomoeda.",
                  "zh_Hans": "获取加密货币的实时价格快照。"
                },
                "llm": "Get the real-time price snapshot for a cryptocurrency."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "financialai",
                "label": {
                  "en_US": "Crypto Snapshot",
                  "pt_BR": "Instantâneo de Criptomoeda",
                  "zh_Hans": "加密货币快照"
                },
                "name": "crypto_snapshot"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The cryptocurrency ticker symbol.",
                    "pt_BR": "O símbolo do ticker da criptomoeda.",
                    "zh_Hans": "加密货币的代码。"
                  },
                  "label": {
                    "en_US": "Ticker symbol",
                    "pt_BR": "Símbolo do ticker da criptomoeda",
                    "zh_Hans": "加密货币代码"
                  },
                  "llm_description": "The cryptocurrency ticker symbol.",
                  "max": null,
                  "min": null,
                  "name": "ticker",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get earnings press releases for a ticker. The data returned from the API includes the URL, publish date, and full text of the press release.",
                  "pt_BR": "Obtenha comunicados de resultados para um ticker. Os dados retornados pela API incluem a URL, a data de publicação e o texto completo do comunicado.",
                  "zh_Hans": "获取股票代码的盈利新闻稿。API 返回的数据包括新闻稿的 URL、发布日期和全文。"
                },
                "llm": "Get earnings press releases for a ticker. The data returned from the API includes the URL, publish date, and full text of the press release."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "financialai",
                "label": {
                  "en_US": "Earnings Press Releases",
                  "pt_BR": "Comunicados de Resultados",
                  "zh_Hans": "盈利新闻稿"
                },
                "name": "earnings_press_releases"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ticker symbol of the company you want to get earnings press releases for.",
                    "pt_BR": "O símbolo do ticker da empresa para a qual você deseja obter comunicados de resultados.",
                    "zh_Hans": "您想获取盈利新闻稿的公司的股票代码。"
                  },
                  "label": {
                    "en_US": "Ticker symbol",
                    "pt_BR": "Símbolo do ticker",
                    "zh_Hans": "股票代码"
                  },
                  "llm_description": "The ticker symbol of the company you want to get earnings press releases for.",
                  "max": null,
                  "min": null,
                  "name": "ticker",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get financial metrics for a ticker, including valuation, profitability, efficiency, liquidity, leverage, growth, and per share metrics.",
                  "pt_BR": "Obtenha métricas financeiras para um ticker, incluindo avaliação, lucratividade, eficiência, liquidez, alavancagem, crescimento e métricas por ação.",
                  "zh_Hans": "获取股票代码的财务指标，包括估值、盈利能力、效率、流动性、杠杆、增长和每股指标。"
                },
                "llm": "Get financial metrics for a ticker, including valuation, profitability, efficiency, liquidity, leverage, growth, and per share metrics."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "financialai",
                "label": {
                  "en_US": "Historical Financial Metrics",
                  "pt_BR": "Métricas Financeiras Históricas",
                  "zh_Hans": "历史财务指标"
                },
                "name": "financial_metrics_historical"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ticker symbol of the company you want to get financial metrics for.",
                    "pt_BR": "O símbolo do ticker da empresa para a qual você deseja obter métricas financeiras.",
                    "zh_Hans": "您想获取财务指标的公司的股票代码。"
                  },
                  "label": {
                    "en_US": "Ticker symbol",
                    "pt_BR": "Símbolo do ticker",
                    "zh_Hans": "股票代码"
                  },
                  "llm_description": "The ticker symbol of the company you want to get financial metrics for.",
                  "max": null,
                  "min": null,
                  "name": "ticker",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The period for the financial metrics.",
                    "pt_BR": "O período para as métricas financeiras.",
                    "zh_Hans": "财务指标的期间。"
                  },
                  "label": {
                    "en_US": "Period",
                    "pt_BR": "Período",
                    "zh_Hans": "期间"
                  },
                  "llm_description": "The period for the financial metrics.",
                  "max": null,
                  "min": null,
                  "name": "period",
                  "options": [
                    {
                      "label": {
                        "en_US": "Annual",
                        "pt_BR": "Anual",
                        "zh_Hans": "年度"
                      },
                      "value": "annual"
                    },
                    {
                      "label": {
                        "en_US": "Quarterly",
                        "pt_BR": "Trimestral",
                        "zh_Hans": "季度"
                      },
                      "value": "quarterly"
                    },
                    {
                      "label": {
                        "en_US": "Trailing twelve months",
                        "pt_BR": "Últimos doze meses",
                        "zh_Hans": "过去十二个月"
                      },
                      "value": "ttm"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The maximum number of financial metrics to return.",
                    "pt_BR": "O número máximo de métricas financeiras a serem retornadas.",
                    "zh_Hans": "要返回的财务指标的最大数量。"
                  },
                  "label": {
                    "en_US": "Limit",
                    "pt_BR": "Limite",
                    "zh_Hans": "限制"
                  },
                  "llm_description": "The maximum number of financial metrics to return.",
                  "max": null,
                  "min": null,
                  "name": "limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get a real-time snapshot of key financial metrics and ratios for a ticker, including valuation, profitability, efficiency, liquidity, leverage, growth, and per share metrics.",
                  "pt_BR": "Obtenha um instantâneo em tempo real das principais métricas e índices financeiros para um ticker, incluindo avaliação, lucratividade, eficiência, liquidez, alavancagem, crescimento e métricas por ação.",
                  "zh_Hans": "获取股票代码的关键财务指标和比率的实时快照，包括估值、盈利能力、效率、流动性、杠杆、增长和每股指标。"
                },
                "llm": "Get a real-time snapshot of key financial metrics and ratios for a ticker, including valuation, profitability, efficiency, liquidity, leverage, growth, and per share metrics."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "financialai",
                "label": {
                  "en_US": "Financial Metrics Snapshot",
                  "pt_BR": "Instantâneo de Métricas Financeiras",
                  "zh_Hans": "财务指标快照"
                },
                "name": "financial_metrics_snapshot"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ticker symbol of the company you want to get financial metrics for.",
                    "pt_BR": "O símbolo do ticker da empresa para a qual você deseja obter métricas financeiras.",
                    "zh_Hans": "您想获取财务指标的公司的股票代码。"
                  },
                  "label": {
                    "en_US": "Ticker symbol",
                    "pt_BR": "Símbolo do ticker",
                    "zh_Hans": "股票代码"
                  },
                  "llm_description": "The ticker symbol of the company you want to get financial metrics for.",
                  "max": null,
                  "min": null,
                  "name": "ticker",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get all financial statements for a ticker, including income statements, balance sheets, and cash flow statements.",
                  "pt_BR": "Obtenha todas as demonstrações financeiras para um ticker, incluindo demonstrações de resultados, balanços patrimoniais e demonstrações de fluxo de caixa.",
                  "zh_Hans": "获取股票代码的所有财务报表，包括损益表、资产负债表和现金流量表。"
                },
                "llm": "Get all financial statements for a ticker, including income statements, balance sheets, and cash flow statements."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "financialai",
                "label": {
                  "en_US": "Financial Statements",
                  "pt_BR": "Demonstrações Financeiras",
                  "zh_Hans": "财务报表"
                },
                "name": "financial_statements"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ticker symbol of the company you want to get financial statements for.",
                    "pt_BR": "O símbolo do ticker da empresa para a qual você deseja obter demonstrações financeiras.",
                    "zh_Hans": "您想获取财务报表的公司的股票代码。"
                  },
                  "label": {
                    "en_US": "Ticker symbol",
                    "pt_BR": "Símbolo do ticker",
                    "zh_Hans": "股票代码"
                  },
                  "llm_description": "The ticker symbol of the company you want to get financial statements for.",
                  "max": null,
                  "min": null,
                  "name": "ticker",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "annual",
                  "form": "llm",
                  "human_description": {
                    "en_US": "The time period for the financial statements.",
                    "pt_BR": "O período das demonstrações financeiras.",
                    "zh_Hans": "财务报表的时间段。"
                  },
                  "label": {
                    "en_US": "Time period",
                    "pt_BR": "Período",
                    "zh_Hans": "时间段"
                  },
                  "llm_description": "The time period for the financial statements.",
                  "max": null,
                  "min": null,
                  "name": "period",
                  "options": [
                    {
                      "label": {
                        "en_US": "Annual",
                        "pt_BR": "Anual",
                        "zh_Hans": "年度"
                      },
                      "value": "annual"
                    },
                    {
                      "label": {
                        "en_US": "Quarterly",
                        "pt_BR": "Trimestral",
                        "zh_Hans": "季度"
                      },
                      "value": "quarterly"
                    },
                    {
                      "label": {
                        "en_US": "Trailing twelve months",
                        "pt_BR": "Últimos doze meses",
                        "zh_Hans": "过去十二个月"
                      },
                      "value": "ttm"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 1,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The number of financial statements to return.",
                    "pt_BR": "O número de demonstrações financeiras a serem retornadas.",
                    "zh_Hans": "要返回的财务报表数量。"
                  },
                  "label": {
                    "en_US": "Limit",
                    "pt_BR": "Limite",
                    "zh_Hans": "限制"
                  },
                  "llm_description": "The number of financial statements to return.",
                  "max": null,
                  "min": null,
                  "name": "limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get insider trades like buys and sells for a ticker by a company insider such as a CEO, CFO, or Director.",
                  "pt_BR": "Obtenha negociações internas, como compras e vendas, para um ticker por um insider da empresa, como um CEO, CFO ou Diretor.",
                  "zh_Hans": "通过公司内部人员（如 CEO、CFO 或董事）获取股票的内部交易，如买入和卖出。"
                },
                "llm": "Get insider trades like buys and sells for a ticker by a company insider such as a CEO, CFO, or Director."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "financialai",
                "label": {
                  "en_US": "Insider Trades",
                  "pt_BR": "Negociações Internas",
                  "zh_Hans": "内部交易"
                },
                "name": "insider_trades"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ticker symbol of the company you want to get insider trades for.",
                    "pt_BR": "O símbolo do ticker da empresa para a qual você deseja obter negociações internas.",
                    "zh_Hans": "您想获取内部交易的公司的股票代码。"
                  },
                  "label": {
                    "en_US": "Ticker symbol",
                    "pt_BR": "Símbolo do ticker",
                    "zh_Hans": "股票代码"
                  },
                  "llm_description": "The ticker symbol of the company you want to get insider trades for.",
                  "max": null,
                  "min": null,
                  "name": "ticker",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 1,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The maximum number of transactions to return (default: 10).",
                    "pt_BR": "O número máximo de transações a serem retornadas (padrão: 10).",
                    "zh_Hans": "要返回的交易数量的最大值（默认值：10）。"
                  },
                  "label": {
                    "en_US": "Limit",
                    "pt_BR": "Limite",
                    "zh_Hans": "限制"
                  },
                  "llm_description": "The maximum number of transactions to return (default: 10).",
                  "max": null,
                  "min": null,
                  "name": "limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get institutional ownership by investor or ticker. This quarterly data comes directly from Form 13F filings and includes tickers, share quantities, estimated holding prices, and market values.",
                  "pt_BR": "Obtenha a propriedade institucional por investidor ou ticker. Esses dados trimestrais vêm diretamente das declarações do Formulário 13F e incluem tickers, quantidades de ações, preços de manutenção estimados e valores de mercado.",
                  "zh_Hans": "通过投资者或股票获取机构持股。这些季度数据直接来自 13F 表格提交，并包括股票代码、股票数量、估计持有价格和市值。"
                },
                "llm": "Get institutional ownership by investor or ticker. This quarterly data comes directly from Form 13F filings and includes tickers, share quantities, estimated holding prices, and market values."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "financialai",
                "label": {
                  "en_US": "Institutional Ownership",
                  "pt_BR": "Propriedade Institucional",
                  "zh_Hans": "机构持股"
                },
                "name": "institutional_ownership"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ticker symbol of the company you want to get institutional ownership for.",
                    "pt_BR": "O símbolo do ticker da empresa para a qual você deseja obter a propriedade institucional.",
                    "zh_Hans": "您想获取机构持股的公司的股票代码。"
                  },
                  "label": {
                    "en_US": "Ticker symbol",
                    "pt_BR": "Símbolo do ticker",
                    "zh_Hans": "股票代码"
                  },
                  "llm_description": "The ticker symbol of the company you want to get institutional ownership for.",
                  "max": null,
                  "min": null,
                  "name": "ticker",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 1,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The maximum number of holdings to return (default: 10).",
                    "pt_BR": "O número máximo de participações a serem retornadas (padrão: 10).",
                    "zh_Hans": "要返回的持股数量的最大值（默认值：10）。"
                  },
                  "label": {
                    "en_US": "Limit",
                    "pt_BR": "Limite",
                    "zh_Hans": "限制"
                  },
                  "llm_description": "The maximum number of holdings to return (default: 10).",
                  "max": null,
                  "min": null,
                  "name": "limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get real-time and historical news for a ticker.",
                  "pt_BR": "Obtenha notícias em tempo real e históricas para um ticker.",
                  "zh_Hans": "获取股票代码的实时和历史新闻。"
                },
                "llm": "Get real-time and historical news for a ticker."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "financialai",
                "label": {
                  "en_US": "Company News",
                  "pt_BR": "Notícias da Empresa",
                  "zh_Hans": "公司新闻"
                },
                "name": "conpany_news"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ticker symbol of the company you want to get news for.",
                    "pt_BR": "O símbolo do ticker da empresa para a qual você deseja obter notícias.",
                    "zh_Hans": "您想获取新闻的公司的股票代码。"
                  },
                  "label": {
                    "en_US": "Ticker symbol",
                    "pt_BR": "Símbolo do ticker",
                    "zh_Hans": "股票代码"
                  },
                  "llm_description": "The ticker symbol of the company you want to get news for.",
                  "max": null,
                  "min": null,
                  "name": "ticker",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The start date for the news data (format: YYYY-MM-DD).",
                    "pt_BR": "A data de início para os dados de notícias (formato: AAAA-MM-DD).",
                    "zh_Hans": "新闻数据的开始日期（格式：YYYY-MM-DD）。"
                  },
                  "label": {
                    "en_US": "Start date (YYYY-MM-DD)",
                    "pt_BR": "Data de início (AAAA-MM-DD)",
                    "zh_Hans": "开始日期 (YYYY-MM-DD)"
                  },
                  "llm_description": "The start date for the news data (format: YYYY-MM-DD).",
                  "max": null,
                  "min": null,
                  "name": "start_date",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The end date for the news data (format: YYYY-MM-DD).",
                    "pt_BR": "A data final para os dados de notícias (formato: AAAA-MM-DD).",
                    "zh_Hans": "新闻数据的结束日期（格式：YYYY-MM-DD）。"
                  },
                  "label": {
                    "en_US": "End date (YYYY-MM-DD)",
                    "pt_BR": "Data final (AAAA-MM-DD)",
                    "zh_Hans": "结束日期 (YYYY-MM-DD)"
                  },
                  "llm_description": "The end date for the news data (format: YYYY-MM-DD).",
                  "max": null,
                  "min": null,
                  "name": "end_date",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 1,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The maximum number of news articles to return (default: 100, max: 100).",
                    "pt_BR": "O número máximo de artigos de notícias a serem retornados (padrão: 100, máximo: 100).",
                    "zh_Hans": "要返回的新闻文章的最大数（默认值：100，最大值：100）。"
                  },
                  "label": {
                    "en_US": "Limit",
                    "pt_BR": "Limite",
                    "zh_Hans": "限制"
                  },
                  "llm_description": "The maximum number of news articles to return (default: 100, max: 100).",
                  "max": null,
                  "min": null,
                  "name": "limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get ranged price data for a ticker to power stock charts and analyze price movements.",
                  "pt_BR": "Obtenha dados de preço variados para um ticker para alimentar gráficos de ações e analisar movimentos de preços.",
                  "zh_Hans": "获取股票代码的价格范围数据，以支持股票图表和分析价格走势。"
                },
                "llm": "Get ranged price data for a ticker to power stock charts and analyze price movements."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "financialai",
                "label": {
                  "en_US": "Stock Prices",
                  "pt_BR": "Preços de Ações",
                  "zh_Hans": "股票价格"
                },
                "name": "stock_prices"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ticker symbol of price data you want to get.",
                    "pt_BR": "O símbolo do ticker dos dados de preço que você deseja obter.",
                    "zh_Hans": "您想获取价格数据的股票代码。"
                  },
                  "label": {
                    "en_US": "Ticker symbol",
                    "pt_BR": "Símbolo do ticker",
                    "zh_Hans": "股票代码"
                  },
                  "llm_description": "The ticker symbol of price data you want to get.",
                  "max": null,
                  "min": null,
                  "name": "ticker",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The time interval for the price data.",
                    "pt_BR": "O intervalo de tempo para os dados de preço.",
                    "zh_Hans": "价格数据的时间间隔。"
                  },
                  "label": {
                    "en_US": "Time interval",
                    "pt_BR": "Intervalo de tempo",
                    "zh_Hans": "时间间隔"
                  },
                  "llm_description": "The time interval for the price data.",
                  "max": null,
                  "min": null,
                  "name": "interval",
                  "options": [
                    {
                      "label": {
                        "en_US": "Second",
                        "pt_BR": "Segundo",
                        "zh_Hans": "秒"
                      },
                      "value": "second"
                    },
                    {
                      "label": {
                        "en_US": "Minute",
                        "pt_BR": "Minuto",
                        "zh_Hans": "分钟"
                      },
                      "value": "minute"
                    },
                    {
                      "label": {
                        "en_US": "Day",
                        "pt_BR": "Dia",
                        "zh_Hans": "天"
                      },
                      "value": "day"
                    },
                    {
                      "label": {
                        "en_US": "Week",
                        "pt_BR": "Semana",
                        "zh_Hans": "周"
                      },
                      "value": "week"
                    },
                    {
                      "label": {
                        "en_US": "Month",
                        "pt_BR": "Mês",
                        "zh_Hans": "月"
                      },
                      "value": "month"
                    },
                    {
                      "label": {
                        "en_US": "Year",
                        "pt_BR": "Ano",
                        "zh_Hans": "年"
                      },
                      "value": "year"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 1,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The multiplier for the time interval.",
                    "pt_BR": "O multiplicador para o intervalo de tempo.",
                    "zh_Hans": "时间间隔的倍增器。"
                  },
                  "label": {
                    "en_US": "Interval multiplier",
                    "pt_BR": "Multiplicador de intervalo",
                    "zh_Hans": "时间间隔倍增器"
                  },
                  "llm_description": "The multiplier for the time interval.",
                  "max": null,
                  "min": 1,
                  "name": "interval_multiplier",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The start date for the price data (format: YYYY-MM-DD).",
                    "pt_BR": "A data de início para os dados de preço (formato: AAAA-MM-DD).",
                    "zh_Hans": "价格数据的开始日期（格式：YYYY-MM-DD）。"
                  },
                  "label": {
                    "en_US": "Start date (YYYY-MM-DD)",
                    "pt_BR": "Data de início (AAAA-MM-DD)",
                    "zh_Hans": "开始日期 (YYYY-MM-DD)"
                  },
                  "llm_description": "The start date for the price data (format: YYYY-MM-DD).",
                  "max": null,
                  "min": null,
                  "name": "start_date",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The end date for the price data (format: YYYY-MM-DD).",
                    "pt_BR": "A data final para os dados de preço (formato: AAAA-MM-DD).",
                    "zh_Hans": "价格数据的结束日期（格式：YYYY-MM-DD）。"
                  },
                  "label": {
                    "en_US": "End date (YYYY-MM-DD)",
                    "pt_BR": "Data final (AAAA-MM-DD)",
                    "zh_Hans": "结束日期 (YYYY-MM-DD)"
                  },
                  "llm_description": "The end date for the price data (format: YYYY-MM-DD).",
                  "max": null,
                  "min": null,
                  "name": "end_date",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 5000,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The maximum number of price records to return (default: 5000, max: 5000).",
                    "pt_BR": "O número máximo de registros de preço a serem retornados (padrão: 5000, máximo: 5000).",
                    "zh_Hans": "要返回的价格记录的最大数量（默认值：5000，最大值：5000）。"
                  },
                  "label": {
                    "en_US": "Limit",
                    "pt_BR": "Limite",
                    "zh_Hans": "限制"
                  },
                  "llm_description": "The maximum number of price records to return (default: 5000, max: 5000).",
                  "max": 5000,
                  "min": 1,
                  "name": "limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get the real-time price snapshot for a ticker.",
                  "pt_BR": "Obtenha o instantâneo de preço em tempo real para um ticker.",
                  "zh_Hans": "获取股票代码的实时价格快照。"
                },
                "llm": "Get the real-time price snapshot for a ticker."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "financialai",
                "label": {
                  "en_US": "Stock Snapshot",
                  "pt_BR": "Instantâneo de Ações",
                  "zh_Hans": "股票快照"
                },
                "name": "stock_snapshot"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ticker symbol.",
                    "pt_BR": "O símbolo do ticker.",
                    "zh_Hans": "股票代码。"
                  },
                  "label": {
                    "en_US": "Ticker symbol",
                    "pt_BR": "Símbolo do ticker",
                    "zh_Hans": "股票代码"
                  },
                  "llm_description": "The ticker symbol.",
                  "max": null,
                  "min": null,
                  "name": "ticker",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get SEC filings for a company. This includes 10-Ks, 10-Qs, 8-Ks, and more.",
                  "pt_BR": "Obtenha arquivamentos da SEC para uma empresa. Isso inclui 10-Ks, 10-Qs, 8-Ks e muito mais.",
                  "zh_Hans": "获取公司的 SEC 备案。这包括 10-K、10-Q、8-K 等。"
                },
                "llm": "Get SEC filings for a company. This includes 10-Ks, 10-Qs, 8-Ks, and more."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "financialai",
                "label": {
                  "en_US": "SEC Filings",
                  "pt_BR": "Arquivamentos da SEC",
                  "zh_Hans": "SEC备案"
                },
                "name": "sec_filings"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ticker symbol of the company you want to get SEC filings for.",
                    "pt_BR": "O símbolo do ticker da empresa para a qual você deseja obter arquivamentos da SEC.",
                    "zh_Hans": "您想获取公司的 SEC 备案的公司的股票代码。"
                  },
                  "label": {
                    "en_US": "Ticker symbol",
                    "pt_BR": "Símbolo do ticker",
                    "zh_Hans": "股票代码"
                  },
                  "llm_description": "The ticker symbol of the company you want to get SEC filings for.",
                  "max": null,
                  "min": null,
                  "name": "ticker",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get SEC filing items for a company. The Items endpoint allows you to extract specific sections (called items) from a given 10-K or 10-Q filing.",
                  "pt_BR": "Obtenha itens de arquivamento da SEC para uma empresa. O endpoint Items permite que você extraia seções específicas (chamadas itens) de um arquivamento 10-K ou 10-Q fornecido.",
                  "zh_Hans": "获取公司的 SEC 备案项目。Items 端点允许您从给定的 10-K 或 10-Q 备案中提取特定部分（称为项目）。"
                },
                "llm": "Get SEC filing items for a company. The Items endpoint allows you to extract specific sections (called items) from a given 10-K or 10-Q filing."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "financialai",
                "label": {
                  "en_US": "SEC Filings Items",
                  "pt_BR": "Itens de Arquivamentos da SEC",
                  "zh_Hans": "SEC备案项目"
                },
                "name": "sec_filings_items"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ticker symbol of the company you want to get SEC filing items for.",
                    "pt_BR": "O símbolo do ticker da empresa para a qual você deseja obter itens de arquivamento da SEC.",
                    "zh_Hans": "您想获取公司的 SEC 备案项目的公司的股票代码。"
                  },
                  "label": {
                    "en_US": "Ticker symbol",
                    "pt_BR": "Símbolo do ticker",
                    "zh_Hans": "股票代码"
                  },
                  "llm_description": "The ticker symbol of the company you want to get SEC filing items for.",
                  "max": null,
                  "min": null,
                  "name": "ticker",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The type of filing you want to get items for.",
                    "pt_BR": "O tipo de arquivamento para o qual você deseja obter itens.",
                    "zh_Hans": "您想获取项目的备案类型。"
                  },
                  "label": {
                    "en_US": "Type of filing",
                    "pt_BR": "O tipo de arquivamento",
                    "zh_Hans": "备案类型"
                  },
                  "llm_description": "The type of filing you want to get items for.",
                  "max": null,
                  "min": null,
                  "name": "filing_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "10-K",
                        "pt_BR": "10-K",
                        "zh_Hans": "10-K"
                      },
                      "value": "10-K"
                    },
                    {
                      "label": {
                        "en_US": "10-Q",
                        "pt_BR": "10-Q",
                        "zh_Hans": "10-Q"
                      },
                      "value": "10-Q"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The year of the filing you want to get items for.",
                    "pt_BR": "O ano do arquivamento para o qual você deseja obter itens.",
                    "zh_Hans": "您想获取项目的备案年份。"
                  },
                  "label": {
                    "en_US": "Year of the filing",
                    "pt_BR": "O ano do arquivamento",
                    "zh_Hans": "备案年份"
                  },
                  "llm_description": "The year of the filing you want to get items for.",
                  "max": null,
                  "min": null,
                  "name": "year",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The quarter of the filing you want to get items for.",
                    "pt_BR": "O trimestre do arquivamento para o qual você deseja obter itens.",
                    "zh_Hans": "您想获取项目的备案季度。"
                  },
                  "label": {
                    "en_US": "Quarter of the filing",
                    "pt_BR": "O trimestre do arquivamento",
                    "zh_Hans": "备案季度"
                  },
                  "llm_description": "The quarter of the filing you want to get items for.",
                  "max": null,
                  "min": null,
                  "name": "quarter",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The item you want to get.",
                    "pt_BR": "O item que você deseja obter.",
                    "zh_Hans": "您想获取的项目。"
                  },
                  "label": {
                    "en_US": "Item",
                    "pt_BR": "Item",
                    "zh_Hans": "项目"
                  },
                  "llm_description": "The item you want to get.",
                  "max": null,
                  "min": null,
                  "name": "item",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-17T12:20:14Z",
        "version_updated_at": "2025-03-17T12:20:14Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Hyper application platform that is particularly friendly to AI",
          "pt_BR": "Plataforma de aplicação hiper que é particularmente amigável à IA",
          "zh_Hans": "对 AI 特别友好的超级应用平台"
        },
        "category": "tool",
        "created_at": "2024-11-29T09:24:08Z",
        "endpoint": {},
        "icon": "langgenius/packages/hap/_assets/icon.svg",
        "index_id": "langgenius___hap",
        "install_count": 357,
        "introduction": "# Overview\nHAP (Hyper Application Platform), developed by 明道云 (Mingdao Cloud), is an APaaS (Application Platform as a Service) solution designed to enable enterprises to build, automate, and integrate applications with minimal or no coding. It empowers businesses to streamline operations, bridge data silos, and enhance collaboration through its robust no-code and low-code capabilities.\nYou can operate worksheets in HAP using the HAP tool.\n\n# Configure\n## Installation\n1. Install HAP from Dify Marketplace.\n![](./_assets/hap_install.png)\n\n2. Add HAP to your workflow.\n\n## Tools\n### Add Worksheet Record\n![](./_assets/hap_add_worksheet_record.png)\n\n### Get Worksheet Fields\n![](./_assets/hap_add_worksheet_field.PNG)\n\n### Delete Worksheet Record\n![](./_assets/hap_delete_worksheet_record.png)\n\n### Get Worksheet Pivot Data\n![](./_assets/hap_get_worksheet_pivot_data.png)\n\n### List Worksheet Records\n![](./_assets/hap_list_worksheet_records.png)\n\n### List Worksheets\n![](./_assets/hap_list_worksheets.png)\n\nUpdate Worksheet Record\n![](./_assets/hap_update_worksheet_record.png)\n\nFor further help, please refer to the [HAP documentation](https://help.mingdao.com/worksheet/introduction/).",
        "label": {
          "en_US": "HAP",
          "pt_BR": "HAP",
          "zh_Hans": "HAP"
        },
        "latest_package_identifier": "langgenius/hap:0.0.2@1752826e6eec1f136bd7fd618168b77c9b7b3850d012e7f0cfbeeedeb6f0d1c4",
        "latest_version": "0.0.2",
        "model": {},
        "name": "hap",
        "org": "langgenius",
        "plugin_id": "langgenius/hap",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/hap.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          }
        ],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "Mingdao",
            "description": {
              "en_US": "Hyper application platform that is particularly friendly to AI",
              "pt_BR": "Plataforma de aplicação hiper que é particularmente amigável à IA",
              "zh_Hans": "对 AI 特别友好的超级应用平台"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "HAP",
              "pt_BR": "HAP",
              "zh_Hans": "HAP"
            },
            "name": "hap",
            "tags": [
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Get fields information of the worksheet",
                  "zh_Hans": "获取指定工作表的所有字段结构信息"
                },
                "llm": "A tool to get fields information of the specific worksheet."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Ryan_Tian",
                "label": {
                  "en_US": "Get Worksheet Fields",
                  "zh_Hans": "获取工作表字段结构"
                },
                "name": "get_worksheet_fields"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The AppKey parameter for the HAP application, typically found in the application's API documentation.",
                    "zh_Hans": "HAP 应用的 AppKey 参数，可以从应用 API 文档中查找到"
                  },
                  "label": {
                    "en_US": "App Key",
                    "zh_Hans": "App Key"
                  },
                  "llm_description": "the AppKey parameter for the HAP application",
                  "max": null,
                  "min": null,
                  "name": "appkey",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The Sign parameter for the HAP application",
                    "zh_Hans": "HAP 应用的 Sign 参数"
                  },
                  "label": {
                    "en_US": "Sign",
                    "zh_Hans": "Sign"
                  },
                  "llm_description": "the Sign parameter for the HAP application",
                  "max": null,
                  "min": null,
                  "name": "sign",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the specified worksheet",
                    "zh_Hans": "要获取字段信息的工作表 ID"
                  },
                  "label": {
                    "en_US": "Worksheet ID",
                    "zh_Hans": "工作表 ID"
                  },
                  "llm_description": "The ID of the specified worksheet which to get the fields information.",
                  "max": null,
                  "min": null,
                  "name": "worksheet_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The address for the privately deployed HAP server.",
                    "zh_Hans": "私有部署 HAP 服务器地址，公有云无需填写"
                  },
                  "label": {
                    "en_US": "Host Address",
                    "zh_Hans": "服务器地址"
                  },
                  "llm_description": "the address for the privately deployed HAP server.",
                  "max": null,
                  "min": null,
                  "name": "host",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "table",
                  "form": "form",
                  "human_description": {
                    "en_US": "used for selecting the result type, table styled text or json text",
                    "zh_Hans": "用于选择结果类型，使用表格格式文本还是JSON格式文本"
                  },
                  "label": {
                    "en_US": "Result type",
                    "zh_Hans": "结果类型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "result_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "table text",
                        "zh_Hans": "表格文本"
                      },
                      "value": "table"
                    },
                    {
                      "label": {
                        "en_US": "json text",
                        "zh_Hans": "JSON文本"
                      },
                      "value": "json"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "List records from the worksheet",
                  "zh_Hans": "查询工作表的记录列表数据，一次最多1000行，可分页获取"
                },
                "llm": "A tool to retrieve record data from the specific worksheet."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Ryan_Tian",
                "label": {
                  "en_US": "List Worksheet Records",
                  "zh_Hans": "查询工作表记录数据"
                },
                "name": "list_worksheet_records"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The AppKey parameter for the HAP application, typically found in the application's API documentation.",
                    "zh_Hans": "HAP 应用的 AppKey 参数，可以从应用 API 文档中查找到"
                  },
                  "label": {
                    "en_US": "App Key",
                    "zh_Hans": "App Key"
                  },
                  "llm_description": "the AppKey parameter for the HAP application",
                  "max": null,
                  "min": null,
                  "name": "appkey",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The Sign parameter for the HAP application",
                    "zh_Hans": "HAP 应用的 Sign 参数"
                  },
                  "label": {
                    "en_US": "Sign",
                    "zh_Hans": "Sign"
                  },
                  "llm_description": "the Sign parameter for the HAP application",
                  "max": null,
                  "min": null,
                  "name": "sign",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the worksheet from which to retrieve record data",
                    "zh_Hans": "要获取记录数据的工作表 ID"
                  },
                  "label": {
                    "en_US": "Worksheet ID",
                    "zh_Hans": "工作表 ID"
                  },
                  "llm_description": "This parameter specifies the ID of the worksheet where the records are stored.",
                  "max": null,
                  "min": null,
                  "name": "worksheet_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "A comma-separated list of field IDs whose data to retrieve. If not provided, all fields' data will be fetched",
                    "zh_Hans": "要获取记录数据的字段 ID，多个 ID 间用英文逗号隔开，不传此参数则将获取所有字段的数据"
                  },
                  "label": {
                    "en_US": "Field IDs",
                    "zh_Hans": "字段 ID 列表"
                  },
                  "llm_description": "This optional parameter lets you specify a comma-separated list of field IDs. Unless the user explicitly requests to output the specified field in the question, this parameter should usually be omitted. If this parameter is omitted, the API will return data for all fields by default. When provided, only the data associated with these fields will be included in the response.",
                  "max": null,
                  "min": null,
                  "name": "field_ids",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "A combination of filters applied to query records, formatted as a JSON array. See the application's API documentation for details on its structure and usage.",
                    "zh_Hans": "查询记录的筛选条件组合，格式为 JSON 数组，可以从应用 API 文档中了解参数结构详情"
                  },
                  "label": {
                    "en_US": "Filter Set",
                    "zh_Hans": "筛选器组合"
                  },
                  "llm_description": "This parameter allows you to specify a set of conditions that records must meet to be included in the result set. It is formatted as a JSON array, with its structure defined as follows:\n```\ntype Filters = { // filter object array\n  controlId: string; // fieldId\n  dataType: number; // fieldTypeId\n  spliceType: number; // condition concatenation method, 1: And, 2: Or\n  filterType: number; // expression type, refer to the <FilterTypeEnum Reference> for enumerable values\n  values?: string[]; // values in the condition, for option-type fields, multiple values can be passed\n  value?: string; // value in the condition, a single value can be passed according to the field type\n  dateRange?: number; // date range, mandatory when filterType is 17 or 18, refer to the <DateRangeEnum Reference> for enumerable values\n  minValue?: string; // minimum value for custom range\n  maxValue?: string; // maximum value for custom range\n  isAsc?: boolean; // ascending order, false: descending, true: ascending\n}[];\n```\nFor option-type fields, if this option field has `options`, then you need to get the corresponding `key` value from the `options` in the current field information via `value`, and pass it into `values` in array format. Do not use the `options` value of other fields as input conditions.\n\n### FilterTypeEnum Reference\n```\nEnum Value, Enum Character, Description\n1, Like, Contains(Include)\n2, Eq, Is (Equal)\n3, Start, Starts With\n4, End, Ends With\n5, NotLike, Does Not Contain(Not Include)\n6, Ne, Is Not (Not Equal)\n7, IsEmpty, Empty\n8, HasValue, Not Empty\n11, Between, Within Range(Belong to)\n12, NotBetween, Outside Range(Not belong to)\n13, Gt, Greater Than\n14, Gte, Greater Than or Equal To\n15, Lt, Less Than\n16, Lte, Less Than or Equal To\n17, DateEnum, Date Is\n18, NotDateEnum, Date Is Not\n24, RCEq, Associated Field Is\n25, RCNe, Associated Field Is Not\n26, ArrEq, Array Equals\n27, ArrNe, Array Does Not Equal\n31, DateBetween, Date Within Range (can only be used with minValue and maxValue)\n32, DateNotBetween, Date Not Within Range (can only be used with minValue and maxValue)\n33, DateGt, Date Later Than\n34, DateGte, Date Later Than or Equal To\n35, DateLt, Date Earlier Than\n36, DateLte, Date Earlier Than or Equal To\n```\n\n### DateRangeEnum Reference\n```\nEnum Value, Enum Character, Description\n1, Today, Today\n2, Yesterday, Yesterday\n3, Tomorrow, Tomorrow\n4, ThisWeek, This Week\n5, LastWeek, Last Week\n6, NextWeek, Next Week\n7, ThisMonth, This Month\n8, LastMonth, Last Month\n9, NextMonth, Next Month\n12, ThisQuarter, This Quarter\n13, LastQuarter, Last Quarter\n14, NextQuarter, Next Quarter\n15, ThisYear, This Year\n16, LastYear, Last Year\n17, NextYear, Next Year\n18, Customize, Custom\n21, Last7Day, Past 7 Days\n22, Last14Day, Past 14 Days\n23, Last30Day, Past 30 Days\n31, Next7Day, Next 7 Days\n32, Next14Day, Next 14 Days\n33, Next33Day, Next 33 Days\n```\n",
                  "max": null,
                  "min": null,
                  "name": "filters",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the field used for sorting",
                    "zh_Hans": "用以排序的字段 ID"
                  },
                  "label": {
                    "en_US": "Sort Field ID",
                    "zh_Hans": "排序字段 ID"
                  },
                  "llm_description": "This optional parameter specifies the unique identifier of the field that will be used to sort the results. It should be set to the ID of an existing field within your data structure.",
                  "max": null,
                  "min": null,
                  "name": "sort_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Determines whether the sorting is in ascending (true) or descending (false) order",
                    "zh_Hans": "排序字段的排序方式：true-升序，false-降序"
                  },
                  "label": {
                    "en_US": "Ascending Order",
                    "zh_Hans": "是否升序排列"
                  },
                  "llm_description": "This optional parameter controls the direction of the sort. If set to true, the results will be sorted in ascending order; if false, they will be sorted in descending order.",
                  "max": null,
                  "min": null,
                  "name": "sort_is_asc",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The maximum number of records to retrieve",
                    "zh_Hans": "要获取的记录数量限制条数"
                  },
                  "label": {
                    "en_US": "Record Limit",
                    "zh_Hans": "记录数量限制"
                  },
                  "llm_description": "This optional parameter allows you to specify the maximum number of records that should be returned in the result set. When retrieving paginated record data, this parameter indicates the number of rows to fetch per page, and must be used in conjunction with the `page_index` parameter.",
                  "max": null,
                  "min": null,
                  "name": "limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The page number when paginating through a list of records",
                    "zh_Hans": "分页读取记录列表时的页码"
                  },
                  "label": {
                    "en_US": "Page Index",
                    "zh_Hans": "页码"
                  },
                  "llm_description": "This parameter is used when you need to paginate through a large set of records. The default value is 1, which refers to the first page. When it is used, the meaning of the `limit` parameter becomes the number of records per page.",
                  "max": null,
                  "min": null,
                  "name": "page_index",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The address for the privately deployed HAP server.",
                    "zh_Hans": "私有部署 HAP 服务器地址，公有云无需填写"
                  },
                  "label": {
                    "en_US": "Host Address",
                    "zh_Hans": "服务器地址"
                  },
                  "llm_description": "the address for the privately deployed HAP server.",
                  "max": null,
                  "min": null,
                  "name": "host",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "table",
                  "form": "form",
                  "human_description": {
                    "en_US": "used for selecting the result type, table styled text or json text",
                    "zh_Hans": "用于选择结果类型，使用表格格式文本还是JSON格式文本"
                  },
                  "label": {
                    "en_US": "Result type",
                    "zh_Hans": "结果类型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "result_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "table text",
                        "zh_Hans": "表格文本"
                      },
                      "value": "table"
                    },
                    {
                      "label": {
                        "en_US": "json text",
                        "zh_Hans": "JSON文本"
                      },
                      "value": "json"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Deletes a single record from a worksheet based on the specified record row ID",
                  "zh_Hans": "根据指定的记录ID删除一条工作表记录数据"
                },
                "llm": "A tool to remove a particular record from a worksheet by specifying its unique record identifier."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Ryan_Tian",
                "label": {
                  "en_US": "Delete Worksheet Record",
                  "zh_Hans": "删除指定的一条工作表记录"
                },
                "name": "delete_worksheet_record"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The AppKey parameter for the HAP application, typically found in the application's API documentation.",
                    "zh_Hans": "HAP 应用的 AppKey 参数，可以从应用 API 文档中查找到"
                  },
                  "label": {
                    "en_US": "App Key",
                    "zh_Hans": "App Key"
                  },
                  "llm_description": "the AppKey parameter for the HAP application",
                  "max": null,
                  "min": null,
                  "name": "appkey",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The Sign parameter for the HAP application",
                    "zh_Hans": "HAP 应用的 Sign 参数"
                  },
                  "label": {
                    "en_US": "Sign",
                    "zh_Hans": "Sign"
                  },
                  "llm_description": "the Sign parameter for the HAP application",
                  "max": null,
                  "min": null,
                  "name": "sign",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the specified worksheet",
                    "zh_Hans": "要获取字段信息的工作表 ID"
                  },
                  "label": {
                    "en_US": "Worksheet ID",
                    "zh_Hans": "工作表 ID"
                  },
                  "llm_description": "The ID of the specified worksheet which to get the fields information.",
                  "max": null,
                  "min": null,
                  "name": "worksheet_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The row ID of the specified record",
                    "zh_Hans": "要删除的记录 ID"
                  },
                  "label": {
                    "en_US": "Record Row ID",
                    "zh_Hans": "记录 ID"
                  },
                  "llm_description": "The row ID of the specified record which to be deleted.",
                  "max": null,
                  "min": null,
                  "name": "row_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The address for the privately deployed HAP server.",
                    "zh_Hans": "私有部署 HAP 服务器地址，公有云无需填写"
                  },
                  "label": {
                    "en_US": "Host Address",
                    "zh_Hans": "服务器地址"
                  },
                  "llm_description": "the address for the privately deployed HAP server.",
                  "max": null,
                  "min": null,
                  "name": "host",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Adds a new record to the specified worksheet",
                  "zh_Hans": "向指定的工作表新增一条记录数据"
                },
                "llm": "A tool to append a new data entry into a specified worksheet."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Ryan_Tian",
                "label": {
                  "en_US": "Add Worksheet Record",
                  "zh_Hans": "新增一条工作表记录"
                },
                "name": "add_worksheet_record"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The AppKey parameter for the HAP application, typically found in the application's API documentation.",
                    "zh_Hans": "HAP 应用的 AppKey 参数，可以从应用 API 文档中查找到"
                  },
                  "label": {
                    "en_US": "App Key",
                    "zh_Hans": "App Key"
                  },
                  "llm_description": "the AppKey parameter for the HAP application",
                  "max": null,
                  "min": null,
                  "name": "appkey",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The Sign parameter for the HAP application",
                    "zh_Hans": "HAP 应用的 Sign 参数"
                  },
                  "label": {
                    "en_US": "Sign",
                    "zh_Hans": "Sign"
                  },
                  "llm_description": "the Sign parameter for the HAP application",
                  "max": null,
                  "min": null,
                  "name": "sign",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the specified worksheet",
                    "zh_Hans": "要获取字段信息的工作表 ID"
                  },
                  "label": {
                    "en_US": "Worksheet ID",
                    "zh_Hans": "工作表 ID"
                  },
                  "llm_description": "The ID of the specified worksheet which to get the fields information.",
                  "max": null,
                  "min": null,
                  "name": "worksheet_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The fields with data of the specified record",
                    "zh_Hans": "要新增的记录数据，JSON 对象数组格式。数组元素属性：controlId-字段ID，value-字段值"
                  },
                  "label": {
                    "en_US": "Record Row Data",
                    "zh_Hans": "记录数据"
                  },
                  "llm_description": "The fields with data of the specified record which to be created. It is in the format of an array of JSON objects, and the structure is defined as follows:\n```\ntype RowData = {\n  controlId: string; // Field ID to be updated\n  value: string; // Field value to be updated\n}[];\n```\n",
                  "max": null,
                  "min": null,
                  "name": "record_data",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The address for the privately deployed HAP server.",
                    "zh_Hans": "私有部署 HAP 服务器地址，公有云无需填写"
                  },
                  "label": {
                    "en_US": "Host Address",
                    "zh_Hans": "服务器地址"
                  },
                  "llm_description": "the address for the privately deployed HAP server.",
                  "max": null,
                  "min": null,
                  "name": "host",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "List worksheets within an application",
                  "zh_Hans": "获取应用下的所有工作表和说明信息"
                },
                "llm": "A tool to list worksheets info within an application, imported parameter is AppKey and Sign of the application."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Ryan_Tian",
                "label": {
                  "en_US": "List Worksheets",
                  "zh_Hans": "获取应用下所有工作表"
                },
                "name": "list_worksheets"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The AppKey parameter for the HAP application, typically found in the application's API documentation.",
                    "zh_Hans": "HAP 应用的 AppKey 参数，可以从应用 API 文档中查找到"
                  },
                  "label": {
                    "en_US": "App Key",
                    "zh_Hans": "App Key"
                  },
                  "llm_description": "the AppKey parameter for the HAP application",
                  "max": null,
                  "min": null,
                  "name": "appkey",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The Sign parameter for the HAP application",
                    "zh_Hans": "HAP 应用的 Sign 参数"
                  },
                  "label": {
                    "en_US": "Sign",
                    "zh_Hans": "Sign"
                  },
                  "llm_description": "the Sign parameter for the HAP application",
                  "max": null,
                  "min": null,
                  "name": "sign",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The address for the privately deployed HAP server.",
                    "zh_Hans": "私有部署 HAP 服务器地址，公有云无需填写"
                  },
                  "label": {
                    "en_US": "Host Address",
                    "zh_Hans": "服务器地址"
                  },
                  "llm_description": "the address for the privately deployed HAP server.",
                  "max": null,
                  "min": null,
                  "name": "host",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "table",
                  "form": "form",
                  "human_description": {
                    "en_US": "used for selecting the result type, table styled text or json text",
                    "zh_Hans": "用于选择结果类型，使用表格格式文本还是JSON格式文本"
                  },
                  "label": {
                    "en_US": "Result type",
                    "zh_Hans": "结果类型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "result_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "table text",
                        "zh_Hans": "表格文本"
                      },
                      "value": "table"
                    },
                    {
                      "label": {
                        "en_US": "json text",
                        "zh_Hans": "JSON文本"
                      },
                      "value": "json"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Updates a single record in a worksheet based on the specified record row ID",
                  "zh_Hans": "根据指定的记录ID更新一条工作表记录数据"
                },
                "llm": "A tool to modify existing information within a particular record of a worksheet by referencing its unique identifier."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Ryan_Tian",
                "label": {
                  "en_US": "Update Worksheet Record",
                  "zh_Hans": "更新指定的一条工作表记录"
                },
                "name": "update_worksheet_record"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The AppKey parameter for the HAP application, typically found in the application's API documentation.",
                    "zh_Hans": "HAP 应用的 AppKey 参数，可以从应用 API 文档中查找到"
                  },
                  "label": {
                    "en_US": "App Key",
                    "zh_Hans": "App Key"
                  },
                  "llm_description": "the AppKey parameter for the HAP application",
                  "max": null,
                  "min": null,
                  "name": "appkey",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The Sign parameter for the HAP application",
                    "zh_Hans": "HAP 应用的 Sign 参数"
                  },
                  "label": {
                    "en_US": "Sign",
                    "zh_Hans": "Sign"
                  },
                  "llm_description": "the Sign parameter for the HAP application",
                  "max": null,
                  "min": null,
                  "name": "sign",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the specified worksheet",
                    "zh_Hans": "要获取字段信息的工作表 ID"
                  },
                  "label": {
                    "en_US": "Worksheet ID",
                    "zh_Hans": "工作表 ID"
                  },
                  "llm_description": "The ID of the specified worksheet which to get the fields information.",
                  "max": null,
                  "min": null,
                  "name": "worksheet_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The row ID of the specified record",
                    "zh_Hans": "要更新的记录 ID"
                  },
                  "label": {
                    "en_US": "Record Row ID",
                    "zh_Hans": "记录 ID"
                  },
                  "llm_description": "The row ID of the specified record which to be updated.",
                  "max": null,
                  "min": null,
                  "name": "row_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The fields with data of the specified record",
                    "zh_Hans": "要更新的记录数据，JSON 对象数组格式。数组元素属性：controlId-字段ID，value-字段值"
                  },
                  "label": {
                    "en_US": "Record Row Data",
                    "zh_Hans": "记录数据"
                  },
                  "llm_description": "The fields with data of the specified record which to be updated. It is in the format of an array of JSON objects, and the structure is defined as follows:\n```\ntype RowData = {\n  controlId: string; // Field ID to be updated\n  value: string; // Field value to be updated\n}[];\n```\n",
                  "max": null,
                  "min": null,
                  "name": "record_data",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The address for the privately deployed HAP server.",
                    "zh_Hans": "私有部署 HAP 服务器地址，公有云无需填写"
                  },
                  "label": {
                    "en_US": "Host Address",
                    "zh_Hans": "服务器地址"
                  },
                  "llm_description": "the address for the privately deployed HAP server.",
                  "max": null,
                  "min": null,
                  "name": "host",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Retrieve statistical pivot table data from a specified worksheet",
                  "zh_Hans": "从指定的工作表中检索统计透视表数据"
                },
                "llm": "A tool for extracting statistical pivot table data from a specific worksheet, providing summarized information for analysis and reporting purposes."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Ryan_Tian",
                "label": {
                  "en_US": "Get Worksheet Pivot Data",
                  "zh_Hans": "获取工作表统计透视数据"
                },
                "name": "get_worksheet_pivot_data"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The AppKey parameter for the HAP application, typically found in the application's API documentation.",
                    "zh_Hans": "HAP 应用的 AppKey 参数，可以从应用 API 文档中查找到"
                  },
                  "label": {
                    "en_US": "App Key",
                    "zh_Hans": "App Key"
                  },
                  "llm_description": "the AppKey parameter for the HAP application",
                  "max": null,
                  "min": null,
                  "name": "appkey",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The Sign parameter for the HAP application",
                    "zh_Hans": "HAP 应用的 Sign 参数"
                  },
                  "label": {
                    "en_US": "Sign",
                    "zh_Hans": "Sign"
                  },
                  "llm_description": "the Sign parameter for the HAP application",
                  "max": null,
                  "min": null,
                  "name": "sign",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the specified worksheet",
                    "zh_Hans": "要获取字段信息的工作表 ID"
                  },
                  "label": {
                    "en_US": "Worksheet ID",
                    "zh_Hans": "工作表 ID"
                  },
                  "llm_description": "The ID of the specified worksheet which to get the fields information.",
                  "max": null,
                  "min": null,
                  "name": "worksheet_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The column fields that make up the pivot table's X-axis groups or other dimensions for the X-axis in pivot charts",
                    "zh_Hans": "组成透视表的统计列或者统计图表的X轴分组及X轴其它维度。JSON 对象数组格式，数组元素属性：controlId-列ID，displayName-显示名称，particleSize(可选)-字段类型是日期或者地区时，通过此参数设置统计维度（日期时间：1-日，2-周，3-月；地区：1-全国，2-省，3-市）"
                  },
                  "label": {
                    "en_US": "Columns (X-axis)",
                    "zh_Hans": "统计列字段（X轴）"
                  },
                  "llm_description": "This parameter allows you to specify the columns that make up the pivot table's X-axis groups or other dimensions for the X-axis in pivot charts. It is formatted as a JSON array, with its structure defined as follows:\n```\ntype XColumnFields = { // X-axis or column object array\n  controlId: string; // fieldId\n  displayName: string; // displayName\n  particleSize?: number; // field type is date or area, set the statistical dimension (date time: 1-day, 2-week, 3-month; area: 1-nation, 2-province, 3-city)\n}[];\n```\n",
                  "max": null,
                  "min": null,
                  "name": "x_column_fields",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The row fields that make up the pivot table's Y-axis groups or other dimensions for the Y-axis in pivot charts",
                    "zh_Hans": "组成透视表的统计行或者统计图表的Y轴分组及Y轴其它维度。JSON 对象数组格式，数组元素属性：controlId-列ID，displayName-显示名称，particleSize(可选)-字段类型是日期或者地区时，通过此参数设置统计维度（日期时间：1-日，2-周，3-月；地区：1-全国，2-省，3-市）"
                  },
                  "label": {
                    "en_US": "Rows (Y-axis)",
                    "zh_Hans": "统计行字段（Y轴）"
                  },
                  "llm_description": "This parameter allows you to specify the rows that make up the pivot table's Y-axis groups or other dimensions for the Y-axis in pivot charts. It is formatted as a JSON array, with its structure defined as follows:\n```\ntype YRowFields = { // Y-axis or row object array\n  controlId: string; // fieldId\n  displayName: string; // displayName\n  particleSize?: number; // field type is date or area, set the statistical dimension (date time: 1-day, 2-week, 3-month; area: 1-nation, 2-province, 3-city)\n}[];\n```\n",
                  "max": null,
                  "min": null,
                  "name": "y_row_fields",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The aggregated value fields in the pivot table",
                    "zh_Hans": "透视表中经过聚合计算后的统计值字段。JSON 对象数组格式，数组元素属性：controlId-列ID，displayName-显示名称，aggregation-聚合方式（SUM,AVG,MIN,MAX,COUNT）"
                  },
                  "label": {
                    "en_US": "Aggregated Values",
                    "zh_Hans": "统计值字段"
                  },
                  "llm_description": "This parameter allows you to specify the aggregated value fields in the pivot table. It is formatted as a JSON array, with its structure defined as follows:\n```\ntype ValueFields = { // aggregated value object array\n  controlId: string; // fieldId\n  displayName: string; // displayName\n  aggregation: string; // aggregation method, e.g.: SUM, AVG, MIN, MAX, COUNT\n}[];\n```\n",
                  "max": null,
                  "min": null,
                  "name": "value_fields",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "A combination of filters applied to query records, formatted as a JSON array. See the application's API documentation for details on its structure and usage.",
                    "zh_Hans": "查询记录的筛选条件组合，格式为 JSON 数组，可以从应用 API 文档中了解参数结构详情"
                  },
                  "label": {
                    "en_US": "Filter Set",
                    "zh_Hans": "筛选器组合"
                  },
                  "llm_description": "This parameter allows you to specify a set of conditions that records must meet to be included in the result set. It is formatted as a JSON array, with its structure defined as follows:\n```\ntype Filters = { // filter object array\n  controlId: string; // fieldId\n  dataType: number; // fieldTypeId\n  spliceType: number; // condition concatenation method, 1: And, 2: Or\n  filterType: number; // expression type, refer to the <FilterTypeEnum Reference> for enumerable values\n  values?: string[]; // values in the condition, for option-type fields, multiple values can be passed\n  value?: string; // value in the condition, a single value can be passed according to the field type\n  dateRange?: number; // date range, mandatory when filterType is 17 or 18, refer to the <DateRangeEnum Reference> for enumerable values\n  minValue?: string; // minimum value for custom range\n  maxValue?: string; // maximum value for custom range\n  isAsc?: boolean; // ascending order, false: descending, true: ascending\n}[];\n```\nFor option-type fields, if this option field has `options`, then you need to get the corresponding `key` value from the `options` in the current field information via `value`, and pass it into `values` in array format. Do not use the `options` value of other fields as input conditions.\n\n### FilterTypeEnum Reference\n```\nEnum Value, Enum Character, Description\n1, Like, Contains\n2, Eq, Is (Equal)\n3, Start, Starts With\n4, End, Ends With\n5, NotLike, Does Not Contain\n6, Ne, Is Not (Not Equal)\n7, IsEmpty, Empty\n8, HasValue, Not Empty\n11, Between, Within Range\n12, NotBetween, Outside Range\n13, Gt, Greater Than\n14, Gte, Greater Than or Equal To\n15, Lt, Less Than\n16, Lte, Less Than or Equal To\n17, DateEnum, Date Is\n18, NotDateEnum, Date Is Not\n21, MySelf, Owned by Me\n22, UnRead, Unread\n23, Sub, Owned by Subordinate\n24, RCEq, Associated Field Is\n25, RCNe, Associated Field Is Not\n26, ArrEq, Array Equals\n27, ArrNe, Array Does Not Equal\n31, DateBetween, Date Within Range (can only be used with minValue and maxValue)\n32, DateNotBetween, Date Not Within Range (can only be used with minValue and maxValue)\n33, DateGt, Date Later Than\n34, DateGte, Date Later Than or Equal To\n35, DateLt, Date Earlier Than\n36, DateLte, Date Earlier Than or Equal To\n```\n\n### DateRangeEnum Reference\n```\nEnum Value, Enum Character, Description\n1, Today, Today\n2, Yesterday, Yesterday\n3, Tomorrow, Tomorrow\n4, ThisWeek, This Week\n5, LastWeek, Last Week\n6, NextWeek, Next Week\n7, ThisMonth, This Month\n8, LastMonth, Last Month\n9, NextMonth, Next Month\n12, ThisQuarter, This Quarter\n13, LastQuarter, Last Quarter\n14, NextQuarter, Next Quarter\n15, ThisYear, This Year\n16, LastYear, Last Year\n17, NextYear, Next Year\n18, Customize, Custom\n21, Last7Day, Past 7 Days\n22, Last14Day, Past 14 Days\n23, Last30Day, Past 30 Days\n31, Next7Day, Next 7 Days\n32, Next14Day, Next 14 Days\n33, Next33Day, Next 33 Days\n```\n",
                  "max": null,
                  "min": null,
                  "name": "filters",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The fields to used for sorting",
                    "zh_Hans": "用于确定排序的字段，不超过3个"
                  },
                  "label": {
                    "en_US": "Sort Fields",
                    "zh_Hans": "排序字段"
                  },
                  "llm_description": "This optional parameter specifies the unique identifier of the fields that will be used to sort the results. It is in the format of an array of JSON objects, and its structure is defined as follows:\n```\ntype SortByFields = {\n  controlId: string; // Field ID used for sorting\n  isAsc: boolean; // Sorting direction, true indicates ascending order, false indicates descending order\n}[];\n```\n",
                  "max": null,
                  "min": null,
                  "name": "sort_fields",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The address for the privately deployed HAP server.",
                    "zh_Hans": "私有部署 HAP 服务器地址，公有云无需填写"
                  },
                  "label": {
                    "en_US": "Host Address",
                    "zh_Hans": "服务器地址"
                  },
                  "llm_description": "the address for the privately deployed HAP server.",
                  "max": null,
                  "min": null,
                  "name": "host",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "table",
                  "form": "form",
                  "human_description": {
                    "en_US": "used for selecting the result type, table styled text or json text",
                    "zh_Hans": "用于选择结果类型，使用表格格式文本还是JSON格式文本"
                  },
                  "label": {
                    "en_US": "Result type",
                    "zh_Hans": "结果类型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "result_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "table text",
                        "zh_Hans": "表格文本"
                      },
                      "value": "table"
                    },
                    {
                      "label": {
                        "en_US": "json text",
                        "zh_Hans": "JSON文本"
                      },
                      "value": "json"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:07:18Z",
        "version_updated_at": "2025-02-17T07:07:18Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Nominatim is a search engine for OpenStreetMap data",
          "ja_JP": "NominatimはOpenStreetMapデータの検索エンジンです",
          "zh_Hans": "Nominatim是OpenStreetMap数据的搜索引擎"
        },
        "category": "tool",
        "created_at": "2024-12-05T05:51:46Z",
        "endpoint": {},
        "icon": "langgenius/packages/nominatim/_assets/icon.svg",
        "index_id": "langgenius___nominatim",
        "install_count": 357,
        "introduction": "## Overview\n\n**Nominatim** is a powerful geocoding tool for accessing and interacting with OpenStreetMap (OSM) data.\n\nIn **Dify**, Nominatim allows you to search for locations, reverse geocode coordinates, and look up OSM objects by their IDs. It streamlines the process of retrieving geographic information, making it easy to integrate location-based services into your applications.\n\n## Configuration \n\nTo start using **Nominatim**, follow these steps:\n\n1. **Install the Nominatim Tool** Open the Plugin Marketplace, search for the Nominatim tool, and install it to integrate it with your application.\n\n2. **Get a Nominatim API Key** Go to the [API Key Management](https://nominatim.org/) page of the Nominatim service, create a new API Key, and ensure your account has the required permissions to access the service.\n\n3. **Authorize the Nominatim Tool** In Dify, go to **Plugins > Nominatim > Authorize**. Enter your API Key to activate the tool.\n\n![](./_assets/nominatim-01.png)\n\n## Tool Features\n\nThe **Nominatim** plugin provides three primary actions to interact with OSM data:\n\n### 1. Nominatim OSM Lookup\n\nThis feature allows you to retrieve information about specific OSM objects using their unique IDs.\n\n* **Input:** A comma-separated list of OSM IDs (e.g., `N123, W456, R789`).\n\n<img src=\"./_assets/nominatim-02.png\" width=\"400\" />\n\n### 2. Nominatim Search\n\nPerform forward geocoding by searching for addresses or place names.\n\n* **Input:** Enter an address or place name in the \"Search Query\" field.\n* **Optional:** Set the \"Result Limit\" to control the maximum number of search results (default: 10).\n\n<img src=\"./_assets/nominatim-03.png\" width=\"400\" />\n\n### 3. Nominatim Reverse Geocoding\n\nConvert geographic coordinates (latitude and longitude) into a human-readable address.\n\n* **Input:** Provide latitude and longitude values.\n\n<img src=\"./_assets/nominatim-04.png\" width=\"400\" />\n\n## Usage\n\n**Nominatim** can be integrated into both Chatflow / Workflow Apps and Agent Apps for a variety of use cases.\n\n### Chatflow / Workflow Apps\n\n1. Add the Nominatim node to your Chatflow or Workflow pipeline.\n2. Configure the input variables for the action you want to perform (e.g., OSM Lookup, Search, Reverse Geocoding).\n3. Run the pipeline to process geographic queries and deliver results as part of the workflow.\n\n![](./_assets/nominatim-05.png)\n\n### Agent Apps\n\n1. Add the Nominatim tool to your Agent application.\n2. Send a query via the chat interface (e.g., enter coordinates for reverse geocoding or search for a place).\n3. The tool processes the query and returns the corresponding data.\n\n![](./_assets/nominatim-06.png)\n\n## Use Cases\n\n* **Location Search:** Find geographic details for specific addresses or place names.\n* **Reverse Geocoding:** Convert GPS coordinates into readable addresses for mapping or reporting.\n* **OSM Object Lookup:** Retrieve detailed data for OSM objects using their unique identifiers.\n* **Geographic Analysis:** Analyze and visualize geographic data for applications like logistics or urban planning.\n\nWith **Nominatim**, you can streamline your access to OpenStreetMap data and build powerful location-based applications with ease.\n",
        "label": {
          "en_US": "Nominatim",
          "ja_JP": "Nominatim",
          "zh_Hans": "Nominatim"
        },
        "latest_package_identifier": "langgenius/nominatim:0.0.3@3e03cec82809ea523aba74322c8eb2acb6a862c7c6cfd42c2fa6898935e8bc9c",
        "latest_version": "0.0.3",
        "model": {},
        "name": "nominatim",
        "org": "langgenius",
        "plugin_id": "langgenius/nominatim",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/nominatim.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "utilities"
          },
          {
            "name": "search"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": "https://nominatim.openstreetmap.org",
              "helper": null,
              "label": {
                "en_US": "Nominatim Base URL",
                "ja_JP": "Nominatim ベースURL",
                "zh_Hans": "Nominatim 基础 URL"
              },
              "name": "base_url",
              "options": null,
              "placeholder": {
                "en_US": "Enter your Nominatim instance URL (default: https://nominatim.openstreetmap.org)",
                "ja_JP": "NominatimインスタンスのURLを入力してください（デフォルト：https://nominatim.openstreetmap.org）",
                "zh_Hans": "输入您的Nominatim实例URL（默认：https://nominatim.openstreetmap.org）"
              },
              "required": false,
              "scope": null,
              "type": "text-input",
              "url": "https://nominatim.org/"
            }
          ],
          "identity": {
            "author": "Charles Zhou",
            "description": {
              "en_US": "Nominatim is a search engine for OpenStreetMap data",
              "ja_JP": "NominatimはOpenStreetMapデータの検索エンジンです",
              "zh_Hans": "Nominatim是OpenStreetMap数据的搜索引擎"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Nominatim",
              "ja_JP": "Nominatim",
              "zh_Hans": "Nominatim"
            },
            "name": "nominatim",
            "tags": [
              "search",
              "utilities"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Look up OSM objects using their IDs with Nominatim",
                  "ja_JP": "Nominatimを使用してIDでOSMオブジェクトを検索",
                  "zh_Hans": "使用Nominatim通过ID查找OSM对象"
                },
                "llm": "A tool for looking up OpenStreetMap objects using their IDs with Nominatim."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Charles Zhou",
                "label": {
                  "en_US": "Nominatim OSM Lookup",
                  "ja_JP": "Nominatim OSM ルックアップ",
                  "zh_Hans": "Nominatim OSM 对象查找"
                },
                "name": "nominatim_lookup"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Comma-separated list of OSM IDs to lookup (e.g., N123,W456,R789)",
                    "ja_JP": "検索するOSM IDのカンマ区切りリスト（例：N123,W456,R789）",
                    "zh_Hans": "要查找的OSM ID的逗号分隔列表（例如：N123,W456,R789）"
                  },
                  "label": {
                    "en_US": "OSM IDs",
                    "ja_JP": "OSM ID",
                    "zh_Hans": "OSM ID"
                  },
                  "llm_description": "A comma-separated list of OSM IDs (prefixed with N, W, or R) for lookup.",
                  "max": null,
                  "min": null,
                  "name": "osm_ids",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Search for locations using Nominatim",
                  "ja_JP": "Nominatimを使用して場所を検索",
                  "zh_Hans": "使用Nominatim搜索位置"
                },
                "llm": "A tool for geocoding using Nominatim, which can search for locations based on addresses or place names."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Charles Zhou",
                "label": {
                  "en_US": "Nominatim Search",
                  "ja_JP": "Nominatim 検索",
                  "zh_Hans": "Nominatim 搜索"
                },
                "name": "nominatim_search"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Enter an address or place name to search for",
                    "ja_JP": "検索する住所または場所の名前を入力してください",
                    "zh_Hans": "输入要搜索的地址或地名"
                  },
                  "label": {
                    "en_US": "Search Query",
                    "ja_JP": "検索クエリ",
                    "zh_Hans": "搜索查询"
                  },
                  "llm_description": "The search query for Nominatim, which can be an address or place name.",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 10,
                  "form": "form",
                  "human_description": {
                    "en_US": "Maximum number of results to return (default: 10, max: 40)",
                    "ja_JP": "返す結果の最大数（デフォルト：10、最大：40）",
                    "zh_Hans": "要返回的最大结果数（默认：10，最大：40）"
                  },
                  "label": {
                    "en_US": "Result Limit",
                    "ja_JP": "結果の制限",
                    "zh_Hans": "结果限制"
                  },
                  "llm_description": "Limit the number of returned results. The default is 10, and the maximum is 40.",
                  "max": 40,
                  "min": 1,
                  "name": "limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Convert coordinates to addresses using Nominatim",
                  "ja_JP": "Nominatimを使用して座標を住所に変換",
                  "zh_Hans": "使用Nominatim将坐标转换为地址"
                },
                "llm": "A tool for reverse geocoding using Nominatim, which can convert latitude and longitude coordinates to an address."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Charles Zhou",
                "label": {
                  "en_US": "Nominatim Reverse Geocoding",
                  "ja_JP": "Nominatim リバースジオコーディング",
                  "zh_Hans": "Nominatim 反向地理编码"
                },
                "name": "nominatim_reverse"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Latitude coordinate for reverse geocoding",
                    "ja_JP": "リバースジオコーディングの緯度座標",
                    "zh_Hans": "用于反向地理编码的纬度坐标"
                  },
                  "label": {
                    "en_US": "Latitude",
                    "ja_JP": "緯度",
                    "zh_Hans": "纬度"
                  },
                  "llm_description": "The latitude coordinate for reverse geocoding.",
                  "max": null,
                  "min": null,
                  "name": "lat",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Longitude coordinate for reverse geocoding",
                    "ja_JP": "リバースジオコーディングの経度座標",
                    "zh_Hans": "用于反向地理编码的经度坐标"
                  },
                  "label": {
                    "en_US": "Longitude",
                    "ja_JP": "経度",
                    "zh_Hans": "经度"
                  },
                  "llm_description": "The longitude coordinate for reverse geocoding.",
                  "max": null,
                  "min": null,
                  "name": "lon",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:08:00Z",
        "version_updated_at": "2025-02-17T07:08:00Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "integration for google sheets",
          "ja_JP": "integration for google sheets",
          "pt_BR": "integration for google sheets",
          "zh_Hans": "integration for google sheets"
        },
        "category": "tool",
        "created_at": "2025-03-31T12:26:51Z",
        "endpoint": {},
        "icon": "omluc/packages/google_sheets/_assets/icon.svg",
        "index_id": "omluc___google_sheets",
        "install_count": 351,
        "introduction": "## google_sheets\n\n**Author:** omluc\n**Version:** 0.0.1\n**Type:** tool\n\n### Description\n\n\n\nThis plugin provides a set of tools for integrating Google Sheets with Dify applications. It allows you to read and write data in Google Sheets directly from your Dify workflows and agents.\n\n### Tools Included\n\n-   **Batch Get**: Efficiently retrieve data from multiple ranges within a Google Sheet.\n-   **Batch Update**: Efficiently update data in multiple ranges within a Google Sheet.\n\n### Setup\n\n#### Prerequisites\n\n-   A Google Cloud Platform account.\n-   A Google Cloud project with the Google Sheets API enabled.\n-   A service account with appropriate permissions for Google Sheets.\n\n#### Creating a Service Account\n\n1.  Go to the [Google Cloud Console](https://console.cloud.google.com/).\n2.  Create a new project or select an existing one.\n3.  Enable the Google Sheets API for your project.\n4.  Create a service account:\n    -   Go to \"IAM & Admin\" > \"Service Accounts\".\n    -   Click \"Create Service Account\".\n    -   Give it a name and description.\n    -   Grant it appropriate roles (e.g., \"Sheets Editor\").\n    -   Click \"Create\".\n5.  Create a key for the service account:\n    -   Click on the service account you just created.\n    -   Go to the \"Keys\" tab.\n    -   Click \"Add Key\" > \"Create new key\".\n    -   Choose JSON format and click \"Create\".\n    -   Save the downloaded JSON file securely.\n\n#### Configuration in Dify\n\n1.  In your Dify application, go to the Plugins section.\n2.  Find and install the Google Sheets plugin.\n3.  When configuring the plugin, you'll need to provide:\n    -   `credentials_json`: The entire content of the service account JSON key file.\n\n### Usage Examples\n\n#### Batch Get\n\nUse the Batch Get tool to retrieve data from multiple ranges.\n\n```json\nInput:\n{\n  \"spreadsheet_id\": \"your_spreadsheet_id\",\n  \"ranges\": [\"Sheet1!A1:C3\", \"Sheet2!B2:D4\"]\n}\n\nOutput:\n{\n    \"spreadsheetId\": \"your_spreadsheet_id\",\n    \"valueRanges\": [\n        {\n            \"range\": \"Sheet1!A1:C3\",\n            \"values\": [\n                [\"Header1\", \"Header2\", \"Header3\"],\n                [\"Value1\", \"Value2\", \"Value3\"],\n                [\"Value4\", \"Value5\", \"Value6\"]\n            ]\n        },\n        {\n            \"range\": \"Sheet2!B2:D4\",\n            \"values\": [\n                [\"HeaderA\", \"HeaderB\", \"HeaderC\"],\n                [\"ValueA1\", \"ValueB1\", \"ValueC1\"],\n                [\"ValueA2\", \"ValueB2\", \"ValueC2\"]\n            ]\n        }\n    ]\n}\n```\n\n#### Batch Update\nUse the 'Batch Update' tool to update multiple ranges in a sheet.\n```json\nInput:\n{\n\"spreadsheet_id\": \"your_spreadsheet_id\",\n\"data\": [\n    {\n        \"range\": \"Sheet1!A1:B2\",\n        \"values\": [\n            [\"NewHeader1\", \"NewHeader2\"],\n            [\"NewValue1\", \"NewValue2\"]\n        ]\n    },\n     {\n        \"range\": \"Sheet2!C3:D4\",\n        \"values\": [\n            [\"Updated1\", \"Updated2\"],\n            [\"Updated3\", \"Updated4\"]\n        ]\n    }\n]\n}\n\nOutput:\n{\n    \"spreadsheetId\": \"your_spreadsheet_id\",\n    \"totalUpdatedRows\": 4,\n    \"totalUpdatedColumns\": 2,\n    \"totalUpdatedCells\": 8,\n    \"responses\": [\n      {\n        \"updatedRange\": \"Sheet1!A1:B2\"\n      },\n      {\n        \"updatedRange\": \"Sheet2!C3:D4\"\n      }\n    ]\n\n}\n```\n\n### Permissions and Security\n\n-   The tools operate with the permissions of the service account you configured.\n-   To access user-specific sheets, you'll need to share those sheets with the service account's email address.\n-   For shared drives, the service account needs to be added as a member of the shared drive.\n\n### Troubleshooting\n\n-   If you encounter issues:\n    -   Verify that the Google Sheets API is enabled in your Google Cloud project.\n    -   Check that the service account has the necessary permissions.\n    -   Ensure the credentials JSON is correctly formatted and complete.\n    -   For \"Sheet not found\" errors, verify that the sheet exists and is accessible to the service account.\n    - Make sure the sheet name is correct.\n\n### Support\n\nFor issues or feature requests, please open an issue in the Dify Official Plugins repository.\n\n",
        "label": {
          "en_US": "google_sheets",
          "ja_JP": "google_sheets",
          "pt_BR": "google_sheets",
          "zh_Hans": "google_sheets"
        },
        "latest_package_identifier": "omluc/google_sheets:0.0.1@e6aca931acea96a0dcc2884a68e05fd42bab952334300a3c67fddcdb7992f18c",
        "latest_version": "0.0.1",
        "model": {},
        "name": "google_sheets",
        "org": "omluc",
        "plugin_id": "omluc/google_sheets",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/google_sheets.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "The service account JSON key for Google Sheets API",
                "ja_JP": "Google スプレッドシート API のサービスアカウント JSON キー",
                "pt_BR": "A chave JSON da conta de serviço para a API do Google Sheets",
                "zh_Hans": "Google 表格 API 的服务账号 JSON 密钥"
              },
              "label": {
                "en_US": "Credentials JSON",
                "ja_JP": "認証情報 JSON",
                "pt_BR": "Credenciais JSON",
                "zh_Hans": "凭证 JSON"
              },
              "name": "credentials_json",
              "options": null,
              "placeholder": {
                "en_US": "Enter your Google Sheets API credentials JSON",
                "ja_JP": "Google スプレッドシート API のサービスアカウント JSON キー",
                "pt_BR": "Digite sua chave JSON de credenciais da API do Google Sheets",
                "zh_Hans": "输入您的 Google Sheets API 凭证 JSON"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://console.cloud.google.com/apis/credentials"
            }
          ],
          "identity": {
            "author": "omluc",
            "description": {
              "en_US": "Integration for Google Sheets to read and write data",
              "ja_JP": "Google スプレッドシートのデータ読み取りと書き込みのための連携",
              "pt_BR": "Integração com Google Sheets para ler e escrever dados",
              "zh_Hans": "Google 表格集成，用于读取和写入数据"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Google Sheets",
              "ja_JP": "Google スプレッドシート",
              "pt_BR": "Google Planilhas",
              "zh_Hans": "Google 表格"
            },
            "name": "google_sheets",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Retrieve data from multiple ranges in a Google Sheet",
                  "pt_BR": "Recuperar dados de múltiplos intervalos em uma planilha Google",
                  "zh_Hans": "从 Google 表格中的多个范围检索数据"
                },
                "llm": "Retrieve data from multiple ranges in a Google Sheet at once"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "omluc",
                "label": {
                  "en_US": "Batch Get",
                  "pt_BR": "Obter em Lote",
                  "zh_Hans": "批量获取"
                },
                "name": "batch_get"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the Google Sheet (found in the URL)",
                    "pt_BR": "O ID da planilha Google (encontrado na URL)",
                    "zh_Hans": "Google 表格的 ID（在 URL 中）"
                  },
                  "label": {
                    "en_US": "Spreadsheet ID",
                    "pt_BR": "ID da Planilha",
                    "zh_Hans": "表格 ID"
                  },
                  "llm_description": "The ID of the Google Sheet, which can be found in the sheet's URL",
                  "max": null,
                  "min": null,
                  "name": "spreadsheet_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "List of ranges to retrieve (e.g. [\"Sheet1!A1:C3\", \"Sheet2!B2:D4\"])",
                    "pt_BR": "Lista de intervalos para recuperar (ex. [\"Sheet1!A1:C3\", \"Sheet2!B2:D4\"])",
                    "zh_Hans": "要检索的范围列表（例如 [\"Sheet1!A1:C3\", \"Sheet2!B2:D4\"]）"
                  },
                  "label": {
                    "en_US": "Ranges",
                    "pt_BR": "Intervalos",
                    "zh_Hans": "范围列表"
                  },
                  "llm_description": "An array of range strings to retrieve in A1 notation or R1C1 notation (e.g. [\"Sheet1!A1:C3\", \"Sheet2!B2:D4\"])",
                  "max": null,
                  "min": null,
                  "name": "ranges",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "SERIAL_NUMBER",
                  "form": "form",
                  "human_description": {
                    "en_US": "How dates, times, and durations should be represented in the output",
                    "pt_BR": "Como datas, horários e durações devem ser representados na saída",
                    "zh_Hans": "日期、时间和持续时间在输出中的表示方式"
                  },
                  "label": {
                    "en_US": "Date Time Render Option",
                    "pt_BR": "Opção de Renderização de Data e Hora",
                    "zh_Hans": "日期时间渲染选项"
                  },
                  "llm_description": "How dates, times, and durations should be represented in the output",
                  "max": null,
                  "min": null,
                  "name": "date_time_render_option",
                  "options": [
                    {
                      "label": {
                        "en_US": "SERIAL_NUMBER",
                        "pt_BR": "NÚMERO DE SÉRIE",
                        "zh_Hans": "序列号"
                      },
                      "value": "SERIAL_NUMBER"
                    },
                    {
                      "label": {
                        "en_US": "FORMATTED_STRING",
                        "pt_BR": "STRING FORMATADA",
                        "zh_Hans": "格式化字符串"
                      },
                      "value": "FORMATTED_STRING"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The major dimension that results should use",
                    "pt_BR": "A dimensão principal que os resultados devem usar",
                    "zh_Hans": "结果应使用的主要维度"
                  },
                  "label": {
                    "en_US": "Major Dimension",
                    "pt_BR": "Dimensão Principal",
                    "zh_Hans": "主要维度"
                  },
                  "llm_description": "The major dimension that results should use (ROWS or COLUMNS)",
                  "max": null,
                  "min": null,
                  "name": "major_dimension",
                  "options": [
                    {
                      "label": {
                        "en_US": "ROWS",
                        "pt_BR": "LINHAS",
                        "zh_Hans": "行"
                      },
                      "value": "ROWS"
                    },
                    {
                      "label": {
                        "en_US": "COLUMNS",
                        "pt_BR": "COLUNAS",
                        "zh_Hans": "列"
                      },
                      "value": "COLUMNS"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "How values should be represented in the output",
                    "pt_BR": "Como os valores devem ser representados na saída",
                    "zh_Hans": "值在输出中的表示方式"
                  },
                  "label": {
                    "en_US": "Value Render Option",
                    "pt_BR": "Opção de Renderização de Valor",
                    "zh_Hans": "值渲染选项"
                  },
                  "llm_description": "How values should be represented in the output",
                  "max": null,
                  "min": null,
                  "name": "value_render_option",
                  "options": [
                    {
                      "label": {
                        "en_US": "FORMATTED_VALUE",
                        "pt_BR": "VALOR FORMATADO",
                        "zh_Hans": "格式化值"
                      },
                      "value": "FORMATTED_VALUE"
                    },
                    {
                      "label": {
                        "en_US": "FORMULA",
                        "pt_BR": "FÓRMULA",
                        "zh_Hans": "公式"
                      },
                      "value": "FORMULA"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Update data in multiple ranges in a Google Sheet",
                  "pt_BR": "Atualizar dados em múltiplos intervalos em uma planilha Google",
                  "zh_Hans": "更新 Google 表格中多个范围的数据"
                },
                "llm": "Update data in multiple ranges in a Google Sheet at once"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "omluc",
                "label": {
                  "en_US": "Batch Update",
                  "pt_BR": "Atualizar em Lote",
                  "zh_Hans": "批量更新"
                },
                "name": "batch_update"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the Google Sheet (found in the URL)",
                    "pt_BR": "O ID da planilha Google (encontrado na URL)",
                    "zh_Hans": "Google 表格的 ID（在 URL 中）"
                  },
                  "label": {
                    "en_US": "Spreadsheet ID",
                    "pt_BR": "ID da Planilha",
                    "zh_Hans": "表格 ID"
                  },
                  "llm_description": "The ID of the Google Sheet, which can be found in the sheet's URL",
                  "max": null,
                  "min": null,
                  "name": "spreadsheet_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "JSON array of objects, each with 'range' (A1 notation like 'Sheet1!A1:B5') and 'values' (2D array of cell values). Example - [{\"range\":\"Sheet1!A1:B2\", \"values\":[[\"Name\",\"Age\"],[\"John\",30]]}]",
                    "pt_BR": "Array JSON de objetos, cada um com 'range' (notação A1 como 'Sheet1!A1:B5') e 'values' (array 2D de valores de célula). Exemplo - [{\"range\":\"Sheet1!A1:B2\", \"values\":[[\"Nome\",\"Idade\"],[\"João\",30]]}]",
                    "zh_Hans": "JSON 对象数组，每个对象包含 'range'（A1 表示法，如 'Sheet1!A1:B5'）和 'values'（单元格值的二维数组）。例如 - [{\"range\":\"Sheet1!A1:B2\", \"values\":[[\"姓名\",\"年龄\"],[\"约翰\",30]]}]"
                  },
                  "label": {
                    "en_US": "Data",
                    "pt_BR": "Dados",
                    "zh_Hans": "数据"
                  },
                  "llm_description": "An array of objects to update in Google Sheets. Each object must contain - 1) 'range' - A string in A1 notation specifying the cells (e.g., 'A1:B5', 'Sheet1!A1:B5', or 'MyNamedRange'), and 2) 'values' - A 2D array representing row/column values to insert. Example - [{\"range\":\"Sheet1!A1:B2\", \"values\":[[\"Header1\",\"Header2\"],[\"Value1\",\"Value2\"]]}]. The dimensions of 'values' must match the range, and you can update multiple non-contiguous ranges in a single request.",
                  "max": null,
                  "min": null,
                  "name": "data",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "USER_ENTERED",
                  "form": "form",
                  "human_description": {
                    "en_US": "How the input data should be interpreted",
                    "pt_BR": "Como os dados de entrada devem ser interpretados",
                    "zh_Hans": "如何解释输入数据"
                  },
                  "label": {
                    "en_US": "Value Input Option",
                    "pt_BR": "Opção de Entrada de Valor",
                    "zh_Hans": "值输入选项"
                  },
                  "llm_description": "How the input data should be interpreted",
                  "max": null,
                  "min": null,
                  "name": "value_input_option",
                  "options": [
                    {
                      "label": {
                        "en_US": "USER_ENTERED",
                        "pt_BR": "ENTRADA DO USUÁRIO",
                        "zh_Hans": "用户输入"
                      },
                      "value": "USER_ENTERED"
                    },
                    {
                      "label": {
                        "en_US": "RAW",
                        "pt_BR": "BRUTO",
                        "zh_Hans": "原始"
                      },
                      "value": "RAW"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to include the values in the response",
                    "pt_BR": "Se deve incluir os valores na resposta",
                    "zh_Hans": "是否在响应中包含值"
                  },
                  "label": {
                    "en_US": "Include Values in Response",
                    "pt_BR": "Incluir Valores na Resposta",
                    "zh_Hans": "在响应中包含值"
                  },
                  "llm_description": "Whether to include the values in the response",
                  "max": null,
                  "min": null,
                  "name": "include_values_in_response",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "How the values in the response should be rendered",
                    "pt_BR": "Como os valores na resposta devem ser renderizados",
                    "zh_Hans": "响应中的值应如何渲染"
                  },
                  "label": {
                    "en_US": "Response Value Render Option",
                    "pt_BR": "Opção de Renderização de Valor da Resposta",
                    "zh_Hans": "响应值渲染选项"
                  },
                  "llm_description": "How the values in the response should be rendered",
                  "max": null,
                  "min": null,
                  "name": "response_value_render_option",
                  "options": [
                    {
                      "label": {
                        "en_US": "FORMATTED_VALUE",
                        "pt_BR": "VALOR FORMATADO",
                        "zh_Hans": "格式化值"
                      },
                      "value": "FORMATTED_VALUE"
                    },
                    {
                      "label": {
                        "en_US": "FORMULA",
                        "pt_BR": "FÓRMULA",
                        "zh_Hans": "公式"
                      },
                      "value": "FORMULA"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "How dates, times, and durations in the response should be rendered",
                    "pt_BR": "Como datas, horários e durações na resposta devem ser renderizados",
                    "zh_Hans": "响应中的日期、时间和持续时间应如何渲染"
                  },
                  "label": {
                    "en_US": "Response Date Time Render Option",
                    "pt_BR": "Opção de Renderização de Data e Hora da Resposta",
                    "zh_Hans": "响应日期时间渲染选项"
                  },
                  "llm_description": "How dates, times, and durations in the response should be rendered",
                  "max": null,
                  "min": null,
                  "name": "response_date_time_render_option",
                  "options": [
                    {
                      "label": {
                        "en_US": "SERIAL_NUMBER",
                        "pt_BR": "NÚMERO DE SÉRIE",
                        "zh_Hans": "序列号"
                      },
                      "value": "SERIAL_NUMBER"
                    },
                    {
                      "label": {
                        "en_US": "FORMATTED_STRING",
                        "pt_BR": "STRING FORMATADA",
                        "zh_Hans": "格式化字符串"
                      },
                      "value": "FORMATTED_STRING"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-31T12:26:58Z",
        "version_updated_at": "2025-03-31T12:26:58Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Secure File Transfer Protocol (SFTP) client for remote file operations",
          "ja_JP": "リモートファイル操作のためのセキュアファイル転送プロトコル (SFTP) クライアント",
          "zh_Hans": "安全文件传输协议 (SFTP) 客户端，用于远程文件操作"
        },
        "category": "tool",
        "created_at": "2025-04-17T15:04:06Z",
        "endpoint": {},
        "icon": "stvlynn/packages/sftp/_assets/icon.png",
        "index_id": "stvlynn___sftp",
        "install_count": 336,
        "introduction": "# SFTP Plugin for Dify\n\n**Author:** [Steven Lynn](https://github.com/stvlynn)\n**Version:** 0.0.1\n**Type:** tool\n\n## Description\n\nSFTP (Secure File Transfer Protocol) plugin for Dify, allowing secure file operations on remote servers. The plugin provides file listing, downloading, uploading, and management capabilities.\n\n## Features\n\nThe plugin provides the following actions:\n\n### 1. List Directory\n\nLists files and directories in a remote location via SFTP, showing details like file size, modification time, and file type.\n\n### 2. Download File\n\nDownloads a file from the remote server and returns it directly as a file attachment for easy access.\n\n### 3. Upload File\n\nUploads files to the remote server using Dify's file variable system for direct file uploads.\n\n### 4. Manage Files and Directories\n\nProvides various file and directory management operations:\n- Create directory\n- Delete file/directory\n- Rename file/directory\n\n## Authentication\n\nThe plugin supports two authentication methods:\n- **Password authentication**: Using username and password\n- **Private key authentication**: Using username and private key (with optional passphrase)\n\n## Parameters\n\n### Common Parameters for All Tools\n\n| Parameter | Type | Required | Description |\n|-----------|------|----------|-------------|\n| host | string | Yes | Hostname or IP address of the remote server |\n| port | number | No | SSH port, default is 22 |\n| username | string | Yes | Username for authentication |\n| auth_type | select | Yes | Authentication type: password or key |\n| password | string | Conditional | Password for password authentication (required if auth_type is password) |\n| private_key | string | Conditional | Private key content for key authentication (required if auth_type is key) |\n| passphrase | string | No | Passphrase for the private key (if the key is encrypted) |\n\n### List Directory Parameters\n\n![](./_assets/list-dir.png)\n\n| Parameter | Type | Required | Description |\n|-----------|------|----------|-------------|\n| remote_path | string | Yes | Directory path on the remote server to list |\n\n### Download File Parameters\n\n![](./_assets/download-file.png)\n\n| Parameter | Type | Required | Description |\n|-----------|------|----------|-------------|\n| remote_path | string | Yes | Path to the file on the remote server |\n\n### Upload File Parameters\n\n![](./_assets/upload-file.png)\n\n| Parameter | Type | Required | Description |\n|-----------|------|----------|-------------|\n| remote_path | string | Yes | Path where to save the file on the remote server |\n| files | files | Yes | File(s) to upload to the remote server |\n\n### Manage Files Parameters\n\n![](./_assets/manage-file.png)\n\n| Parameter | Type | Required | Description |\n|-----------|------|----------|-------------|\n| action | select | Yes | Action to perform (rename, delete, create directory) |\n| path | string | Yes | Path to file or directory on remote server |\n| new_path | string | Conditional | New path for rename operation (required if action is rename) |\n\n## Usage Examples\n\n### List Directory Example\n\n```json\n{\n    \"host\": \"example.com\",\n    \"port\": 22,\n    \"username\": \"user\",\n    \"auth_type\": \"password\",\n    \"password\": \"your_password\",\n    \"remote_path\": \"/home/user\"\n}\n```\n\n### Download File Example\n\n```json\n{\n    \"host\": \"example.com\",\n    \"port\": 22,\n    \"username\": \"user\",\n    \"auth_type\": \"password\",\n    \"password\": \"your_password\",\n    \"remote_path\": \"/home/user/file.txt\"\n}\n```\n\n### Upload File Example\n\n```json\n{\n    \"host\": \"example.com\",\n    \"port\": 22,\n    \"username\": \"user\",\n    \"auth_type\": \"key\",\n    \"private_key\": \"-----BEGIN RSA PRIVATE KEY-----\\n...\\n-----END RSA PRIVATE KEY-----\",\n    \"remote_path\": \"/home/user/\",\n    \"files\": [file1, file2]\n}\n```\n\n### Manage Files Example\n\n```json\n{\n    \"host\": \"example.com\",\n    \"port\": 22,\n    \"username\": \"user\",\n    \"auth_type\": \"password\",\n    \"password\": \"your_password\",\n    \"action\": \"mkdir\",\n    \"path\": \"/home/user/new_directory\"\n}\n```\n\n## Security Considerations\n\n- Ensure you have permission to access the target server\n- Sensitive information such as private keys and passwords should be kept secure\n- Store sensitive credentials in the Dify Environment Variables section as secrets\n- Follow the principle of least privilege when accessing remote servers\n\n## License\n\n[MIT](./LICENSE)\n\n## Feedback and Issues\n\nIf you encounter any problems or have suggestions for improvements:\n\n1. Please open an issue in the [plugin's GitHub repository](https://github.com/stvlynn/sftp-Dify-Plugin/issues)\n\n2. Provide details about your problem, including error messages and steps to reproduce\n\n3. **Do not** submit issues to the main [Dify](https://github.com/langgenius/dify) repository for plugin-specific problems\n\n\n\n\n",
        "label": {
          "en_US": "SFTP Client",
          "ja_JP": "SFTP クライアント",
          "zh_Hans": "SFTP 客户端"
        },
        "latest_package_identifier": "stvlynn/sftp:0.0.1@812240b6e43950ec6b51c795e17ae30d391adb093a6fee3760c508e6bbe1033d",
        "latest_version": "0.0.1",
        "model": {},
        "name": "sftp",
        "org": "stvlynn",
        "plugin_id": "stvlynn/sftp",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/sftp.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {}
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "stvlynn",
            "description": {
              "en_US": "Secure File Transfer Protocol operations",
              "zh_Hans": "安全文件传输协议操作"
            },
            "icon": "icon.png",
            "label": {
              "en_US": "SFTP Operations",
              "zh_Hans": "SFTP 操作"
            },
            "name": "sftp_provider",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "List files and directories in a remote directory via SFTP",
                  "zh_Hans": "通过SFTP列出远程目录中的文件和子目录"
                },
                "llm": "Lists files and directories in a remote directory via SFTP, showing details like file size, modification time and file type."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "stvlynn",
                "label": {
                  "en_US": "List Directory",
                  "zh_Hans": "列出目录"
                },
                "name": "list"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Remote server hostname or IP address",
                    "zh_Hans": "远程服务器主机名或IP地址"
                  },
                  "label": {
                    "en_US": "Host",
                    "zh_Hans": "主机地址"
                  },
                  "llm_description": "The hostname or IP address of the remote SFTP server",
                  "max": null,
                  "min": null,
                  "name": "host",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 22,
                  "form": "llm",
                  "human_description": {
                    "en_US": "SFTP port number (default 22)",
                    "zh_Hans": "SFTP端口号（默认22）"
                  },
                  "label": {
                    "en_US": "Port",
                    "zh_Hans": "端口"
                  },
                  "llm_description": "The port number for the SFTP connection",
                  "max": null,
                  "min": null,
                  "name": "port",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Username for authentication",
                    "zh_Hans": "用于认证的用户名"
                  },
                  "label": {
                    "en_US": "Username",
                    "zh_Hans": "用户名"
                  },
                  "llm_description": "Username for authenticating with the SFTP server",
                  "max": null,
                  "min": null,
                  "name": "username",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "password",
                  "form": "form",
                  "human_description": {
                    "en_US": "Choose between password or private key authentication",
                    "zh_Hans": "选择密码或私钥认证"
                  },
                  "label": {
                    "en_US": "Authentication Type",
                    "zh_Hans": "认证类型"
                  },
                  "llm_description": "The authentication method to use (password or private key).",
                  "max": null,
                  "min": null,
                  "name": "auth_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "Password",
                        "zh_Hans": "密码"
                      },
                      "value": "password"
                    },
                    {
                      "label": {
                        "en_US": "Private Key",
                        "zh_Hans": "私钥"
                      },
                      "value": "key"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The password for password authentication (required if auth_type is password)",
                    "zh_Hans": "用于密码认证的密码（如果认证类型为密码则必填）"
                  },
                  "label": {
                    "en_US": "Password",
                    "zh_Hans": "密码"
                  },
                  "llm_description": "The password for password authentication. Required if auth_type is password.",
                  "max": null,
                  "min": null,
                  "name": "password",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The private key for key authentication (required if auth_type is key)",
                    "zh_Hans": "用于密钥认证的私钥（如果认证类型为私钥则必填）"
                  },
                  "label": {
                    "en_US": "Private Key",
                    "zh_Hans": "私钥"
                  },
                  "llm_description": "The private key content for key-based authentication. Required if auth_type is key.",
                  "max": null,
                  "min": null,
                  "name": "private_key",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The passphrase for the private key (if the key is encrypted)",
                    "zh_Hans": "私钥的密码（如果私钥已加密）"
                  },
                  "label": {
                    "en_US": "Passphrase",
                    "zh_Hans": "密钥口令"
                  },
                  "llm_description": "The passphrase for the private key if it is encrypted. Optional.",
                  "max": null,
                  "min": null,
                  "name": "passphrase",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Directory path on the remote server to list",
                    "zh_Hans": "要列出的远程服务器上的目录路径"
                  },
                  "label": {
                    "en_US": "Remote Path",
                    "zh_Hans": "远程路径"
                  },
                  "llm_description": "The directory path to list",
                  "max": null,
                  "min": null,
                  "name": "remote_path",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Download a file from a remote server via SFTP",
                  "zh_Hans": "通过SFTP从远程服务器下载文件"
                },
                "llm": "Downloads a file from a remote server via SFTP and returns it as a file attachment."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "stvlynn",
                "label": {
                  "en_US": "Download File",
                  "zh_Hans": "下载文件"
                },
                "name": "download"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Remote server hostname or IP address",
                    "zh_Hans": "远程服务器主机名或IP地址"
                  },
                  "label": {
                    "en_US": "Host",
                    "zh_Hans": "主机地址"
                  },
                  "llm_description": "The hostname or IP address of the remote SFTP server",
                  "max": null,
                  "min": null,
                  "name": "host",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 22,
                  "form": "llm",
                  "human_description": {
                    "en_US": "SFTP port number (default 22)",
                    "zh_Hans": "SFTP端口号（默认22）"
                  },
                  "label": {
                    "en_US": "Port",
                    "zh_Hans": "端口"
                  },
                  "llm_description": "The port number for the SFTP connection",
                  "max": null,
                  "min": null,
                  "name": "port",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Username for authentication",
                    "zh_Hans": "用于认证的用户名"
                  },
                  "label": {
                    "en_US": "Username",
                    "zh_Hans": "用户名"
                  },
                  "llm_description": "Username for authenticating with the SFTP server",
                  "max": null,
                  "min": null,
                  "name": "username",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "password",
                  "form": "form",
                  "human_description": {
                    "en_US": "Choose between password or private key authentication",
                    "zh_Hans": "选择密码或私钥认证"
                  },
                  "label": {
                    "en_US": "Authentication Type",
                    "zh_Hans": "认证类型"
                  },
                  "llm_description": "The authentication method to use (password or private key).",
                  "max": null,
                  "min": null,
                  "name": "auth_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "Password",
                        "zh_Hans": "密码"
                      },
                      "value": "password"
                    },
                    {
                      "label": {
                        "en_US": "Private Key",
                        "zh_Hans": "私钥"
                      },
                      "value": "key"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The password for password authentication (required if auth_type is password)",
                    "zh_Hans": "用于密码认证的密码（如果认证类型为密码则必填）"
                  },
                  "label": {
                    "en_US": "Password",
                    "zh_Hans": "密码"
                  },
                  "llm_description": "The password for password authentication. Required if auth_type is password.",
                  "max": null,
                  "min": null,
                  "name": "password",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The private key for key authentication (required if auth_type is key)",
                    "zh_Hans": "用于密钥认证的私钥（如果认证类型为私钥则必填）"
                  },
                  "label": {
                    "en_US": "Private Key",
                    "zh_Hans": "私钥"
                  },
                  "llm_description": "The private key content for key-based authentication. Required if auth_type is key.",
                  "max": null,
                  "min": null,
                  "name": "private_key",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The passphrase for the private key (if the key is encrypted)",
                    "zh_Hans": "私钥的密码（如果私钥已加密）"
                  },
                  "label": {
                    "en_US": "Passphrase",
                    "zh_Hans": "密钥口令"
                  },
                  "llm_description": "The passphrase for the private key if it is encrypted. Optional.",
                  "max": null,
                  "min": null,
                  "name": "passphrase",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Path to the file on the remote server",
                    "zh_Hans": "远程服务器上文件的路径"
                  },
                  "label": {
                    "en_US": "Remote File Path",
                    "zh_Hans": "远程文件路径"
                  },
                  "llm_description": "The path to the file to download",
                  "max": null,
                  "min": null,
                  "name": "remote_path",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Upload a file to a remote server via SFTP",
                  "zh_Hans": "通过SFTP上传文件到远程服务器"
                },
                "llm": "Uploads a file to a remote server via SFTP."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "stvlynn",
                "label": {
                  "en_US": "Upload File",
                  "zh_Hans": "上传文件"
                },
                "name": "upload"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Remote server hostname or IP address",
                    "zh_Hans": "远程服务器主机名或IP地址"
                  },
                  "label": {
                    "en_US": "Host",
                    "zh_Hans": "主机地址"
                  },
                  "llm_description": "The hostname or IP address of the remote SFTP server",
                  "max": null,
                  "min": null,
                  "name": "host",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 22,
                  "form": "llm",
                  "human_description": {
                    "en_US": "SFTP port number (default 22)",
                    "zh_Hans": "SFTP端口号（默认22）"
                  },
                  "label": {
                    "en_US": "Port",
                    "zh_Hans": "端口"
                  },
                  "llm_description": "The port number for the SFTP connection",
                  "max": null,
                  "min": null,
                  "name": "port",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Username for authentication",
                    "zh_Hans": "用于认证的用户名"
                  },
                  "label": {
                    "en_US": "Username",
                    "zh_Hans": "用户名"
                  },
                  "llm_description": "Username for authenticating with the SFTP server",
                  "max": null,
                  "min": null,
                  "name": "username",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "password",
                  "form": "form",
                  "human_description": {
                    "en_US": "Choose between password or private key authentication",
                    "zh_Hans": "选择密码或私钥认证"
                  },
                  "label": {
                    "en_US": "Authentication Type",
                    "zh_Hans": "认证类型"
                  },
                  "llm_description": "The authentication method to use (password or private key).",
                  "max": null,
                  "min": null,
                  "name": "auth_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "Password",
                        "zh_Hans": "密码"
                      },
                      "value": "password"
                    },
                    {
                      "label": {
                        "en_US": "Private Key",
                        "zh_Hans": "私钥"
                      },
                      "value": "key"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The password for password authentication (required if auth_type is password)",
                    "zh_Hans": "用于密码认证的密码（如果认证类型为密码则必填）"
                  },
                  "label": {
                    "en_US": "Password",
                    "zh_Hans": "密码"
                  },
                  "llm_description": "The password for password authentication. Required if auth_type is password.",
                  "max": null,
                  "min": null,
                  "name": "password",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The private key for key authentication (required if auth_type is key)",
                    "zh_Hans": "用于密钥认证的私钥（如果认证类型为私钥则必填）"
                  },
                  "label": {
                    "en_US": "Private Key",
                    "zh_Hans": "私钥"
                  },
                  "llm_description": "The private key content for key-based authentication. Required if auth_type is key.",
                  "max": null,
                  "min": null,
                  "name": "private_key",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The passphrase for the private key (if the key is encrypted)",
                    "zh_Hans": "私钥的密码（如果私钥已加密）"
                  },
                  "label": {
                    "en_US": "Passphrase",
                    "zh_Hans": "密钥口令"
                  },
                  "llm_description": "The passphrase for the private key if it is encrypted. Optional.",
                  "max": null,
                  "min": null,
                  "name": "passphrase",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Path where to save the file on the remote server",
                    "zh_Hans": "在远程服务器上保存文件的路径"
                  },
                  "label": {
                    "en_US": "Remote File Path",
                    "zh_Hans": "远程文件路径"
                  },
                  "llm_description": "The path on the remote server to save the file",
                  "max": null,
                  "min": null,
                  "name": "remote_path",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Files to upload to the remote server",
                    "zh_Hans": "要上传到远程服务器的文件"
                  },
                  "label": {
                    "en_US": "Upload Files",
                    "zh_Hans": "上传文件"
                  },
                  "llm_description": "The files to upload to the remote server",
                  "max": null,
                  "min": null,
                  "name": "files",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "files"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Manage files and directories on a remote server via SFTP (rename, delete, mkdir)",
                  "zh_Hans": "通过SFTP管理远程服务器上的文件和目录（重命名、删除、创建目录）"
                },
                "llm": "Manages files and directories on a remote server via SFTP. This includes operations like rename, delete, and create directory."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "stvlynn",
                "label": {
                  "en_US": "Manage Files",
                  "zh_Hans": "管理文件"
                },
                "name": "manage"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Remote server hostname or IP address",
                    "zh_Hans": "远程服务器主机名或IP地址"
                  },
                  "label": {
                    "en_US": "Host",
                    "zh_Hans": "主机地址"
                  },
                  "llm_description": "The hostname or IP address of the remote SFTP server",
                  "max": null,
                  "min": null,
                  "name": "host",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 22,
                  "form": "llm",
                  "human_description": {
                    "en_US": "SFTP port number (default 22)",
                    "zh_Hans": "SFTP端口号（默认22）"
                  },
                  "label": {
                    "en_US": "Port",
                    "zh_Hans": "端口"
                  },
                  "llm_description": "The port number for the SFTP connection",
                  "max": null,
                  "min": null,
                  "name": "port",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Username for authentication",
                    "zh_Hans": "用于认证的用户名"
                  },
                  "label": {
                    "en_US": "Username",
                    "zh_Hans": "用户名"
                  },
                  "llm_description": "Username for authenticating with the SFTP server",
                  "max": null,
                  "min": null,
                  "name": "username",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "password",
                  "form": "form",
                  "human_description": {
                    "en_US": "Choose between password or private key authentication",
                    "zh_Hans": "选择密码或私钥认证"
                  },
                  "label": {
                    "en_US": "Authentication Type",
                    "zh_Hans": "认证类型"
                  },
                  "llm_description": "The authentication method to use (password or private key).",
                  "max": null,
                  "min": null,
                  "name": "auth_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "Password",
                        "zh_Hans": "密码"
                      },
                      "value": "password"
                    },
                    {
                      "label": {
                        "en_US": "Private Key",
                        "zh_Hans": "私钥"
                      },
                      "value": "key"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The password for password authentication (required if auth_type is password)",
                    "zh_Hans": "用于密码认证的密码（如果认证类型为密码则必填）"
                  },
                  "label": {
                    "en_US": "Password",
                    "zh_Hans": "密码"
                  },
                  "llm_description": "The password for password authentication. Required if auth_type is password.",
                  "max": null,
                  "min": null,
                  "name": "password",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The private key for key authentication (required if auth_type is key)",
                    "zh_Hans": "用于密钥认证的私钥（如果认证类型为私钥则必填）"
                  },
                  "label": {
                    "en_US": "Private Key",
                    "zh_Hans": "私钥"
                  },
                  "llm_description": "The private key content for key-based authentication. Required if auth_type is key.",
                  "max": null,
                  "min": null,
                  "name": "private_key",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The passphrase for the private key (if the key is encrypted)",
                    "zh_Hans": "私钥的密码（如果私钥已加密）"
                  },
                  "label": {
                    "en_US": "Passphrase",
                    "zh_Hans": "密钥口令"
                  },
                  "llm_description": "The passphrase for the private key if it is encrypted. Optional.",
                  "max": null,
                  "min": null,
                  "name": "passphrase",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Action to perform (rename, delete, create directory)",
                    "zh_Hans": "要执行的操作（重命名、删除、创建目录）"
                  },
                  "label": {
                    "en_US": "Action",
                    "zh_Hans": "操作"
                  },
                  "llm_description": "The action to perform",
                  "max": null,
                  "min": null,
                  "name": "action",
                  "options": [
                    {
                      "label": {
                        "en_US": "Rename",
                        "zh_Hans": "重命名"
                      },
                      "value": "rename"
                    },
                    {
                      "label": {
                        "en_US": "Delete",
                        "zh_Hans": "删除"
                      },
                      "value": "delete"
                    },
                    {
                      "label": {
                        "en_US": "Create Directory",
                        "zh_Hans": "创建目录"
                      },
                      "value": "mkdir"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Path to file or directory on remote server",
                    "zh_Hans": "远程服务器上的文件或目录路径"
                  },
                  "label": {
                    "en_US": "Path",
                    "zh_Hans": "路径"
                  },
                  "llm_description": "The path to the file or directory on the remote server",
                  "max": null,
                  "min": null,
                  "name": "path",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "New path for rename operation",
                    "zh_Hans": "重命名操作的新路径"
                  },
                  "label": {
                    "en_US": "New Path",
                    "zh_Hans": "新路径"
                  },
                  "llm_description": "The new path for rename operations",
                  "max": null,
                  "min": null,
                  "name": "new_path",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-17T15:04:21Z",
        "version_updated_at": "2025-04-17T15:04:21Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Crossref is a cross-publisher reference linking registration query system using DOI technology created in 2000. Crossref establishes cross-database links between the reference list and citation full text of papers, making it very convenient for readers to access the full text of papers.",
          "zh_Hans": "Crossref是于2000年创建的使用DOI技术的跨出版商参考文献链接注册查询系统。Crossref建立了在论文的参考文献列表和引文全文之间的跨数据库链接，使得读者能够非常便捷地获取文献全文。"
        },
        "category": "tool",
        "created_at": "2024-12-02T13:17:23Z",
        "endpoint": {},
        "icon": "langgenius/packages/crossref/_assets/icon.svg",
        "index_id": "langgenius___crossref",
        "install_count": 323,
        "introduction": "# CrossRef Integration and Usage in Dify\n\n## Overview\n\nCrossRef is a research discovery and linking tool. It helps researchers, librarians, and publishers find, connect, and cite scholarly publications. It leverages a vast database of metadata, offering features like similarity searches, citation lookups, and identifier resolution. In Dify, **it helps users to query literature information by DOI and by title**.\n\n## Configuration\n\n### 1. Get CrossRef tools from Plugin Marketplace\n\nThe CrossRef tools could be found at the Plugin Marketplace, please install it first.\n\n### 2. Fill in the configuration in Dify\n\nOn the Dify navigation page, click `Tools > CrossRef > Authorize` and fill in your email address. For more details, please check [this link](https://api.crossref.org/swagger-ui/index.html#/).\n\n![](./_assets/crossref_1.PNG)\n\n### 3. Using the tool\n\nYou can use the CrossRef tool in the following application types:\n\n![](./_assets/crossref_2.PNG)\n\n#### Chatflow / Workflow applications\n\nBoth Chatflow and Workflow applications support the `CrossRef` tool node.\n\n#### Agent applications\n\nAdd the `CrossRef` tool in the Agent application, then enter the literature command to call this tool.",
        "label": {
          "en_US": "CrossRef",
          "zh_Hans": "CrossRef"
        },
        "latest_package_identifier": "langgenius/crossref:0.0.2@2f79d9a8773a3c0e42958a3c21891dc315c71844c0542c850086e89c0de933ac",
        "latest_version": "0.0.2",
        "model": {},
        "name": "crossref",
        "org": "langgenius",
        "plugin_id": "langgenius/crossref",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/crossref.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "search"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "email address",
                "pt_BR": "email address",
                "zh_Hans": "email地址"
              },
              "name": "mailto",
              "options": null,
              "placeholder": {
                "en_US": "Please input your email address",
                "pt_BR": "Please input your email address",
                "zh_Hans": "请输入你的email地址"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": "https://api.crossref.org/swagger-ui/index.html"
            }
          ],
          "identity": {
            "author": "Sakura4036",
            "description": {
              "en_US": "Crossref is a cross-publisher reference linking registration query system using DOI technology created in 2000. Crossref establishes cross-database links between the reference list and citation full text of papers, making it very convenient for readers to access the full text of papers.",
              "zh_Hans": "Crossref是于2000年创建的使用DOI技术的跨出版商参考文献链接注册查询系统。Crossref建立了在论文的参考文献列表和引文全文之间的跨数据库链接，使得读者能够非常便捷地获取文献全文。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "CrossRef",
              "zh_Hans": "CrossRef"
            },
            "name": "crossref",
            "tags": [
              "search"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool for querying literature information using CrossRef by title.",
                  "pt_BR": "A tool for querying literature information using CrossRef by title.",
                  "zh_Hans": "一个使用CrossRef通过标题搜索文献信息的工具。"
                },
                "llm": "A tool for querying literature information using CrossRef by title."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Sakura4036",
                "label": {
                  "en_US": "CrossRef Title Query",
                  "pt_BR": "CrossRef Title Query",
                  "zh_Hans": "CrossRef 标题查询"
                },
                "name": "crossref_query_title"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Query bibliographic information, useful for citation look up. Includes titles, authors, ISSNs and publication years",
                    "pt_BR": "Query bibliographic information, useful for citation look up. Includes titles, authors, ISSNs and publication years",
                    "zh_Hans": "用于搜索文献信息，有助于查找引用。包括标题，作者，ISSN和出版年份"
                  },
                  "label": {
                    "en_US": "标题",
                    "pt_BR": "标题",
                    "zh_Hans": "查询语句"
                  },
                  "llm_description": "key words for querying in Web of Science",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "used for selecting the query type, fuzzy query returns more results, precise query returns 1 or none",
                    "pt_BR": "used for selecting the query type, fuzzy query returns more results, precise query returns 1 or none",
                    "zh_Hans": "用于选择搜索类型，模糊搜索返回更多结果，精确搜索返回1条结果或无"
                  },
                  "label": {
                    "en_US": "Whether to fuzzy search",
                    "pt_BR": "Whether to fuzzy search",
                    "zh_Hans": "是否模糊搜索"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "fuzzy_query",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": 50,
                  "form": "llm",
                  "human_description": {
                    "en_US": "max query number(fuzzy search returns the maximum number of results or precise search the maximum number of matches)",
                    "pt_BR": "max query number(fuzzy search returns the maximum number of results or precise search the maximum number of matches)",
                    "zh_Hans": "最大搜索数(模糊搜索返回的最大结果数或精确搜索最大匹配数)"
                  },
                  "label": {
                    "en_US": "max query number",
                    "pt_BR": "max query number",
                    "zh_Hans": "最大搜索数"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "relevance",
                  "form": "form",
                  "human_description": {
                    "en_US": "Sorting of query results",
                    "pt_BR": "Sorting of query results",
                    "zh_Hans": "检索结果的排序字段"
                  },
                  "label": {
                    "en_US": "sorting field",
                    "pt_BR": "sorting field",
                    "zh_Hans": "排序字段"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "sort",
                  "options": [
                    {
                      "label": {
                        "en_US": "relevance",
                        "pt_BR": "relevance",
                        "zh_Hans": "相关性"
                      },
                      "value": "relevance"
                    },
                    {
                      "label": {
                        "en_US": "publication date",
                        "pt_BR": "publication date",
                        "zh_Hans": "出版日期"
                      },
                      "value": "published"
                    },
                    {
                      "label": {
                        "en_US": "references-count",
                        "pt_BR": "references-count",
                        "zh_Hans": "引用次数"
                      },
                      "value": "references-count"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "desc",
                  "form": "form",
                  "human_description": {
                    "en_US": "Order of query results",
                    "pt_BR": "Order of query results",
                    "zh_Hans": "检索结果的排序方式"
                  },
                  "label": {
                    "en_US": "Order",
                    "pt_BR": "Order",
                    "zh_Hans": "排序"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "order",
                  "options": [
                    {
                      "label": {
                        "en_US": "descending",
                        "pt_BR": "descending",
                        "zh_Hans": "降序"
                      },
                      "value": "desc"
                    },
                    {
                      "label": {
                        "en_US": "ascending",
                        "pt_BR": "ascending",
                        "zh_Hans": "升序"
                      },
                      "value": "asc"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for searching literature information using CrossRef by DOI.",
                  "pt_BR": "A tool for searching literature information using CrossRef by DOI.",
                  "zh_Hans": "一个使用CrossRef通过DOI获取文献信息的工具。"
                },
                "llm": "A tool for searching literature information using CrossRef by DOI."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Sakura4036",
                "label": {
                  "en_US": "CrossRef Query DOI",
                  "pt_BR": "CrossRef Query DOI",
                  "zh_Hans": "CrossRef DOI 查询"
                },
                "name": "crossref_query_doi"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "DOI for searching in CrossRef",
                    "pt_BR": "DOI for searching in CrossRef",
                    "zh_Hans": "用于在CrossRef中搜索的DOI"
                  },
                  "label": {
                    "en_US": "DOI",
                    "pt_BR": "DOI",
                    "zh_Hans": "DOI"
                  },
                  "llm_description": "DOI for searching in CrossRef",
                  "max": null,
                  "min": null,
                  "name": "doi",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:10:26Z",
        "version_updated_at": "2025-02-17T07:10:26Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Generate presentation slides using SlideSpeak API",
          "zh_Hans": "使用 SlideSpeak API 生成演示幻灯片"
        },
        "category": "tool",
        "created_at": "2024-12-04T08:18:35Z",
        "endpoint": {},
        "icon": "langgenius/packages/slidespeak/_assets/icon.png",
        "index_id": "langgenius___slidespeak",
        "install_count": 312,
        "introduction": "## Overview\n\n**SlideSpeak** is a powerful tool for generating presentation slides from text.\n\nIn **Dify**, SlideSpeak streamlines the process of creating visually engaging slides based on the content you provide. Whether you're preparing for meetings, lectures, or pitches, SlideSpeak enables efficient slide creation with minimal effort.\n\n## Configuration\n\nTo start using **SlideSpeak**, follow these steps:\n\n1. **Install the SlideSpeak Tool** Open the Plugin Marketplace, search for the SlideSpeak tool, and install it to integrate it with your application.\n\n2. **Get a SlideSpeak API Key** Visit the SlideSpeak platform, create a new API Key, and ensure your account has the necessary permissions to access its features.\n\n3. **Authorize SlideSpeak** In Dify, go to **Plugins > SlideSpeak > To Authorize**. Enter your API Key to activate the tool.\n\n![](./_assets/slidespeak-01.png)\n\n## Tool Features\n\nThe **SlideSpeak** plugin includes a single, highly efficient action:\n\n### Slides Generator\n\nCreate presentation slides from text-based topics or content.\n\n**Input Variables:**\n\n* **Topic or Content (Required):** Provide the text or topic to be converted into slides.\n\nThis action simplifies slide creation by automatically generating layouts, summaries, and key points from your text.\n\n<img src=\"./_assets/slidespeak-02.png\" width=\"400\" alt=\"SlideSpeak Tool Interface\" />\n\n## Usage\n\n**SlideSpeak can seamlessly integrate Chatflow / Workflow Apps and Agent Apps.**\n\n### Chatflow / Workflow Apps\n\n1. Add the SlideSpeak node to your Chatflow or Workflow pipeline.\n2. Configure the \"Slides Generator\" action by specifying the topic or content.\n3. Run the pipeline to generate slides and deliver them as part of your workflow.\n\n![](./_assets/slidespeak-03.png)\n\n### Agent Apps\n\n1. Add the SlideSpeak tool to your Agent application.\n2. Provide the topic or content via the chat interface.\n3. The tool processes your input and returns the generated presentation slides.\n\n![](./_assets/slidespeak-04.png)\n\n## Use Cases\n\n* **Presentations:** Quickly create slides for business meetings, academic lectures, or project pitches.\n* **Content Summarization:** Convert long documents or ideas into concise, well-structured slides.\n* **Educational Material:** Generate slides for courses, tutorials, or workshops.\n* **Idea Sharing:** Create visually engaging slides to present concepts or ideas.\n\nWith **SlideSpeak**, you can save time and effort by automating the slide creation process, focusing more on delivering impactful presentations.\n",
        "label": {
          "en_US": "SlideSpeak",
          "zh_Hans": "SlideSpeak"
        },
        "latest_package_identifier": "langgenius/slidespeak:0.0.4@76577047ef9e44a0732f521a4f4be90ef76f0492bb64e3a2145a8966c4615d95",
        "latest_version": "0.0.4",
        "model": {},
        "name": "slidespeak",
        "org": "langgenius",
        "plugin_id": "langgenius/slidespeak",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/slidespeak.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "API Key",
                "zh_Hans": "API 密钥"
              },
              "name": "slidespeak_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Enter your SlideSpeak API key",
                "zh_Hans": "输入您的 SlideSpeak API 密钥"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://app.slidespeak.co/settings/developer"
            }
          ],
          "identity": {
            "author": "Kalo Chin",
            "description": {
              "en_US": "Generate presentation slides using SlideSpeak API",
              "zh_Hans": "使用 SlideSpeak API 生成演示幻灯片"
            },
            "icon": "icon.png",
            "label": {
              "en_US": "SlideSpeak",
              "zh_Hans": "SlideSpeak"
            },
            "name": "slidespeak",
            "tags": []
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Generate presentation slides from text using SlideSpeak API.",
                  "zh_Hans": "使用 SlideSpeak API 从文本生成演示幻灯片。"
                },
                "llm": "This tool converts text input into a presentation using the SlideSpeak API service, with options for slide length and theme."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Kalo Chin",
                "label": {
                  "en_US": "Slides Generator",
                  "zh_Hans": "幻灯片生成器"
                },
                "name": "slide_generator"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The topic or content to be converted into presentation slides.",
                    "zh_Hans": "需要转换为幻灯片的内容或主题。"
                  },
                  "label": {
                    "en_US": "Topic or Content",
                    "zh_Hans": "主题或内容"
                  },
                  "llm_description": "A string containing the topic or content to be transformed into presentation slides.",
                  "max": null,
                  "min": null,
                  "name": "plain_text",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The desired number of slides in the presentation (optional).",
                    "zh_Hans": "演示文稿中所需的幻灯片数量（可选）。"
                  },
                  "label": {
                    "en_US": "Number of Slides",
                    "zh_Hans": "幻灯片数量"
                  },
                  "llm_description": "Optional parameter specifying the number of slides to generate.",
                  "max": null,
                  "min": null,
                  "name": "length",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The visual theme for the presentation (optional).",
                    "zh_Hans": "演示文稿的视觉主题（可选）。"
                  },
                  "label": {
                    "en_US": "Presentation Theme",
                    "zh_Hans": "演示主题"
                  },
                  "llm_description": "Optional parameter specifying the presentation theme.",
                  "max": null,
                  "min": null,
                  "name": "theme",
                  "options": [
                    {
                      "label": {
                        "en_US": "Adam",
                        "zh_Hans": "Adam"
                      },
                      "value": "adam"
                    },
                    {
                      "label": {
                        "en_US": "Aurora",
                        "zh_Hans": "Aurora"
                      },
                      "value": "aurora"
                    },
                    {
                      "label": {
                        "en_US": "Bruno",
                        "zh_Hans": "Bruno"
                      },
                      "value": "bruno"
                    },
                    {
                      "label": {
                        "en_US": "Clyde",
                        "zh_Hans": "Clyde"
                      },
                      "value": "clyde"
                    },
                    {
                      "label": {
                        "en_US": "Daniel",
                        "zh_Hans": "Daniel"
                      },
                      "value": "daniel"
                    },
                    {
                      "label": {
                        "en_US": "Default",
                        "zh_Hans": "Default"
                      },
                      "value": "default"
                    },
                    {
                      "label": {
                        "en_US": "Eddy",
                        "zh_Hans": "Eddy"
                      },
                      "value": "eddy"
                    },
                    {
                      "label": {
                        "en_US": "Felix",
                        "zh_Hans": "Felix"
                      },
                      "value": "felix"
                    },
                    {
                      "label": {
                        "en_US": "Gradient",
                        "zh_Hans": "Gradient"
                      },
                      "value": "gradient"
                    },
                    {
                      "label": {
                        "en_US": "Iris",
                        "zh_Hans": "Iris"
                      },
                      "value": "iris"
                    },
                    {
                      "label": {
                        "en_US": "Lavender",
                        "zh_Hans": "Lavender"
                      },
                      "value": "lavender"
                    },
                    {
                      "label": {
                        "en_US": "Monolith",
                        "zh_Hans": "Monolith"
                      },
                      "value": "monolith"
                    },
                    {
                      "label": {
                        "en_US": "Nebula",
                        "zh_Hans": "Nebula"
                      },
                      "value": "nebula"
                    },
                    {
                      "label": {
                        "en_US": "Nexus",
                        "zh_Hans": "Nexus"
                      },
                      "value": "nexus"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-11T09:50:17Z",
        "version_updated_at": "2025-03-11T09:50:17Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Upstage"
        },
        "category": "model",
        "created_at": "2025-02-17T07:00:36Z",
        "endpoint": {},
        "icon": "langgenius/packages/upstage/_assets/icon_s_en.svg",
        "index_id": "langgenius___upstage",
        "install_count": 308,
        "introduction": "",
        "label": {
          "en_US": "upstage"
        },
        "latest_package_identifier": "langgenius/upstage:0.0.5@1cf7681087471c379a93b99730ac3b978c88a738a47fb137ddb04dd9db2600ab",
        "latest_version": "0.0.5",
        "model": {
          "background": "#FFFFF",
          "configurate_methods": [
            "predefined-model"
          ],
          "description": {
            "en_US": "Models provided by Upstage, such as Solar-1-mini-chat.",
            "zh_Hans": "Upstage 提供的模型，例如 Solar-1-mini-chat."
          },
          "help": {
            "title": {
              "en_US": "Get your API Key from Upstage",
              "zh_Hans": "从 Upstage 获取 API Key"
            },
            "url": {
              "en_US": "https://console.upstage.ai/api-keys"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.svg"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "Upstage"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "upstage_api_key"
              }
            ],
            "model": {
              "label": {
                "en_US": "Model Name",
                "zh_Hans": "模型名称"
              },
              "placeholder": {
                "en_US": "Enter your model name",
                "zh_Hans": "输入模型名称"
              }
            }
          },
          "models": [
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "solar-1-mini-chat",
                "zh_Hans": "solar-1-mini-chat"
              },
              "model": "solar-1-mini-chat",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 512,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 32768,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "If specified, model will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.",
                    "zh_Hans": "如果指定，模型将尽最大努力进行确定性采样，使得重复的具有相同种子和参数的请求应该返回相同的结果。不能保证确定性，您应该参考 system_fingerprint 响应参数来监视变化。"
                  },
                  "label": {
                    "en_US": "Seed",
                    "zh_Hans": "种子"
                  },
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.5",
                "output": "0.5",
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "solar-embedding-1-large-passage"
              },
              "model": "solar-embedding-1-large-passage",
              "model_properties": {
                "context_size": 4000,
                "max_chunks": 32
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.1",
                "output": null,
                "unit": "0.000001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "solar-embedding-1-large-query"
              },
              "model": "solar-embedding-1-large-query",
              "model_properties": {
                "context_size": 4000,
                "max_chunks": 32
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.1",
                "output": null,
                "unit": "0.000001"
              }
            }
          ],
          "position": {
            "llm": [
              "solar-1-mini-chat"
            ]
          },
          "provider": "upstage",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "upstage_api_key"
              }
            ]
          },
          "supported_model_types": [
            "llm",
            "text-embedding"
          ]
        },
        "name": "upstage",
        "org": "langgenius",
        "plugin_id": "langgenius/upstage",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/upstage.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-02-28T14:11:09Z",
        "version_updated_at": "2025-02-28T14:11:09Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "ElevenLabs TTS/STT provider",
          "ja_JP": "ElevenLabs TTS/STT provider",
          "pt_BR": "ElevenLabs TTS/STT provider",
          "zh_Hans": "ElevenLabs TTS/STT provider"
        },
        "category": "model",
        "created_at": "2025-03-31T16:09:09Z",
        "endpoint": {},
        "icon": "cdpath/packages/dify-elevenlabs-provider/_assets/icon.svg",
        "index_id": "cdpath___dify-elevenlabs-provider",
        "install_count": 302,
        "introduction": "# ElevenLabs Provider for Dify\n\nA Dify plugin for integrating ElevenLabs Text-to-Speech and Speech-to-Text services.\n\n## Features\n\n- **Text-to-Speech (TTS)**: Convert text to high-quality, natural-sounding speech using ElevenLabs' advanced voice synthesis technology.\n- **Speech-to-Text (STT)**: Transcribe audio to text with accurate speech recognition.\n\n## Setup\n\n1. Install the plugin in your Dify instance\n2. Configure the plugin with your ElevenLabs API key\n3. Use the ElevenLabs models in your Dify applications\n\n## Requirements\n\n- An [ElevenLabs account](https://elevenlabs.io/)\n- ElevenLabs API key, available from your [ElevenLabs account page](https://elevenlabs.io/app/settings/api-keys)\n\n## Models\n\n### Text-to-Speech\n\n- **Model**: `eleven_multilingual_v2`\n- **Voices**: Aria, Roger, Sarah, Laura, Charlie, George, Callum, River, Liam, Charlotte, Alice, Matilda, Will, Jessica, Eric, Chris, Brian, Daniel, Lily, Bill, Koby\n- **Default Voice**: Sarah\n\n### Speech-to-Text\n\n- **Model**: `scribe_v1`\n- **Mode**: transcription\n- **Supported File Extensions**: mp3, mp4, mpeg, mpga, m4a, wav, webm\n- **File Upload Limit**: 25MB\n\n## License\n\nThis plugin is provided under the MIT license.\n\n",
        "label": {
          "en_US": "ElevenLabs",
          "ja_JP": "ElevenLabs",
          "pt_BR": "ElevenLabs",
          "zh_Hans": "ElevenLabs"
        },
        "latest_package_identifier": "cdpath/dify-elevenlabs-provider:0.0.2@35eacbd89c1597a2064d554f8918197f214958718be6fd43a2917a432d9a47d8",
        "latest_version": "0.0.2",
        "model": {
          "background": "#000000",
          "configurate_methods": [
            "predefined-model",
            "customizable-model"
          ],
          "description": {
            "en_US": "Models provided by ElevenLabs.",
            "zh_Hans": "ElevenLabs 提供的模型。"
          },
          "help": {
            "title": {
              "en_US": "Get your API Key from ElevenLabs",
              "zh_Hans": "从 ElevenLabs 获取 API Key"
            },
            "url": {
              "en_US": "https://elevenlabs.io/app/settings/api-keys"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.svg"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "ElevenLabs"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your ElevenLabs API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              }
            ],
            "model": {
              "label": {
                "en_US": "Model Name",
                "zh_Hans": "模型名称"
              },
              "placeholder": {
                "en_US": "Enter your model name",
                "zh_Hans": "输入模型名称"
              }
            }
          },
          "models": [
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "scribe_v1"
              },
              "model": "scribe_v1",
              "model_properties": {
                "context_size": 25600,
                "file_upload_limit": 25,
                "mode": "transcription",
                "supported_file_extensions": [
                  "mp3",
                  "mp4",
                  "mpeg",
                  "mpga",
                  "m4a",
                  "wav",
                  "webm"
                ]
              },
              "model_type": "speech2text",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.25",
                "output": "0",
                "unit": "1"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "eleven_multilingual_v2"
              },
              "model": "eleven_multilingual_v2",
              "model_properties": {
                "audio_type": "mp3",
                "default_voice": "Sarah",
                "max_workers": 5,
                "voices": [
                  {
                    "language": [
                      "en-US"
                    ],
                    "mode": "9BWtsMINqrJLrRacOk9x",
                    "name": "Aria"
                  },
                  {
                    "language": [
                      "en-US"
                    ],
                    "mode": "CwhRBWXzGAHq8TQ4Fs17",
                    "name": "Roger"
                  },
                  {
                    "language": [
                      "en-US"
                    ],
                    "mode": "EXAVITQu4vr4xnSDxMaL",
                    "name": "Sarah"
                  },
                  {
                    "language": [
                      "en-US"
                    ],
                    "mode": "FGY2WhTYpPnrIDTdsKH5",
                    "name": "Laura"
                  },
                  {
                    "language": [
                      "en-US"
                    ],
                    "mode": "IKne3meq5aSn9XLyUdCD",
                    "name": "Charlie"
                  },
                  {
                    "language": [
                      "en-US"
                    ],
                    "mode": "JBFqnCBsd6RMkjVDRZzb",
                    "name": "George"
                  },
                  {
                    "language": [
                      "en-US"
                    ],
                    "mode": "N2lVS1w4EtoT3dr4eOWO",
                    "name": "Callum"
                  },
                  {
                    "language": [
                      "en-US"
                    ],
                    "mode": "SAz9YHcvj6GT2YYXdXww",
                    "name": "River"
                  },
                  {
                    "language": [
                      "en-US"
                    ],
                    "mode": "TX3LPaxmHKxFdv7VOQHJ",
                    "name": "Liam"
                  },
                  {
                    "language": [
                      "en-US"
                    ],
                    "mode": "XB0fDUnXU5powFXDhCwa",
                    "name": "Charlotte"
                  },
                  {
                    "language": [
                      "en-US"
                    ],
                    "mode": "Xb7hH8MSUJpSbSDYk0k2",
                    "name": "Alice"
                  },
                  {
                    "language": [
                      "en-US"
                    ],
                    "mode": "XrExE9yKIg1WjnnlVkGX",
                    "name": "Matilda"
                  },
                  {
                    "language": [
                      "en-US"
                    ],
                    "mode": "bIHbv24MWmeRgasZH58o",
                    "name": "Will"
                  },
                  {
                    "language": [
                      "en-US"
                    ],
                    "mode": "cgSgspJ2msm6clMCkdW9",
                    "name": "Jessica"
                  },
                  {
                    "language": [
                      "en-US"
                    ],
                    "mode": "cjVigY5qzO86Huf0OWal",
                    "name": "Eric"
                  },
                  {
                    "language": [
                      "en-US"
                    ],
                    "mode": "iP95p4xoKVk53GoZ742B",
                    "name": "Chris"
                  },
                  {
                    "language": [
                      "en-US"
                    ],
                    "mode": "nPczCjzI2devNBz1zQrb",
                    "name": "Brian"
                  },
                  {
                    "language": [
                      "en-US"
                    ],
                    "mode": "onwK4e9ZLuTAKqWW03F9",
                    "name": "Daniel"
                  },
                  {
                    "language": [
                      "en-US"
                    ],
                    "mode": "pFZP5JQG7iQjIQuC4Bku",
                    "name": "Lily"
                  },
                  {
                    "language": [
                      "en-US"
                    ],
                    "mode": "pqHfZKP75CvOlQylNhV4",
                    "name": "Bill"
                  },
                  {
                    "language": [
                      "en-US"
                    ],
                    "mode": "7V2labMjY8jnJlxDRW75",
                    "name": "Koby"
                  }
                ],
                "word_limit": 5000
              },
              "model_type": "tts",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.015",
                "output": "0",
                "unit": "0.001"
              }
            }
          ],
          "position": {},
          "provider": "dify-elevenlabs-provider",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your ElevenLabs API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              }
            ]
          },
          "supported_model_types": [
            "tts",
            "speech2text"
          ]
        },
        "name": "dify-elevenlabs-provider",
        "org": "cdpath",
        "plugin_id": "cdpath/dify-elevenlabs-provider",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/dify-elevenlabs-provider.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": false,
              "moderation": false,
              "rerank": false,
              "speech2text": true,
              "text_embedding": false,
              "tts": true
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-03-31T16:09:19Z",
        "version_updated_at": "2025-03-31T16:09:19Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Lark calendar, requires the following permissions: calendar:calendar:read、calendar:calendar、contact:user.id:readonly.\n",
          "zh_Hans": "Lark 日历，需要开通以下权限: calendar:calendar:read、calendar:calendar、contact:user.id:readonly。\n"
        },
        "category": "tool",
        "created_at": "2025-02-26T10:44:59Z",
        "endpoint": {},
        "icon": "langgenius/packages/lark_calendar/_assets/icon.png",
        "index_id": "langgenius___lark_calendar",
        "install_count": 299,
        "introduction": "",
        "label": {
          "en_US": "Lark Calendar",
          "zh_Hans": "Lark 日历"
        },
        "latest_package_identifier": "langgenius/lark_calendar:0.0.1@ba15d15c1a8b81d97a5b75d091da492b2e197b478af19f2a48ab03787f7f1ddc",
        "latest_version": "0.0.1",
        "model": {},
        "name": "lark_calendar",
        "org": "langgenius",
        "plugin_id": "langgenius/lark_calendar",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/lark_calendar.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "social"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "APP ID"
              },
              "name": "app_id",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Lark app id",
                "zh_Hans": "请输入你的 Lark app id"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": "https://open.larksuite.com/app"
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "APP Secret"
              },
              "name": "app_secret",
              "options": null,
              "placeholder": {
                "en_US": "Please input your app secret",
                "zh_Hans": "请输入你的 Lark app secret"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            }
          ],
          "identity": {
            "author": "Doug Lea",
            "description": {
              "en_US": "Lark calendar, requires the following permissions: calendar:calendar:read、calendar:calendar、contact:user.id:readonly.\n",
              "zh_Hans": "Lark 日历，需要开通以下权限: calendar:calendar:read、calendar:calendar、contact:user.id:readonly。\n"
            },
            "icon": "icon.png",
            "label": {
              "en_US": "Lark Calendar",
              "zh_Hans": "Lark 日历"
            },
            "name": "lark_calendar",
            "tags": [
              "social",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Add Event Attendees",
                  "zh_Hans": "添加日程参会人"
                },
                "llm": "A tool for adding attendees to events in Lark. (在 Lark 中添加日程参会人)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Add Event Attendees",
                  "zh_Hans": "添加日程参会人"
                },
                "name": "add_event_attendees"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the event, which will be returned when the event is created. For example: fb2a6406-26d6-4c8d-a487-6f0246c94d2f_0.\n",
                    "zh_Hans": "创建日程时会返回日程 ID。例如: fb2a6406-26d6-4c8d-a487-6f0246c94d2f_0。\n"
                  },
                  "label": {
                    "en_US": "Event ID",
                    "zh_Hans": "日程 ID"
                  },
                  "llm_description": "日程 ID，创建日程时会返回日程 ID。例如: fb2a6406-26d6-4c8d-a487-6f0246c94d2f_0。\n",
                  "max": null,
                  "min": null,
                  "name": "event_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to send a Bot notification to attendees. true: send, false: do not send.\n",
                    "zh_Hans": "是否给参与人发送 Bot 通知，true: 发送，false: 不发送。\n"
                  },
                  "label": {
                    "en_US": "Need Notification",
                    "zh_Hans": "是否需要通知"
                  },
                  "llm_description": "是否给参与人发送 Bot 通知，true: 发送，false: 不发送。\n",
                  "max": null,
                  "min": null,
                  "name": "need_notification",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The list of attendee emails or phone numbers, separated by commas.",
                    "zh_Hans": "日程参会人邮箱或者手机号列表，使用逗号分隔。"
                  },
                  "label": {
                    "en_US": "Attendee Phone or Email",
                    "zh_Hans": "参会人电话或邮箱"
                  },
                  "llm_description": "日程参会人邮箱或者手机号列表，使用逗号分隔。",
                  "max": null,
                  "min": null,
                  "name": "attendee_phone_or_email",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Search Events",
                  "zh_Hans": "搜索日程"
                },
                "llm": "A tool for searching events in Lark.(在 Lark 中搜索日程)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Search Events",
                  "zh_Hans": "搜索日程"
                },
                "name": "search_events"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": "open_id",
                  "form": "form",
                  "human_description": {
                    "en_US": "User ID type, optional values are open_id, union_id, user_id, with a default value of open_id.",
                    "zh_Hans": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。"
                  },
                  "label": {
                    "en_US": "user_id_type",
                    "zh_Hans": "用户 ID 类型"
                  },
                  "llm_description": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。",
                  "max": null,
                  "min": null,
                  "name": "user_id_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "open_id",
                        "zh_Hans": "open_id"
                      },
                      "value": "open_id"
                    },
                    {
                      "label": {
                        "en_US": "union_id",
                        "zh_Hans": "union_id"
                      },
                      "value": "union_id"
                    },
                    {
                      "label": {
                        "en_US": "user_id",
                        "zh_Hans": "user_id"
                      },
                      "value": "user_id"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The search keyword used for fuzzy searching event names, with a maximum input of 200 characters.",
                    "zh_Hans": "用于模糊查询日程名称的搜索关键字，最大输入 200 字符。"
                  },
                  "label": {
                    "en_US": "Query",
                    "zh_Hans": "搜索关键字"
                  },
                  "llm_description": "用于模糊查询日程名称的搜索关键字，最大输入 200 字符。",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The start time, defaults to 0:00 of the current day if not provided, format: 2006-01-02 15:04:05.\n",
                    "zh_Hans": "开始时间，不传值时默认当天 0 点时间，格式为:2006-01-02 15:04:05。"
                  },
                  "label": {
                    "en_US": "Start Time",
                    "zh_Hans": "开始时间"
                  },
                  "llm_description": "开始时间，不传值时默认当天 0 点时间，格式为:2006-01-02 15:04:05。",
                  "max": null,
                  "min": null,
                  "name": "start_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The end time, defaults to 23:59 of the current day if not provided, format: 2006-01-02 15:04:05.\n",
                    "zh_Hans": "结束时间，不传值时默认当天 23:59 分时间，格式为:2006-01-02 15:04:05。"
                  },
                  "label": {
                    "en_US": "End Time",
                    "zh_Hans": "结束时间"
                  },
                  "llm_description": "结束时间，不传值时默认当天 23:59 分时间，格式为:2006-01-02 15:04:05。",
                  "max": null,
                  "min": null,
                  "name": "end_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 20,
                  "form": "form",
                  "human_description": {
                    "en_US": "The page size, i.e., the number of data entries returned in a single request. The default value is 20, and the value range is [10,100].",
                    "zh_Hans": "分页大小，即单次请求所返回的数据条目数。默认值为 20，取值范围为 [10,100]。"
                  },
                  "label": {
                    "en_US": "Page Size",
                    "zh_Hans": "分页大小"
                  },
                  "llm_description": "分页大小，即单次请求所返回的数据条目数。默认值为 20，取值范围为 [10,100]。",
                  "max": null,
                  "min": null,
                  "name": "page_size",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The pagination token. Leave it blank for the first request, indicating to start traversing from the beginning; when the pagination query result has more items, a new page_token will be returned simultaneously, which can be used to obtain the query result in the next traversal.",
                    "zh_Hans": "分页标记，第一次请求不填，表示从头开始遍历；分页查询结果还有更多项时会同时返回新的 page_token，下次遍历可采用该 page_token 获取查询结果。"
                  },
                  "label": {
                    "en_US": "Page Token",
                    "zh_Hans": "分页标记"
                  },
                  "llm_description": "分页标记，第一次请求不填，表示从头开始遍历；分页查询结果还有更多项时会同时返回新的 page_token，下次遍历可采用该 page_token 获取查询结果。",
                  "max": null,
                  "min": null,
                  "name": "page_token",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get Primary Calendar",
                  "zh_Hans": "查询主日历信息"
                },
                "llm": "A tool for querying primary calendar information in Lark.(在 Lark 中查询主日历信息)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Get Primary Calendar",
                  "zh_Hans": "查询主日历信息"
                },
                "name": "get_primary_calendar"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": "open_id",
                  "form": "form",
                  "human_description": {
                    "en_US": "User ID type, optional values are open_id, union_id, user_id, with a default value of open_id.",
                    "zh_Hans": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。"
                  },
                  "label": {
                    "en_US": "user_id_type",
                    "zh_Hans": "用户 ID 类型"
                  },
                  "llm_description": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。",
                  "max": null,
                  "min": null,
                  "name": "user_id_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "open_id",
                        "zh_Hans": "open_id"
                      },
                      "value": "open_id"
                    },
                    {
                      "label": {
                        "en_US": "union_id",
                        "zh_Hans": "union_id"
                      },
                      "value": "union_id"
                    },
                    {
                      "label": {
                        "en_US": "user_id",
                        "zh_Hans": "user_id"
                      },
                      "value": "user_id"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Create Event",
                  "zh_Hans": "创建日程"
                },
                "llm": "A tool for creating events in Lark.(创建 Lark 日程)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Create Event",
                  "zh_Hans": "创建日程"
                },
                "name": "create_event"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The title of the event. If not filled, the event title will display (No Subject).",
                    "zh_Hans": "日程标题，若不填则日程标题显示 (无主题)。"
                  },
                  "label": {
                    "en_US": "Summary",
                    "zh_Hans": "日程标题"
                  },
                  "llm_description": "日程标题，若不填则日程标题显示 (无主题)。",
                  "max": null,
                  "min": null,
                  "name": "summary",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The description of the event.",
                    "zh_Hans": "日程描述。"
                  },
                  "label": {
                    "en_US": "Description",
                    "zh_Hans": "日程描述"
                  },
                  "llm_description": "日程描述。",
                  "max": null,
                  "min": null,
                  "name": "description",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to send a bot message when the event is created, true: send, false: do not send.\n",
                    "zh_Hans": "创建日程时是否发送 bot 消息，true：发送，false：不发送。"
                  },
                  "label": {
                    "en_US": "Need Notification",
                    "zh_Hans": "是否发送通知"
                  },
                  "llm_description": "创建日程时是否发送 bot 消息，true：发送，false：不发送。",
                  "max": null,
                  "min": null,
                  "name": "need_notification",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The start time of the event, format: 2006-01-02 15:04:05.\n",
                    "zh_Hans": "日程开始时间，格式：2006-01-02 15:04:05。"
                  },
                  "label": {
                    "en_US": "Start Time",
                    "zh_Hans": "开始时间"
                  },
                  "llm_description": "日程开始时间，格式：2006-01-02 15:04:05。",
                  "max": null,
                  "min": null,
                  "name": "start_time",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The end time of the event, format: 2006-01-02 15:04:05.\n",
                    "zh_Hans": "日程结束时间，格式：2006-01-02 15:04:05。"
                  },
                  "label": {
                    "en_US": "End Time",
                    "zh_Hans": "结束时间"
                  },
                  "llm_description": "日程结束时间，格式：2006-01-02 15:04:05。",
                  "max": null,
                  "min": null,
                  "name": "end_time",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "none",
                  "form": "form",
                  "human_description": {
                    "en_US": "Attendee ability, optional values are none, can_see_others, can_invite_others, can_modify_event, with a default value of none.",
                    "zh_Hans": "参会人权限，可选值有无、可以查看参与人列表、可以邀请其它参与人、可以编辑日程，默认值为无。"
                  },
                  "label": {
                    "en_US": "attendee_ability",
                    "zh_Hans": "参会人权限"
                  },
                  "llm_description": "参会人权限，可选值有无、可以查看参与人列表、可以邀请其它参与人、可以编辑日程，默认值为无。",
                  "max": null,
                  "min": null,
                  "name": "attendee_ability",
                  "options": [
                    {
                      "label": {
                        "en_US": "none",
                        "zh_Hans": "无"
                      },
                      "value": "none"
                    },
                    {
                      "label": {
                        "en_US": "can_see_others",
                        "zh_Hans": "可以查看参与人列表"
                      },
                      "value": "can_see_others"
                    },
                    {
                      "label": {
                        "en_US": "can_invite_others",
                        "zh_Hans": "可以邀请其它参与人"
                      },
                      "value": "can_invite_others"
                    },
                    {
                      "label": {
                        "en_US": "can_modify_event",
                        "zh_Hans": "可以编辑日程"
                      },
                      "value": "can_modify_event"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to enable automatic recording, true: enabled, automatically record when the meeting starts; false: not enabled.\n",
                    "zh_Hans": "是否开启自动录制，true：开启，会议开始后自动录制；false：不开启。"
                  },
                  "label": {
                    "en_US": "Auto Record",
                    "zh_Hans": "自动录制"
                  },
                  "llm_description": "是否开启自动录制，true：开启，会议开始后自动录制；false：不开启。",
                  "max": null,
                  "min": null,
                  "name": "auto_record",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Delete Event",
                  "zh_Hans": "删除日程"
                },
                "llm": "A tool for deleting events in Lark.(在 Lark 中删除日程)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Delete Event",
                  "zh_Hans": "删除日程"
                },
                "name": "delete_event"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the event, for example: e8b9791c-39ae-4908-8ad8-66b13159b9fb_0.\n",
                    "zh_Hans": "日程 ID，例如：e8b9791c-39ae-4908-8ad8-66b13159b9fb_0。"
                  },
                  "label": {
                    "en_US": "Event ID",
                    "zh_Hans": "日程 ID"
                  },
                  "llm_description": "日程 ID，例如：e8b9791c-39ae-4908-8ad8-66b13159b9fb_0。",
                  "max": null,
                  "min": null,
                  "name": "event_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "Indicates whether to send bot notifications to event participants upon deletion. true: send, false: do not send.\n",
                    "zh_Hans": "删除日程是否给日程参与人发送 bot 通知，true：发送，false：不发送。"
                  },
                  "label": {
                    "en_US": "Need Notification",
                    "zh_Hans": "是否需要通知"
                  },
                  "llm_description": "删除日程是否给日程参与人发送 bot 通知，true：发送，false：不发送。",
                  "max": null,
                  "min": null,
                  "name": "need_notification",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "List Events",
                  "zh_Hans": "获取日程列表"
                },
                "llm": "A tool for listing events in Lark.(在 Lark 中获取日程列表)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "List Events",
                  "zh_Hans": "获取日程列表"
                },
                "name": "list_events"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The start time, defaults to 0:00 of the current day if not provided, format: 2006-01-02 15:04:05.\n",
                    "zh_Hans": "开始时间，不传值时默认当天 0 点时间，格式为:2006-01-02 15:04:05。"
                  },
                  "label": {
                    "en_US": "Start Time",
                    "zh_Hans": "开始时间"
                  },
                  "llm_description": "开始时间，不传值时默认当天 0 点时间，格式为:2006-01-02 15:04:05。",
                  "max": null,
                  "min": null,
                  "name": "start_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The end time, defaults to 23:59 of the current day if not provided, format: 2006-01-02 15:04:05.\n",
                    "zh_Hans": "结束时间，不传值时默认当天 23:59 分时间，格式为:2006-01-02 15:04:05。"
                  },
                  "label": {
                    "en_US": "End Time",
                    "zh_Hans": "结束时间"
                  },
                  "llm_description": "结束时间，不传值时默认当天 23:59 分时间，格式为:2006-01-02 15:04:05。",
                  "max": null,
                  "min": null,
                  "name": "end_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 50,
                  "form": "form",
                  "human_description": {
                    "en_US": "The page size, i.e., the number of data entries returned in a single request. The default value is 50, and the value range is [50,1000].",
                    "zh_Hans": "分页大小，即单次请求所返回的数据条目数。默认值为 50，取值范围为 [50,1000]。"
                  },
                  "label": {
                    "en_US": "Page Size",
                    "zh_Hans": "分页大小"
                  },
                  "llm_description": "分页大小，即单次请求所返回的数据条目数。默认值为 50，取值范围为 [50,1000]。",
                  "max": null,
                  "min": null,
                  "name": "page_size",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The pagination token. Leave it blank for the first request, indicating to start traversing from the beginning; when the pagination query result has more items, a new page_token will be returned simultaneously, which can be used to obtain the query result in the next traversal.",
                    "zh_Hans": "分页标记，第一次请求不填，表示从头开始遍历；分页查询结果还有更多项时会同时返回新的 page_token，下次遍历可采用该 page_token 获取查询结果。"
                  },
                  "label": {
                    "en_US": "Page Token",
                    "zh_Hans": "分页标记"
                  },
                  "llm_description": "分页标记，第一次请求不填，表示从头开始遍历；分页查询结果还有更多项时会同时返回新的 page_token，下次遍历可采用该 page_token 获取查询结果。",
                  "max": null,
                  "min": null,
                  "name": "page_token",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Update Event",
                  "zh_Hans": "更新日程"
                },
                "llm": "A tool for updating events in Lark.(更新 Lark 中的日程)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Doug Lea",
                "label": {
                  "en_US": "Update Event",
                  "zh_Hans": "更新日程"
                },
                "name": "update_event"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the event, for example: e8b9791c-39ae-4908-8ad8-66b13159b9fb_0.\n",
                    "zh_Hans": "日程 ID，例如：e8b9791c-39ae-4908-8ad8-66b13159b9fb_0。"
                  },
                  "label": {
                    "en_US": "Event ID",
                    "zh_Hans": "日程 ID"
                  },
                  "llm_description": "日程 ID，例如：e8b9791c-39ae-4908-8ad8-66b13159b9fb_0。",
                  "max": null,
                  "min": null,
                  "name": "event_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The title of the event.",
                    "zh_Hans": "日程标题。"
                  },
                  "label": {
                    "en_US": "Summary",
                    "zh_Hans": "日程标题"
                  },
                  "llm_description": "日程标题。",
                  "max": null,
                  "min": null,
                  "name": "summary",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The description of the event.",
                    "zh_Hans": "日程描述。"
                  },
                  "label": {
                    "en_US": "Description",
                    "zh_Hans": "日程描述"
                  },
                  "llm_description": "日程描述。",
                  "max": null,
                  "min": null,
                  "name": "description",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to send a bot message when the event is updated, true: send, false: do not send.\n",
                    "zh_Hans": "更新日程时是否发送 bot 消息，true：发送，false：不发送。"
                  },
                  "label": {
                    "en_US": "Need Notification",
                    "zh_Hans": "是否发送通知"
                  },
                  "llm_description": "更新日程时是否发送 bot 消息，true：发送，false：不发送。",
                  "max": null,
                  "min": null,
                  "name": "need_notification",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The start time of the event, format: 2006-01-02 15:04:05.\n",
                    "zh_Hans": "日程开始时间，格式：2006-01-02 15:04:05。"
                  },
                  "label": {
                    "en_US": "Start Time",
                    "zh_Hans": "开始时间"
                  },
                  "llm_description": "日程开始时间，格式：2006-01-02 15:04:05。",
                  "max": null,
                  "min": null,
                  "name": "start_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The end time of the event, format: 2006-01-02 15:04:05.\n",
                    "zh_Hans": "日程结束时间，格式：2006-01-02 15:04:05。"
                  },
                  "label": {
                    "en_US": "End Time",
                    "zh_Hans": "结束时间"
                  },
                  "llm_description": "日程结束时间，格式：2006-01-02 15:04:05。",
                  "max": null,
                  "min": null,
                  "name": "end_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to enable automatic recording, true: enabled, automatically record when the meeting starts; false: not enabled.\n",
                    "zh_Hans": "是否开启自动录制，true：开启，会议开始后自动录制；false：不开启。"
                  },
                  "label": {
                    "en_US": "Auto Record",
                    "zh_Hans": "自动录制"
                  },
                  "llm_description": "是否开启自动录制，true：开启，会议开始后自动录制；false：不开启。",
                  "max": null,
                  "min": null,
                  "name": "auto_record",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-26T10:45:03Z",
        "version_updated_at": "2025-02-26T10:45:03Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "RapidAPI is the world's largest API marketplace with over 1,000,000 developers and 10,000 APIs.",
          "zh_Hans": "RapidAPI是全球最大的API市场，拥有超过100万开发人员和10000个API。"
        },
        "category": "tool",
        "created_at": "2024-12-04T11:29:33Z",
        "endpoint": {},
        "icon": "langgenius/packages/rapidapi/_assets/rapidapi.png",
        "index_id": "langgenius___rapidapi",
        "install_count": 270,
        "introduction": "## Overview\n\n**RapidAPI** is the world's largest API marketplace, featuring over 1,000,000 developers and 10,000 APIs. It enables developers to seamlessly connect to a wide range of APIs, offering tools for diverse tasks such as data aggregation, analysis, and automation.\n\nThe **GoogleNews** action within **RapidAPI** provides access to aggregated news articles, allowing users to retrieve a continuous, customizable stream of news updates from Google News.\n\n## Configuration\n\nTo use **RapidAPI**, follow these steps:\n\n1. **Get a RapidAPI Key** You can go to the [RapidAPI Google News](https://rapidapi.com/bfd-id/api/google-news13/playground/apiendpoint_7a387229-24a0-4185-9be2-ce2791df0d78) website, create a new API Key, and make sure your account has the required permissions to access the desired APIs.\n\n![](./_assets/rapidapi-01.png)\n\n2. **Install the RapidAPI Tool** Open the Plugin Marketplace, search for the RapidAPI tool, and install it to integrate it with your application.\n\n3. **Authorize RapidAPI** In Dify, go to **Plugins > RapidAPI > Authorize**. Enter your API Key to activate the tool.\n\n![](./_assets/rapidapi-02.png)\n\n## Tool Features\n\nThe **RapidAPI** tool currently includes the **GoogleNews** action, allowing you to aggregate and retrieve news content efficiently.\n\n### GoogleNews\n\n**Description:** GoogleNews is a customizable news aggregator service developed by Google. It provides a continuous flow of articles organized from various publishers worldwide.\n\n**Parameters:**\n\n* **Language and Region** (String, Required): Specify the language and region for the search results using the \"National Language Code Comparison Table\" (e.g., `en-US` for English in the US or `zh-CN` for Simplified Chinese).\n\n<img src=\"./_assets/rapidapi-03.png\" width=\"400\" alt=\"Language and Region Settings\" />\n\n## Usage\n\nRapidAPI can seamlessly integrate **Chatflow / Workflow Apps** and **Agent Apps**.\n\n### Chatflow / Workflow Apps\n\n1. Add the RapidAPI node to your Chatflow or Workflow pipeline.\n2. Configure the **GoogleNews** action by specifying the **Language and Region** parameter.\n3. Run the pipeline to retrieve news articles, which can be used in downstream actions or displayed in your app.\n\n![](./_assets/rapidapi-04.png)\n\n### Agent Apps\n\n1. You can add the RapidAPI tool to your Agent application.\n2. Send a request to **GoogleNews** by specifying the language and region.\n3. The tool processes the request and returns the relevant news content.\n\n![](./_assets/rapidapi-05.png)\n\n## Use Cases\n\n* **News Aggregation:** Retrieve news articles for dashboards, reports, or alerts.\n* **Localized Content:** Provide region-specific news in different languages.\n* **Trend Analysis:** Collect news data for sentiment analysis or topic detection.\n* **Content Automation:** Automate the delivery of fresh news content for websites or applications.\n\nWith **RapidAPI**, you can quickly integrate powerful APIs like **GoogleNews** into your workflows, unlocking a wide range of possibilities for data-driven applications.\n",
        "label": {
          "en_US": "RapidAPI",
          "zh_Hans": "RapidAPI"
        },
        "latest_package_identifier": "langgenius/rapidapi:0.0.3@3216efa09868d55d1fda10e2ba7d041fcf23c0aa1f0121073a10a8f59d4af81a",
        "latest_version": "0.0.3",
        "model": {},
        "name": "rapidapi",
        "org": "langgenius",
        "plugin_id": "langgenius/rapidapi",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/rapidapi.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "news"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "x-rapidapi-host",
                "zh_Hans": "x-rapidapi-host"
              },
              "name": "x-rapidapi-host",
              "options": null,
              "placeholder": {
                "en_US": "Please input your x-rapidapi-host",
                "zh_Hans": "请输入你的 x-rapidapi-host"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": "https://rapidapi.com/"
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "x-rapidapi-key",
                "zh_Hans": "x-rapidapi-key"
              },
              "name": "x-rapidapi-key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your x-rapidapi-key",
                "zh_Hans": "请输入你的 x-rapidapi-key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://rapidapi.com/"
            }
          ],
          "identity": {
            "author": "Steven Sun",
            "description": {
              "en_US": "RapidAPI is the world's largest API marketplace with over 1,000,000 developers and 10,000 APIs.",
              "zh_Hans": "RapidAPI是全球最大的API市场，拥有超过100万开发人员和10000个API。"
            },
            "icon": "rapidapi.png",
            "label": {
              "en_US": "RapidAPI",
              "zh_Hans": "RapidAPI"
            },
            "name": "rapidapi",
            "tags": [
              "news"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "google news is a news aggregator service developed by Google. It presents a continuous, customizable flow of articles organized from thousands of publishers and magazines.",
                  "zh_Hans": "谷歌新闻是由谷歌开发的新闻聚合服务。它提供了一个持续的、可定制的文章流，这些文章是从成千上万的出版商和杂志中整理出来的。"
                },
                "llm": "A tool to get the latest news from Google News."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Steven Sun",
                "label": {
                  "en_US": "GoogleNews",
                  "zh_Hans": "谷歌新闻"
                },
                "name": "google_news"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": "en-US",
                  "form": "llm",
                  "human_description": {
                    "en_US": "The language and region determine the language and region of the search results, and its value is assigned according to the \"National Language Code Comparison Table\", such as en-US, which stands for English (United States); zh-CN, stands for Chinese (Simplified).",
                    "zh_Hans": "语言和地区决定了搜索结果的语言和地区,其赋值按照《国家语言代码对照表》，形如en-US,代表英语（美国）；zh-CN，代表中文（简体）。"
                  },
                  "label": {
                    "en_US": "Language and Region",
                    "zh_Hans": "语言和地区"
                  },
                  "llm_description": "The language and region determine the language and region of the search results, and its value is assigned according to the \"National Language Code Comparison Table\", such as en-US, which stands for English (United States); zh-CN, stands for Chinese (Simplified).",
                  "max": null,
                  "min": null,
                  "name": "language_region",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:04:49Z",
        "version_updated_at": "2025-02-17T07:04:49Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Mixedbread"
        },
        "category": "model",
        "created_at": "2025-02-17T06:57:50Z",
        "endpoint": {},
        "icon": "langgenius/packages/mixedbread/_assets/icon_s_en.png",
        "index_id": "langgenius___mixedbread",
        "install_count": 264,
        "introduction": "## Overview\nMixedBread provides text embedding, and reranking designed for enterprise applications.\nFind exactly what you need from your business data with precision and speed.\n\nThe latest mxbai-rerank-v2 model works with 100+ languages and all content types and it was tested on English, Chinese, multilingual, tool retrieval, and code-search benchmarks, comparing it to other open- and closed-source models.\n\nThe results are impressive outperforming open and closed source competitors such as Cohere or Voyage by a good margin.\n\n<img src=\"./_assets/beir-performance.png\" width=\"600\" />\n\n\n## Configure\nInstall the Mixedbread plugin, then configure it in Model Provider settings with the API Key.\nGet your API key from [Mixedbread AI](https://www.mixedbread.com) and save your settings.\n\n<img src=\"./_assets/icon_l_en.png\" width=\"400\" />\n",
        "label": {
          "en_US": "Mixedbread"
        },
        "latest_package_identifier": "langgenius/mixedbread:0.0.4@0a8052691ded76dc5042b44593a739757da4f1d8f112b5fc240ac4b694691364",
        "latest_version": "0.0.4",
        "model": {
          "background": "#EFFDFD",
          "configurate_methods": [
            "predefined-model"
          ],
          "description": {
            "en_US": "Embedding and Rerank Model Supported"
          },
          "help": {
            "title": {
              "en_US": "Get your API key from Mixedbread AI",
              "zh_Hans": "从 Mixedbread 获取 API Key"
            },
            "url": {
              "en_US": "https://mixedbread.com/"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.png"
          },
          "icon_small": {
            "en_US": "icon_s_en.png"
          },
          "label": {
            "en_US": "Mixedbread"
          },
          "model_credential_schema": null,
          "models": [
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "mxbai-rerank-large-v1"
              },
              "model": "mxbai-rerank-large-v1",
              "model_properties": {
                "context_size": 512
              },
              "model_type": "rerank",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "mxbai-rerank-large-v2"
              },
              "model": "mxbai-rerank-large-v2",
              "model_properties": {
                "context_size": 8000
              },
              "model_type": "rerank",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "mxbai-embed-2d-large-v1"
              },
              "model": "mxbai-embed-2d-large-v1",
              "model_properties": {
                "context_size": 512
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.0001",
                "output": null,
                "unit": "0.001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "mxbai-embed-large-v1"
              },
              "model": "mxbai-embed-large-v1",
              "model_properties": {
                "context_size": 512
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.0001",
                "output": null,
                "unit": "0.001"
              }
            }
          ],
          "position": {},
          "provider": "mixedbread",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              }
            ]
          },
          "supported_model_types": [
            "text-embedding",
            "rerank"
          ]
        },
        "name": "mixedbread",
        "org": "langgenius",
        "plugin_id": "langgenius/mixedbread",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/mixedbread.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": false,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-14T02:05:00Z",
        "version_updated_at": "2025-04-14T02:05:00Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Trello: A visual tool for organizing your work and life.",
          "pt_BR": "Trello: Uma ferramenta visual para organizar seu trabalho e vida.",
          "zh_Hans": "Trello: 一个用于组织工作和生活的视觉工具。"
        },
        "category": "tool",
        "created_at": "2024-12-02T05:37:08Z",
        "endpoint": {},
        "icon": "langgenius/packages/trello/_assets/icon.svg",
        "index_id": "langgenius___trello",
        "install_count": 258,
        "introduction": "",
        "label": {
          "en_US": "Trello",
          "pt_BR": "Trello",
          "zh_Hans": "Trello"
        },
        "latest_package_identifier": "langgenius/trello:0.0.2@80c694087317265e1c5fb231aa08a75d5c7dc4e8da79d9c2565ba5d97e3b1a4c",
        "latest_version": "0.0.2",
        "model": {},
        "name": "trello",
        "org": "langgenius",
        "plugin_id": "langgenius/trello",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/trello.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "Trello API key",
                "pt_BR": "Trello API key",
                "zh_Hans": "Trello API key"
              },
              "name": "trello_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Enter your Trello API key",
                "pt_BR": "Insira sua chave API do Trello",
                "zh_Hans": "输入您的 Trello API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://developer.atlassian.com/cloud/trello/guides/rest-api/api-introduction/"
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "Trello API token",
                "pt_BR": "Trello API token",
                "zh_Hans": "Trello API token"
              },
              "name": "trello_api_token",
              "options": null,
              "placeholder": {
                "en_US": "Enter your Trello API token",
                "pt_BR": "Insira seu token API do Trello",
                "zh_Hans": "输入您的 Trello API token"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://developer.atlassian.com/cloud/trello/guides/rest-api/api-introduction/"
            }
          ],
          "identity": {
            "author": "Yash Parmar",
            "description": {
              "en_US": "Trello: A visual tool for organizing your work and life.",
              "pt_BR": "Trello: Uma ferramenta visual para organizar seu trabalho e vida.",
              "zh_Hans": "Trello: 一个用于组织工作和生活的视觉工具。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Trello",
              "pt_BR": "Trello",
              "zh_Hans": "Trello"
            },
            "name": "trello",
            "tags": [
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Updates specified attributes of a Trello card, such as its name, description, list ID, and board ID, by providing the card's unique ID.",
                  "pt_BR": "Atualiza atributos específicos de um cartão Trello, como seu nome, descrição, ID da lista e ID do quadro, fornecendo o ID único do cartão.",
                  "zh_Hans": "通过提供卡片的唯一 ID，更新 Trello 卡片的特定属性，如其名称、描述、列表 ID 和看板 ID。"
                },
                "llm": "Modify a Trello card's key details, including name, description, and its placement on the board, by using the card's ID. Enables precise and targeted updates to card information."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Yash Parmar",
                "label": {
                  "en_US": "Update Card by ID",
                  "pt_BR": "Atualizar Cartão por ID",
                  "zh_Hans": "通过 ID 更新卡片"
                },
                "name": "update_card_by_id"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The unique identifier of the Trello card you intend to update.",
                    "pt_BR": "O identificador único do cartão Trello que você pretende atualizar.",
                    "zh_Hans": "您打算更新的 Trello 卡片的唯一标识符。"
                  },
                  "label": {
                    "en_US": "Card ID",
                    "pt_BR": "ID do Cartão",
                    "zh_Hans": "卡片 ID"
                  },
                  "llm_description": "Input the ID of the Trello card to be updated to ensure the correct card is targeted.",
                  "max": null,
                  "min": null,
                  "name": "id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional. The new name to assign to the card.",
                    "pt_BR": "Opcional. O novo nome a ser atribuído ao cartão.",
                    "zh_Hans": "可选。要分配给卡片的新名称。"
                  },
                  "label": {
                    "en_US": "New Name",
                    "pt_BR": "Novo Nome",
                    "zh_Hans": "新名称"
                  },
                  "llm_description": "Specify a new name for the card if changing it. This name is what will be displayed on the Trello board.",
                  "max": null,
                  "min": null,
                  "name": "name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional. The new description to assign to the card.",
                    "pt_BR": "Opcional. A nova descrição a ser atribuída ao cartão.",
                    "zh_Hans": "可选。要分配给卡片的新描述。"
                  },
                  "label": {
                    "en_US": "New Description",
                    "pt_BR": "Nova Descrição",
                    "zh_Hans": "新描述"
                  },
                  "llm_description": "Provide a new description for the card if you wish to update it; this description provides additional context about the card.",
                  "max": null,
                  "min": null,
                  "name": "desc",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional. The ID of the list to which the card should be moved.",
                    "pt_BR": "Opcional. O ID da lista para a qual o cartão deve ser movido.",
                    "zh_Hans": "可选。卡片应移动到的列表的 ID。"
                  },
                  "label": {
                    "en_US": "List ID",
                    "pt_BR": "ID da Lista",
                    "zh_Hans": "列表 ID"
                  },
                  "llm_description": "Enter the ID of the list where you want to move the card. This action relocates the card to the specified list.",
                  "max": null,
                  "min": null,
                  "name": "idList",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional. The ID of the board to which the card should be moved.",
                    "pt_BR": "Opcional. O ID do quadro para o qual o cartão deve ser movido.",
                    "zh_Hans": "可选。卡片应移动到的看板的 ID。"
                  },
                  "label": {
                    "en_US": "Board ID",
                    "pt_BR": "ID do Quadro",
                    "zh_Hans": "看板 ID"
                  },
                  "llm_description": "Provide the ID of the board where you want to move the card. This action relocates the card to the specified board.",
                  "max": null,
                  "min": null,
                  "name": "idBoard",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Retrieves detailed information about a specific Trello board using its unique ID. This tool enables users to quickly access board details without navigating through the Trello interface.",
                  "pt_BR": "Recupera informações detalhadas sobre um quadro Trello específico usando seu ID único. Esta ferramenta permite que os usuários acessem rapidamente os detalhes do quadro sem navegar pela interface do Trello.",
                  "zh_Hans": "使用其唯一 ID 检索有关特定 Trello 看板的详细信息。此工具使用户能够快速访问看板详情，无需通过 Trello 界面导航。"
                },
                "llm": "Access details of a Trello board by providing its ID. This tool offers a direct way to view board information, simplifying the process of managing and reviewing Trello boards."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Yash Parmar",
                "label": {
                  "en_US": "Get Board by ID",
                  "pt_BR": "Obter Quadro por ID",
                  "zh_Hans": "通过 ID 获取看板"
                },
                "name": "get_board_by_id"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The unique identifier for the Trello board you wish to retrieve. This ID enables precise targeting and fetching of the board's details.",
                    "pt_BR": "O identificador único do quadro Trello que você deseja recuperar. Este ID permite o direcionamento preciso e a obtenção dos detalhes do quadro.",
                    "zh_Hans": "您希望检索的 Trello 看板的唯一标识符。此 ID 使能够准确定位和获取看板的详细信息。"
                  },
                  "label": {
                    "en_US": "Board ID",
                    "pt_BR": "ID do Quadro",
                    "zh_Hans": "看板 ID"
                  },
                  "llm_description": "Input the ID of the Trello board to get its details. This unique ID ensures accurate retrieval of information about the specified board.",
                  "max": null,
                  "min": null,
                  "name": "boardId",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Retrieves cards from a Trello board using a specified filter and the board's ID. Filters include options like 'all', 'open', 'closed', 'none', and 'visible', allowing for tailored views of board content.",
                  "pt_BR": "Recupera cartões de um quadro Trello usando um filtro especificado e o ID do quadro. Os filtros incluem opções como 'all', 'open', 'closed', 'none' e 'visible', permitindo visualizações personalizadas do conteúdo do quadro.",
                  "zh_Hans": "使用指定的过滤器和看板的 ID 从 Trello 看板检索卡片。过滤器包括 'all', 'open', 'closed', 'none' 和 'visible' 等选项，允许对看板内容进行定制查看。"
                },
                "llm": "Access cards on a Trello board through specific filters such as 'all', 'open', 'closed', 'none', and 'visible' by providing the board's ID. This feature enables focused examination of the board's cards."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Yash Parmar",
                "label": {
                  "en_US": "Get Filtered Board Cards",
                  "pt_BR": "Obter Cartões Filtrados do Quadro",
                  "zh_Hans": "获取筛选的看板卡片"
                },
                "name": "get_filtered_board_cards"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The unique identifier for the Trello board from which to retrieve the filtered cards.",
                    "pt_BR": "O identificador único do quadro Trello do qual os cartões filtrados serão recuperados.",
                    "zh_Hans": "用于检索筛选卡片的 Trello 看板的唯一标识符。"
                  },
                  "label": {
                    "en_US": "Board ID",
                    "pt_BR": "ID do Quadro",
                    "zh_Hans": "看板 ID"
                  },
                  "llm_description": "Enter the Trello board's ID to specify from which board to fetch the cards using the filter.",
                  "max": null,
                  "min": null,
                  "name": "boardId",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The filter to apply when retrieving cards. Valid values are 'all', 'open', 'closed', 'none', and 'visible'.",
                    "pt_BR": "O filtro a ser aplicado ao recuperar cartões. Os valores válidos são 'all', 'open', 'closed', 'none' e 'visible'.",
                    "zh_Hans": "检索卡片时应用的过滤器。有效值为 'all', 'open', 'closed', 'none', 和 'visible'。"
                  },
                  "label": {
                    "en_US": "Filter",
                    "pt_BR": "Filtro",
                    "zh_Hans": "过滤器"
                  },
                  "llm_description": "Specify the filter for card retrieval. Choose from 'all', 'open', 'closed', 'none', or 'visible' to control which cards are fetched.",
                  "max": null,
                  "min": null,
                  "name": "filter",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Creates a new list on a specified Trello board by providing the board's ID and the desired name for the list. Streamlines the process of organizing board content.",
                  "pt_BR": "Cria uma nova lista em um quadro Trello especificado, fornecendo o ID do quadro e o nome desejado para a lista. Facilita o processo de organização do conteúdo do quadro.",
                  "zh_Hans": "通过提供看板的 ID 和列表的所需名称，在指定的 Trello 看板上创建一个新列表。简化了组织看板内容的过程。"
                },
                "llm": "Generate a new list within a Trello board by specifying the board's ID and a name for the list. Enhances board management by allowing quick additions of new lists."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Yash Parmar",
                "label": {
                  "en_US": "Create List on Board",
                  "pt_BR": "Criar Lista no Quadro",
                  "zh_Hans": "在看板上创建列表"
                },
                "name": "create_list_on_board"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The unique identifier of the Trello board where the new list will be created.",
                    "pt_BR": "O identificador único do quadro Trello onde a nova lista será criada.",
                    "zh_Hans": "新列表将被创建在其上的 Trello 看板的唯一标识符。"
                  },
                  "label": {
                    "en_US": "Board ID",
                    "pt_BR": "ID do Quadro",
                    "zh_Hans": "看板 ID"
                  },
                  "llm_description": "Input the ID of the Trello board to pinpoint where the new list should be added, ensuring correct placement.",
                  "max": null,
                  "min": null,
                  "name": "id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The name for the new list to be created on the Trello board.",
                    "pt_BR": "O nome para a nova lista que será criada no quadro Trello.",
                    "zh_Hans": "将在 Trello 看板上创建的新列表的名称。"
                  },
                  "label": {
                    "en_US": "List Name",
                    "pt_BR": "Nome da Lista",
                    "zh_Hans": "列表名称"
                  },
                  "llm_description": "Provide a name for the new list, defining its purpose or content focus, to facilitate board organization.",
                  "max": null,
                  "min": null,
                  "name": "name",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Creates a new card on a Trello board with specified details like name, description, list ID, and other optional parameters. Facilitates task addition and project management within Trello.",
                  "pt_BR": "Cria um novo cartão em um quadro Trello com detalhes especificados, como nome, descrição, ID da lista e outros parâmetros opcionais. Facilita a adição de tarefas e a gestão de projetos dentro do Trello.",
                  "zh_Hans": "用指定的详情（如名称、描述、列表 ID 和其他可选参数）在 Trello 看板上创建一个新卡片。便于在 Trello 中添加任务和管理项目。"
                },
                "llm": "Initiate a new card on a Trello board by specifying essential details such as the card's name, description, and the list it belongs to, among other settings. Streamlines project task additions and organizational workflows."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Yash Parmar",
                "label": {
                  "en_US": "Create New Card on Board",
                  "pt_BR": "Criar Novo Cartão no Quadro",
                  "zh_Hans": "在看板上创建新卡片"
                },
                "name": "create_new_card_on_board"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The name for the new card. Acts as the primary identifier and summary of the card's purpose.",
                    "pt_BR": "O nome para o novo cartão. Funciona como o identificador principal e resumo do propósito do cartão.",
                    "zh_Hans": "新卡片的名称。作为卡片目的的主要标识和总结。"
                  },
                  "label": {
                    "en_US": "Card Name",
                    "pt_BR": "Nome do Cartão",
                    "zh_Hans": "卡片名称"
                  },
                  "llm_description": "Provide a concise, descriptive name for the card, outlining its main focus or task.",
                  "max": null,
                  "min": null,
                  "name": "name",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional. A brief description of the card's purpose or contents.",
                    "pt_BR": "Opcional. Uma breve descrição do propósito ou conteúdo do cartão.",
                    "zh_Hans": "可选。卡片目的或内容的简要描述。"
                  },
                  "label": {
                    "en_US": "Card Description",
                    "pt_BR": "Descrição do Cartão",
                    "zh_Hans": "卡片描述"
                  },
                  "llm_description": "Add a brief description to the card to provide context or additional information about its purpose.",
                  "max": null,
                  "min": null,
                  "name": "desc",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional. The position of the card in the list. Can be 'top', 'bottom', or a positive number.",
                    "pt_BR": "Opcional. A posição do cartão na lista. Pode ser 'top', 'bottom' ou um número positivo.",
                    "zh_Hans": "可选。卡片在列表中的位置。可以是“top”、“bottom” 或正数。"
                  },
                  "label": {
                    "en_US": "Position",
                    "pt_BR": "Posição",
                    "zh_Hans": "位置"
                  },
                  "llm_description": "Specify the position of the card within the list, either at the top, bottom, or a specific numerical index.",
                  "max": null,
                  "min": null,
                  "name": "pos",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional. The due date for the card in the format 'MM/DD/YYYY'.",
                    "pt_BR": "Opcional. A data de vencimento do cartão no formato 'MM/DD/YYYY'.",
                    "zh_Hans": "可选。卡片的截止日期，格式为“MM/DD/YYYY”。"
                  },
                  "label": {
                    "en_US": "Due Date",
                    "pt_BR": "Data de Vencimento",
                    "zh_Hans": "截止日期"
                  },
                  "llm_description": "Set a due date for the card to establish a deadline for completion or action.",
                  "max": null,
                  "min": null,
                  "name": "due",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional. The start date for the card in the format 'MM/DD/YYYY'.",
                    "pt_BR": "Opcional. A data de início do cartão no formato 'MM/DD/YYYY'.",
                    "zh_Hans": "可选。卡片的开始日期，格式为“MM/DD/YYYY”。"
                  },
                  "label": {
                    "en_US": "Start Date",
                    "pt_BR": "Data de Início",
                    "zh_Hans": "开始日期"
                  },
                  "llm_description": "Specify a start date for the card to mark the beginning of a task or project phase.",
                  "max": null,
                  "min": null,
                  "name": "start",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional. Set to true if the due date has been completed, or false if it is pending.",
                    "pt_BR": "Opcional. Defina como true se a data de vencimento foi concluída, ou como false se estiver pendente.",
                    "zh_Hans": "可选。如果截止日期已完成，则设置为 true；如果尚未完成，则设置为 false。"
                  },
                  "label": {
                    "en_US": "Due Complete",
                    "pt_BR": "Vencimento Concluído",
                    "zh_Hans": "截止日期已完成"
                  },
                  "llm_description": "Indicate whether the due date for the card has been marked as complete or is still pending.",
                  "max": null,
                  "min": null,
                  "name": "dueComplete",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The unique identifier of the list where the card will be added.",
                    "pt_BR": "O identificador único da lista onde o cartão será adicionado.",
                    "zh_Hans": "卡片将被添加到的列表的唯一标识符。"
                  },
                  "label": {
                    "en_US": "List ID",
                    "pt_BR": "ID da Lista",
                    "zh_Hans": "列表 ID"
                  },
                  "llm_description": "Input the ID of the list where the card should be placed, ensuring it is added to the correct list.",
                  "max": null,
                  "min": null,
                  "name": "idList",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional. The IDs of members to assign to the card.",
                    "pt_BR": "Opcional. Os IDs dos membros a serem atribuídos ao cartão.",
                    "zh_Hans": "可选。要分配给卡片的成员的 ID。"
                  },
                  "label": {
                    "en_US": "Member IDs",
                    "pt_BR": "IDs de Membros",
                    "zh_Hans": "成员 ID"
                  },
                  "llm_description": "Specify the IDs of members to assign to the card, allowing for task delegation or collaboration.",
                  "max": null,
                  "min": null,
                  "name": "idMembers",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional. The IDs of labels to assign to the card.",
                    "pt_BR": "Opcional. Os IDs das etiquetas a serem atribuídos ao cartão.",
                    "zh_Hans": "可选。要分配给卡片的标签的 ID。"
                  },
                  "label": {
                    "en_US": "Label IDs",
                    "pt_BR": "IDs de Etiquetas",
                    "zh_Hans": "标签 ID"
                  },
                  "llm_description": "Assign specific labels to the card by providing their IDs, aiding in visual categorization or prioritization.",
                  "max": null,
                  "min": null,
                  "name": "idLabels",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional. The URL to attach as the card's source.",
                    "pt_BR": "Opcional. O URL a ser anexado como a fonte do cartão.",
                    "zh_Hans": "可选。要附加为卡片来源的 URL。"
                  },
                  "label": {
                    "en_US": "Source URL",
                    "pt_BR": "URL de Origem",
                    "zh_Hans": "来源 URL"
                  },
                  "llm_description": "Provide a URL to serve as the source reference for the card, linking to external resources or documents.",
                  "max": null,
                  "min": null,
                  "name": "urlSource",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Retrieves all cards present on a specific Trello board by its ID, providing a list of card names and their IDs. Useful for managing and organizing project tasks.",
                  "pt_BR": "Recupera todos os cartões presentes em um quadro Trello específico pelo seu ID, fornecendo uma lista dos nomes dos cartões e seus IDs. Útil para gerenciar e organizar tarefas de projetos.",
                  "zh_Hans": "通过其 ID 检索特定 Trello 看板上的所有卡片，提供卡片名称及其 ID 的列表。用于管理和组织项目任务。"
                },
                "llm": "Obtain a list of all cards on a specific Trello board by entering the board's ID. This tool helps in quickly assessing the tasks or items associated with the board."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Yash Parmar",
                "label": {
                  "en_US": "Get Board Cards",
                  "pt_BR": "Obter Cartões do Quadro",
                  "zh_Hans": "获取看板卡片"
                },
                "name": "get_board_cards"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The unique identifier of the Trello board from which you want to retrieve cards. It specifies the exact board to gather card details from.",
                    "pt_BR": "O identificador único do quadro Trello do qual você deseja recuperar os cartões. Especifica o quadro exato para obter detalhes dos cartões.",
                    "zh_Hans": "您想要从中检索卡片的 Trello 看板的唯一标识符。它指定了要从中收集卡片详细信息的确切看板。"
                  },
                  "label": {
                    "en_US": "Board ID",
                    "pt_BR": "ID do Quadro",
                    "zh_Hans": "看板 ID"
                  },
                  "llm_description": "Input the ID of the Trello board to fetch its cards, allowing for a detailed overview of the board's contents.",
                  "max": null,
                  "min": null,
                  "name": "boardId",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Updates a Trello board's settings based on the provided ID and parameters. Allows for changing the board's name, description, status, and other preferences.",
                  "pt_BR": "Atualiza as configurações de um quadro Trello com base no ID fornecido e nos parâmetros. Permite alterar o nome, descrição, status e outras preferências do quadro.",
                  "zh_Hans": "根据提供的 ID 和参数更新 Trello 看板的设置。允许更改看板的名称、描述、状态和其他偏好设置。"
                },
                "llm": "Modify a Trello board's attributes like its name, description, and visibility settings using the board's ID. This tool streamlines board customization and management."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Yash Parmar",
                "label": {
                  "en_US": "Update Board by ID",
                  "pt_BR": "Atualizar Quadro por ID",
                  "zh_Hans": "通过 ID 更新看板"
                },
                "name": "update_board_by_id"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The unique identifier of the Trello board you want to update. Ensures targeted and precise updates.",
                    "pt_BR": "O identificador único do quadro Trello que você deseja atualizar. Garante atualizações direcionadas e precisas.",
                    "zh_Hans": "您要更新的 Trello 看板的唯一标识符。确保目标准确和更新精确。"
                  },
                  "label": {
                    "en_US": "Board ID",
                    "pt_BR": "ID do Quadro",
                    "zh_Hans": "看板 ID"
                  },
                  "llm_description": "Provide the specific ID of the Trello board you aim to update to ensure accuracy in modification process.",
                  "max": null,
                  "min": null,
                  "name": "boardId",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional. The new name for the board.",
                    "pt_BR": "Opcional. O novo nome para o quadro.",
                    "zh_Hans": "可选。看板的新名称。"
                  },
                  "label": {
                    "en_US": "Board Name",
                    "pt_BR": "Nome do Quadro",
                    "zh_Hans": "看板名称"
                  },
                  "llm_description": "Enter a new name for the board if you wish to change it; this name identifies the board in Trello.",
                  "max": null,
                  "min": null,
                  "name": "name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional. The new description for the board.",
                    "pt_BR": "Opcional. A nova descrição para o quadro.",
                    "zh_Hans": "可选。看板的新描述。"
                  },
                  "label": {
                    "en_US": "Board Description",
                    "pt_BR": "Descrição do Quadro",
                    "zh_Hans": "看板描述"
                  },
                  "llm_description": "Provide a new description for the board if you wish to update it; this description provides additional context about the board.",
                  "max": null,
                  "min": null,
                  "name": "desc",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional. Set to true to close the board, or false to keep it open.",
                    "pt_BR": "Opcional. Defina como true para fechar o quadro ou como false para mantê-lo aberto.",
                    "zh_Hans": "可选。设置为 true 以关闭看板，或设置为 false 以保持打开。"
                  },
                  "label": {
                    "en_US": "Closed",
                    "pt_BR": "Fechado",
                    "zh_Hans": "已关闭"
                  },
                  "llm_description": "Specify whether the board should be closed or kept open by setting this parameter to true or false.",
                  "max": null,
                  "min": null,
                  "name": "closed",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional. Set to true to subscribe to the board, or false to unsubscribe.",
                    "pt_BR": "Opcional. Defina como true para se inscrever no quadro ou como false para cancelar a inscrição.",
                    "zh_Hans": "可选。设置为 true 以订阅看板，或设置为 false 以取消订阅。"
                  },
                  "label": {
                    "en_US": "Subscribed",
                    "pt_BR": "Inscrito",
                    "zh_Hans": "订阅"
                  },
                  "llm_description": "Choose to subscribe or unsubscribe from the board by setting this parameter to true or false.",
                  "max": null,
                  "min": null,
                  "name": "subscribed",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional. The ID of the organization to which the board belongs.",
                    "pt_BR": "Opcional. O ID da organização à qual o quadro pertence.",
                    "zh_Hans": "可选。看板所属组织的 ID。"
                  },
                  "label": {
                    "en_US": "Organization ID",
                    "pt_BR": "ID da Organização",
                    "zh_Hans": "组织 ID"
                  },
                  "llm_description": "Input the ID of the organization to which the board is associated, if applicable.",
                  "max": null,
                  "min": null,
                  "name": "idOrganization",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional. The permission level for the board. Valid values are 'private', 'org', or 'public'.",
                    "pt_BR": "Opcional. O nível de permissão para o quadro. Os valores válidos são 'private', 'org' ou 'public'.",
                    "zh_Hans": "可选。看板的权限级别。有效值为 'private'、'org' 或 'public'。"
                  },
                  "label": {
                    "en_US": "Permission Level",
                    "pt_BR": "Nível de Permissão",
                    "zh_Hans": "权限级别"
                  },
                  "llm_description": "Specify the permission level for the board by choosing from 'private', 'org', or 'public'.",
                  "max": null,
                  "min": null,
                  "name": "prefs_permissionLevel",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional. Set to true to allow members to join the board without an invitation, or false to require an invitation.",
                    "pt_BR": "Opcional. Defina como true para permitir que os membros se inscrevam no quadro sem um convite, ou como false para exigir um convite.",
                    "zh_Hans": "可选。设置为 true 以允许成员加入看板而无需邀请，或设置为 false 以要求邀请。"
                  },
                  "label": {
                    "en_US": "Allow Self-Join",
                    "pt_BR": "Permitir Auto-Inscrição",
                    "zh_Hans": "允许自行加入"
                  },
                  "llm_description": "Choose whether to allow members to join the board without an invitation by setting this parameter to true or false.",
                  "max": null,
                  "min": null,
                  "name": "prefs_selfJoin",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional. Set to true to enable card covers, or false to disable them.",
                    "pt_BR": "Opcional. Defina como true para habilitar capas de cartão ou como false para desabilitá-las.",
                    "zh_Hans": "可选。设置为 true 以启用卡片封面，或设置为 false 以禁用卡片封面。"
                  },
                  "label": {
                    "en_US": "Card Covers",
                    "pt_BR": "Capas de Cartão",
                    "zh_Hans": "卡片封面"
                  },
                  "llm_description": "Enable or disable card covers by setting this parameter to true or false.",
                  "max": null,
                  "min": null,
                  "name": "prefs_cardCovers",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional. Set to true to hide votes, or false to show them.",
                    "pt_BR": "Opcional. Defina como true para ocultar votos ou como false para mostrá-los.",
                    "zh_Hans": "可选。设置为 true 以隐藏投票，或设置为 false 以显示投票。"
                  },
                  "label": {
                    "en_US": "Hide Votes",
                    "pt_BR": "Ocultar Votos",
                    "zh_Hans": "隐藏投票"
                  },
                  "llm_description": "Choose to hide or show votes by setting this parameter to true or false.",
                  "max": null,
                  "min": null,
                  "name": "prefs_hideVotes",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional. Set to 'members' to allow only board members to send invitations, or 'admins' to allow admins to send invitations.",
                    "pt_BR": "Opcional. Defina como 'members' para permitir que apenas membros do quadro enviem convites, ou 'admins' para permitir que os administradores enviem convites.",
                    "zh_Hans": "可选。设置为 'members' 以仅允许看板成员发送邀请，或设置为 'admins' 以允许管理员发送邀请。"
                  },
                  "label": {
                    "en_US": "Invitations",
                    "pt_BR": "Convites",
                    "zh_Hans": "邀请"
                  },
                  "llm_description": "Choose who can send invitations by setting this parameter to 'members' or 'admins'.",
                  "max": null,
                  "min": null,
                  "name": "prefs_invitations",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Retrieves all lists from a specified Trello board by its ID, providing an overview of the board's organization and current phases or categories.",
                  "pt_BR": "Recupera todas as listas de um quadro Trello especificado pelo seu ID, fornecendo uma visão geral da organização do quadro e das fases ou categorias atuais.",
                  "zh_Hans": "通过其 ID 从指定的 Trello 看板检索所有列表，提供看板组织和当前阶段或类别的概览。"
                },
                "llm": "Fetch and display all lists from a specific Trello board by inputting the board's ID. This aids in understanding the board's structure and task categorization."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Yash Parmar",
                "label": {
                  "en_US": "Get Lists from Board",
                  "pt_BR": "Obter Listas do Quadro",
                  "zh_Hans": "获取看板的列表"
                },
                "name": "get_lists_from_board"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The unique identifier of the Trello board from which to retrieve the lists.",
                    "pt_BR": "O identificador único do quadro Trello do qual as listas serão recuperadas.",
                    "zh_Hans": "用于检索列表的 Trello 看板的唯一标识符。"
                  },
                  "label": {
                    "en_US": "Board ID",
                    "pt_BR": "ID do Quadro",
                    "zh_Hans": "看板 ID"
                  },
                  "llm_description": "Enter the ID of the Trello board to obtain a detailed list of all its lists, providing insight into the board's structure.",
                  "max": null,
                  "min": null,
                  "name": "boardId",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Creates a new Trello board with a specified name. This tool allows users to quickly add new boards to their Trello account, facilitating project organization and management.",
                  "pt_BR": "Cria um novo quadro Trello com um nome especificado. Esta ferramenta permite que os usuários adicionem rapidamente novos quadros à sua conta Trello, facilitando a organização e gestão de projetos.",
                  "zh_Hans": "使用指定的名称创建一个新的 Trello 看板。此工具允许用户快速向其 Trello 账户添加新的看板，促进项目组织和管理。"
                },
                "llm": "Create a new Trello board using the specified name. This functionality simplifies the addition of boards, enhancing project organization and management within Trello."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Yash Parmar",
                "label": {
                  "en_US": "Create Board",
                  "pt_BR": "Criar Quadro",
                  "zh_Hans": "创建看板"
                },
                "name": "create_board"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The name for the new Trello board. This name helps in identifying and organizing your projects on Trello.",
                    "pt_BR": "O nome para o novo quadro Trello. Este nome ajuda a identificar e organizar seus projetos no Trello.",
                    "zh_Hans": "新 Trello 看板的名称。这个名称有助于在 Trello 上识别和组织您的项目。"
                  },
                  "label": {
                    "en_US": "Board Name",
                    "pt_BR": "Nome do Quadro",
                    "zh_Hans": "看板名称"
                  },
                  "llm_description": "Specify the name for your new Trello board, aiding in project identification and organization within Trello.",
                  "max": null,
                  "min": null,
                  "name": "name",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Deletes a Trello board using its unique ID. This tool allows for the removal of boards that are no longer needed, ensuring a tidy workspace.",
                  "pt_BR": "Exclui um quadro Trello usando seu ID único. Esta ferramenta permite a remoção de quadros que não são mais necessários, garantindo um espaço de trabalho organizado.",
                  "zh_Hans": "使用其唯一 ID 删除 Trello 看板。此工具允许删除不再需要的看板，确保工作区整洁。"
                },
                "llm": "Remove a Trello board by specifying its ID. This functionality is helpful for cleaning up unnecessary boards from your Trello account."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Yash Parmar",
                "label": {
                  "en_US": "Delete Board",
                  "pt_BR": "Excluir Quadro",
                  "zh_Hans": "删除看板"
                },
                "name": "delete_board"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The unique identifier for the Trello board you wish to delete. This ensures the specific board is accurately targeted for deletion.",
                    "pt_BR": "O identificador único para o quadro Trello que você deseja excluir. Isso garante que o quadro específico seja precisamente direcionado para exclusão.",
                    "zh_Hans": "您希望删除的 Trello 看板的唯一标识符。这确保了准确地针对特定看板进行删除。"
                  },
                  "label": {
                    "en_US": "Board ID",
                    "pt_BR": "ID do Quadro",
                    "zh_Hans": "看板 ID"
                  },
                  "llm_description": "Enter the ID of the Trello board you want to remove. This ID is essential to identify the board precisely and perform the deletion.",
                  "max": null,
                  "min": null,
                  "name": "boardId",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Deletes a Trello card using its unique ID. This tool facilitates the removal of cards that are no longer needed, maintaining an organized board.",
                  "pt_BR": "Exclui um cartão Trello usando seu ID único. Esta ferramenta facilita a remoção de cartões que não são mais necessários, mantendo um quadro organizado.",
                  "zh_Hans": "使用其唯一 ID 删除 Trello 卡片。此工具便于删除不再需要的卡片，保持看板的有序。"
                },
                "llm": "Remove a specific Trello card by providing its ID. Ideal for cleaning up and organizing your Trello boards by eliminating unwanted cards."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Yash Parmar",
                "label": {
                  "en_US": "Delete Card by ID",
                  "pt_BR": "Deletar Cartão por ID",
                  "zh_Hans": "通过 ID 删除卡片"
                },
                "name": "delete_card_by_id"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The unique identifier of the Trello card you wish to delete. This ensures the precise card is removed.",
                    "pt_BR": "O identificador único do cartão Trello que você deseja excluir. Isso garante que o cartão exato seja removido.",
                    "zh_Hans": "您希望删除的 Trello 卡片的唯一标识符。这确保了精确移除特定卡片。"
                  },
                  "label": {
                    "en_US": "Card ID",
                    "pt_BR": "ID do Cartão",
                    "zh_Hans": "卡片 ID"
                  },
                  "llm_description": "Input the ID of the Trello card targeted for deletion to ensure accurate and specific removal.",
                  "max": null,
                  "min": null,
                  "name": "id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Retrieves all the Trello boards associated with the user's account. This tool provides a quick overview of all open boards, aiding in efficient project management and organization.",
                  "pt_BR": "Recupera todos os quadros do Trello associados à conta do usuário. Esta ferramenta oferece uma visão geral rápida de todos os quadros abertos, auxiliando na gestão e organização eficiente do projeto.",
                  "zh_Hans": "检索与用户账户关联的所有 Trello 看板。该工具提供了所有打开的看板的快速概览，有助于高效的项目管理和组织。"
                },
                "llm": "This tool fetches all Trello boards linked to the user's account, offering a swift snapshot of open boards to streamline project management and organization tasks."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Yash Parmar",
                "label": {
                  "en_US": "Fetch All Boards",
                  "pt_BR": "Buscar Todos os Quadros",
                  "zh_Hans": "获取所有看板"
                },
                "name": "fetch_all_boards"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": "open",
                  "form": "llm",
                  "human_description": {
                    "en_US": "Specifies the type of boards to retrieve. Default is 'open', fetching all open boards. Other options include 'closed', 'members', 'organization', etc.",
                    "pt_BR": "Especifica o tipo de quadros a serem recuperados. O padrão é 'open', buscando todos os quadros abertos. Outras opções incluem 'closed', 'members', 'organization', etc.",
                    "zh_Hans": "指定要检索的看板类型。默认为“open”，获取所有打开的看板。其他选项包括“closed”，“members”，“organization”等。"
                  },
                  "label": {
                    "en_US": "Boards filter",
                    "pt_BR": "Filtro de quadros",
                    "zh_Hans": "看板过滤器"
                  },
                  "llm_description": "Determines the category of boards to be displayed, with 'open' as the default setting to show all open boards. Variants like 'closed', 'members', and 'organization' are also selectable.",
                  "max": null,
                  "min": null,
                  "name": "boards",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Retrieves a list of actions (such as updates, movements, and comments) for a Trello board by its ID. This tool provides insights into the board's activity history.",
                  "pt_BR": "Recupera uma lista de ações (como atualizações, movimentos e comentários) para um quadro Trello pelo seu ID. Esta ferramenta oferece insights sobre o histórico de atividades do quadro.",
                  "zh_Hans": "通过其 ID 为 Trello 看板检索操作列表（如更新、移动和评论）。此工具提供了看板活动历史的见解。"
                },
                "llm": "Fetch the sequence of actions performed on a Trello board, such as card updates, movements, and comments, by providing the board's ID. Offers a historical view of board activities."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Yash Parmar",
                "label": {
                  "en_US": "Get Board Actions",
                  "pt_BR": "Obter Ações do Quadro",
                  "zh_Hans": "获取看板操作"
                },
                "name": "get_board_actions"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The unique identifier of the Trello board for which you want to retrieve actions. It targets the specific board to fetch its activity log.",
                    "pt_BR": "O identificador único do quadro Trello para o qual você deseja recuperar ações. Direciona especificamente para o quadro para buscar seu registro de atividades.",
                    "zh_Hans": "您想要检索操作的 Trello 看板的唯一标识符。它定位特定的看板以获取其活动日志。"
                  },
                  "label": {
                    "en_US": "Board ID",
                    "pt_BR": "ID do Quadro",
                    "zh_Hans": "看板 ID"
                  },
                  "llm_description": "Input the ID of the Trello board to access its detailed action history, including all updates, comments, and movements related to the board.",
                  "max": null,
                  "min": null,
                  "name": "boardId",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:14:49Z",
        "version_updated_at": "2025-02-17T07:14:49Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "nacos client",
          "ja_JP": "nacos client",
          "pt_BR": "nacos client",
          "zh_Hans": "nacos client"
        },
        "category": "tool",
        "created_at": "2025-04-01T21:16:25Z",
        "endpoint": {},
        "icon": "aias00/packages/nacos/_assets/nacos-logo.png",
        "index_id": "aias00___nacos",
        "install_count": 258,
        "introduction": "# Nacos Plugin\n\n**Author:** [aias00](https://github.com/aias00)\n**Version:** 0.0.1\n**Type:** tool\n\n## Description\n\n### NacosWriter Plugin\n\nThe Nacos Writer Plugin allows users to write data into Nacos.\n![](./_assets/nacos_writer.png)\n\n### Features\n\n- Write data into Nacos and returns standard output and standard error\n\n### Parameters\n\n| Parameter | Type | Required | Description |\n|-----------|------|----------|-------------|\n| server_addresses | string | Yes | server addresses of the Nacos server |\n| username | string | Yes | username of the Nacos server |\n| password | string | Yes | password of the Nacos server |\n| namespace | string | Yes | namespace of the Nacos server |\n| data_id | string | Yes | data_id of the Nacos server |\n| group | string | Yes | group of the Nacos server |\n| content | string | Yes | Content to write into Nacos |\n\n\n### NacosReader Plugin\n\nThe Nacos Reader Plugin allows users to read data from Nacos.\n![](./_assets/nacos_reader.png)\n\n### Features\n\n- Read data from Nacos and returns standard output and standard error\n\n### Parameters\n\n| Parameter | Type | Required | Description |\n|-----------|------|----------|-------------|\n| server_addresses | string | Yes | server addresses of the Nacos server |\n| username | string | Yes | username of the Nacos server |\n| password | string | Yes | password of the Nacos server |\n| namespace | string | Yes | namespace of the Nacos server |\n| data_id | string | Yes | data_id of the Nacos server |\n| group | string | Yes | group of the Nacos server |\n\n## Security Considerations\n\n- Ensure you have permission to access the target server\n- Sensitive information such as private keys and passwords should be kept secure\n- Follow the principle of least privilege, granting only necessary execution permissions\n\n## License\n\n[MIT](./LICENSE)\n\n\n\n",
        "label": {
          "en_US": "nacos",
          "ja_JP": "nacos",
          "pt_BR": "nacos",
          "zh_Hans": "nacos"
        },
        "latest_package_identifier": "aias00/nacos:0.0.1@4169c9d199ffda874bfee36c99d076865fbd33fc55c24fe428024ec8246781ab",
        "latest_version": "0.0.1",
        "model": {},
        "name": "nacos",
        "org": "aias00",
        "plugin_id": "aias00/nacos",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/nacos.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "aias00",
            "description": {
              "en_US": "nacos client",
              "pt_BR": "nacos client",
              "zh_Hans": "nacos client"
            },
            "icon": "nacos-logo.png",
            "label": {
              "en_US": "nacos",
              "pt_BR": "nacos",
              "zh_Hans": "nacos"
            },
            "name": "nacos",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "nacos reader",
                  "pt_BR": "nacos reader",
                  "zh_Hans": "读取 nacos"
                },
                "llm": "A tool help with nacos config"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "aias00",
                "label": {
                  "en_US": "nacos reader",
                  "pt_BR": "nacos reader",
                  "zh_Hans": "读取 nacos"
                },
                "name": "nacos_reader"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Nacos server addresses",
                    "pt_BR": "Nacos server addresses",
                    "zh_Hans": "Nacos服务器地址列表"
                  },
                  "label": {
                    "en_US": "Server Addresses",
                    "pt_BR": "Server Addresses",
                    "zh_Hans": "服务器地址"
                  },
                  "llm_description": "Nacos server addresses list (e.g. localhost:8848)",
                  "max": null,
                  "min": null,
                  "name": "server_addresses",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Nacos username",
                    "pt_BR": "Nacos username",
                    "zh_Hans": "Nacos用户名"
                  },
                  "label": {
                    "en_US": "Username",
                    "pt_BR": "Username",
                    "zh_Hans": "用户名"
                  },
                  "llm_description": "The username for Nacos authentication",
                  "max": null,
                  "min": null,
                  "name": "username",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Nacos password",
                    "pt_BR": "Nacos password",
                    "zh_Hans": "Nacos密码"
                  },
                  "label": {
                    "en_US": "Password",
                    "pt_BR": "Password",
                    "zh_Hans": "密码"
                  },
                  "llm_description": "The password for Nacos authentication",
                  "max": null,
                  "min": null,
                  "name": "password",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Nacos namespace ID",
                    "pt_BR": "Nacos namespace ID",
                    "zh_Hans": "Nacos命名空间ID"
                  },
                  "label": {
                    "en_US": "Namespace",
                    "pt_BR": "Namespace",
                    "zh_Hans": "命名空间"
                  },
                  "llm_description": "The namespace ID in Nacos",
                  "max": null,
                  "min": null,
                  "name": "namespace",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Nacos configuration data ID",
                    "pt_BR": "Nacos configuration data ID",
                    "zh_Hans": "Nacos配置的数据ID"
                  },
                  "label": {
                    "en_US": "Data ID",
                    "pt_BR": "Data ID",
                    "zh_Hans": "配置ID"
                  },
                  "llm_description": "The data ID of the configuration in Nacos",
                  "max": null,
                  "min": null,
                  "name": "data_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Nacos configuration group",
                    "pt_BR": "Nacos configuration group",
                    "zh_Hans": "Nacos配置分组"
                  },
                  "label": {
                    "en_US": "Group",
                    "pt_BR": "Group",
                    "zh_Hans": "分组"
                  },
                  "llm_description": "The group name of the configuration in Nacos",
                  "max": null,
                  "min": null,
                  "name": "group",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "nacos writer",
                  "pt_BR": "nacos writer",
                  "zh_Hans": "写入 nacos"
                },
                "llm": "A tool help with nacos config"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "aias00",
                "label": {
                  "en_US": "nacos writer",
                  "pt_BR": "nacos writer",
                  "zh_Hans": "写入 nacos"
                },
                "name": "nacos_writer"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Nacos server addresses",
                    "pt_BR": "Nacos server addresses",
                    "zh_Hans": "Nacos服务器地址列表"
                  },
                  "label": {
                    "en_US": "Server Addresses",
                    "pt_BR": "Server Addresses",
                    "zh_Hans": "服务器地址"
                  },
                  "llm_description": "Nacos server addresses list (e.g. localhost:8848)",
                  "max": null,
                  "min": null,
                  "name": "server_addresses",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Nacos username",
                    "pt_BR": "Nacos username",
                    "zh_Hans": "Nacos用户名"
                  },
                  "label": {
                    "en_US": "Username",
                    "pt_BR": "Username",
                    "zh_Hans": "用户名"
                  },
                  "llm_description": "The username for Nacos authentication",
                  "max": null,
                  "min": null,
                  "name": "username",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Nacos password",
                    "pt_BR": "Nacos password",
                    "zh_Hans": "Nacos密码"
                  },
                  "label": {
                    "en_US": "Password",
                    "pt_BR": "Password",
                    "zh_Hans": "密码"
                  },
                  "llm_description": "The password for Nacos authentication",
                  "max": null,
                  "min": null,
                  "name": "password",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "content",
                    "pt_BR": "content",
                    "zh_Hans": "配置"
                  },
                  "label": {
                    "en_US": "content",
                    "pt_BR": "content",
                    "zh_Hans": "配置内容"
                  },
                  "llm_description": "content",
                  "max": null,
                  "min": null,
                  "name": "content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Nacos namespace ID",
                    "pt_BR": "Nacos namespace ID",
                    "zh_Hans": "Nacos命名空间ID"
                  },
                  "label": {
                    "en_US": "Namespace",
                    "pt_BR": "Namespace",
                    "zh_Hans": "命名空间"
                  },
                  "llm_description": "The namespace ID in Nacos",
                  "max": null,
                  "min": null,
                  "name": "namespace",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Nacos configuration data ID",
                    "pt_BR": "Nacos configuration data ID",
                    "zh_Hans": "Nacos配置的数据ID"
                  },
                  "label": {
                    "en_US": "Data ID",
                    "pt_BR": "Data ID",
                    "zh_Hans": "配置ID"
                  },
                  "llm_description": "The data ID of the configuration in Nacos",
                  "max": null,
                  "min": null,
                  "name": "data_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Nacos configuration group",
                    "pt_BR": "Nacos configuration group",
                    "zh_Hans": "Nacos配置分组"
                  },
                  "label": {
                    "en_US": "Group",
                    "pt_BR": "Group",
                    "zh_Hans": "分组"
                  },
                  "llm_description": "The group name of the configuration in Nacos",
                  "max": null,
                  "min": null,
                  "name": "group",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-01T21:16:37Z",
        "version_updated_at": "2025-04-01T21:16:37Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Time-based one-time password (TOTP)",
          "ja_JP": "Time-based one-time password (TOTP)",
          "pt_BR": "Senha única baseada em tempo (TOTP)",
          "zh_Hans": "动态口令 TOTP（Time based One Time Password)"
        },
        "category": "tool",
        "created_at": "2025-04-01T09:21:17Z",
        "endpoint": {},
        "icon": "alterxyz/packages/totp/_assets/lock-password-line.svg",
        "index_id": "alterxyz___totp",
        "install_count": 257,
        "introduction": "# TOTP Plugin\n\nTOTP (Time-based One-Time Password) is a dynamic authentication mechanism that enhances account security by generating time-sensitive passwords. This plugin provides TOTP verification and key generation capabilities for the Dify platform.\n\n## Getting Started\n\nRepository: [dify-plugins-collections/totp](https://github.com/alterxyz/dify-plugins-collections/tree/main/totp)\n\nFor issues, bug reports, or feature requests, please visit our [Issues page](https://github.com/alterxyz/dify-plugins-collections/issues).\n\nFeel free to contribute or provide feedback to help improve this plugin!\n\n## Features\n\nThis plugin offers two main tools:\n\n1. **TOTP Validator**\n\n    - Validates 6-digit TOTP codes submitted by users\n    - Supports both secret keys and provisioning URIs\n\n2. **TOTP Key Generator**\n    - Generates standard-compliant TOTP secret keys\n    - Optionally creates configuration with account and issuer information\n\n## Usage\n\n### TOTP Validator\n\nTo validate a TOTP code:\n\n- **secret_key**: TOTP secret key or provisioning URI (required)\n- **user_code**: 6-digit verification code from user (required)\n\nReturns:\n\n- Text message: Success or failure status\n- JSON response: Detailed verification results\n    - `status` - Verification result (\"success\" or \"fail\")\n    - `detail` - Detailed verification information. A 5-second time drift is allowed for compatibility.\n- Variable `True_or_False`: Verification result as string (\"True\" or \"False\")\n\n### TOTP Key Generator\n\nTo generate a new TOTP key:\n\n- **name**: Account name (optional)\n- **issuer_name**: Issuer name (optional)\n\nReturns:\n\n- Generated secret key\n- Provisioning URI (when account name and issuer name are provided)\n\n## Compatibility with Authenticator Apps\n\nDifferent authenticator applications have varying levels of support for TOTP setup methods:\n\n- **BitWarden**: Supports both secret keys and provisioning URIs\n- **Google Authenticator**: QR code scanning supports provisioning URIs only, manual entry supports secret keys only (requires user to input account name)\n- **Microsoft Authenticator**: QR code scanning supports provisioning URIs only\n- **Other apps**: Support varies; refer to the specific application's documentation\n\nWhen implementing TOTP authentication:\n- For maximum compatibility, provide both the secret key and a QR code containing the provisioning URI\n- For manual setup, ensure users have access to the secret key and relevant account/issuer information\n\n### Example\n\n![Example](_assets/image1.png)\n![Google Authenticator](_assets/IMG_3613.jpeg)\n\n## Security Considerations\n\n- Keep TOTP secret keys confidential\n- Use secure key management solutions for storing TOTP secrets\n- Ensure secure communication channels in production environments\n\n## Privacy\n\nThis plugin does not collect any user data. See [PRIVACY.md](PRIVACY.md) for details.\n",
        "label": {
          "en_US": "TOTP",
          "ja_JP": "TOTP",
          "pt_BR": "TOTP",
          "zh_Hans": "TOTP"
        },
        "latest_package_identifier": "alterxyz/totp:0.0.3@a59b4d279249f4fbeb6e77fe9c832d3710916766b7f253c6286f8609f7f28303",
        "latest_version": "0.0.3",
        "model": {},
        "name": "totp",
        "org": "alterxyz",
        "plugin_id": "alterxyz/totp",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/totp.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {}
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "utilities"
          }
        ],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "alterxyz",
            "description": {
              "en_US": "Time-based one-time password (TOTP)",
              "pt_BR": "Time-based one-time password (TOTP)",
              "zh_Hans": "动态口令 Time-based one-time password (TOTP)"
            },
            "icon": "lock-password-line.svg",
            "label": {
              "en_US": "TOTP",
              "pt_BR": "TOTP",
              "zh_Hans": "动态口令 (TOTP)"
            },
            "name": "totp",
            "tags": [
              "productivity",
              "utilities"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Time-based one-time password (TOTP) validator",
                  "pt_BR": "Validador de senha única baseado em tempo (TOTP)",
                  "zh_Hans": "基于时间的一次性密码 (TOTP) 验证器"
                },
                "llm": "Time-based one-time password (TOTP) validator, this tool is used to validate a 6 digit TOTP code with a secret key or provisioning URI. You should keep the secret key secret, and warn the user to not share it with anyone and so on in best practices about cybersecurity."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "alterxyz",
                "label": {
                  "en_US": "TOTP Validator",
                  "pt_BR": "Validador TOTP",
                  "zh_Hans": "TOTP 验证器"
                },
                "name": "totp"
              },
              "output_schema": {
                "properties": {
                  "True_or_False": {
                    "description": "Whether the TOTP is valid or not, return in string format, \"True\" or \"False\".",
                    "type": "string"
                  }
                },
                "type": "object"
              },
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The secret key or provisioning URI used to generate the TOTP",
                    "pt_BR": "A chave secreta ou URI de provisionamento usada para gerar o TOTP",
                    "zh_Hans": "用于生成 TOTP 的私钥或 URI"
                  },
                  "label": {
                    "en_US": "TOTP secret key or provisioning URI",
                    "pt_BR": "Chave secreta TOTP ou URI de provisionamento",
                    "zh_Hans": "TOTP 私钥或 URI"
                  },
                  "llm_description": "The secret key or provisioning URI (starting with 'otpauth://') used to generate the TOTP, this is highly sensitive and should be kept secret.",
                  "max": null,
                  "min": null,
                  "name": "secret_key",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "6 digit TOTP code to validate",
                    "pt_BR": "Código TOTP de 6 dígitos para validar",
                    "zh_Hans": "要验证的 6 位 TOTP 代码"
                  },
                  "label": {
                    "en_US": "6 digit TOTP code to validate",
                    "pt_BR": "Código TOTP de 6 dígitos para validar",
                    "zh_Hans": "要验证的 6 位 TOTP 代码"
                  },
                  "llm_description": "6 digit TOTP code to validate",
                  "max": null,
                  "min": null,
                  "name": "user_code",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Generate a random secret key that conforms to the TOTP standard",
                  "pt_BR": "Gera uma chave secreta TOTP aleatória",
                  "zh_Hans": "随机生成一个符合 TOTP 标准的秘钥"
                },
                "llm": "Generate a random secret key that conforms to the TOTP standard"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "alterxyz",
                "label": {
                  "en_US": "TOTP Secret Key Generator",
                  "pt_BR": "Gerador de chave secreta TOTP",
                  "zh_Hans": "TOTP 秘钥生成"
                },
                "name": "secret_generator"
              },
              "output_schema": {
                "properties": {
                  "provisioning_uri": {
                    "description": "Provisioning URI - available if name and issuer_name are provided",
                    "type": "string"
                  }
                },
                "type": "object"
              },
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The name of the account this TOTP is for",
                    "pt_BR": "O nome da conta para qual este TOTP é destinado",
                    "zh_Hans": "此 TOTP 对应的账户名称"
                  },
                  "label": {
                    "en_US": "Account Name",
                    "pt_BR": "Nome da conta",
                    "zh_Hans": "账户名称"
                  },
                  "llm_description": "The account name to be used in the TOTP URI",
                  "max": null,
                  "min": null,
                  "name": "name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The name of the organization issuing the TOTP",
                    "pt_BR": "O nome da organização que emite o TOTP",
                    "zh_Hans": "发行 TOTP 的组织名称"
                  },
                  "label": {
                    "en_US": "Issuer Name",
                    "pt_BR": "Nome do emissor",
                    "zh_Hans": "发行方名称"
                  },
                  "llm_description": "The issuer name to be used in the TOTP URI",
                  "max": null,
                  "min": null,
                  "name": "issuer_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-09T01:14:31Z",
        "version_updated_at": "2025-04-09T01:14:31Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "D-ID is a tool enabling the creation of high-quality, custom videos of Digital Humans from a single image."
        },
        "category": "tool",
        "created_at": "2024-12-04T04:55:06Z",
        "endpoint": {},
        "icon": "langgenius/packages/did/_assets/icon.svg",
        "index_id": "langgenius___did",
        "install_count": 254,
        "introduction": "",
        "label": {
          "en_US": "D-ID"
        },
        "latest_package_identifier": "langgenius/did:0.0.2@33970ce58ab9cbef2fae31e0566f8f541d03cefb62f633ddd18948c84d709a25",
        "latest_version": "0.0.2",
        "model": {},
        "name": "did",
        "org": "langgenius",
        "plugin_id": "langgenius/did",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/did.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "videos"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "D-ID server's Base URL"
              },
              "name": "base_url",
              "options": null,
              "placeholder": {
                "en_US": "https://api.d-id.com"
              },
              "required": false,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "D-ID API Key"
              },
              "name": "did_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your D-ID API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://studio.d-id.com/account-settings"
            }
          ],
          "identity": {
            "author": "Matri Qi",
            "description": {
              "en_US": "D-ID is a tool enabling the creation of high-quality, custom videos of Digital Humans from a single image."
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "D-ID"
            },
            "name": "did",
            "tags": [
              "videos"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Animations enables to create videos matching head movements, expressions, emotions, and voice from a driver video and image."
                },
                "llm": "Animations enables to create videos matching head movements, expressions, emotions, and voice from a driver video and image."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Matri Qi",
                "label": {
                  "en_US": "Animations"
                },
                "name": "animations"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The URL of the source image to be animated by the driver video, or a selection from the list of provided studio actors."
                  },
                  "label": {
                    "en_US": "source url"
                  },
                  "llm_description": "The URL of the source image to be animated by the driver video, or a selection from the list of provided studio actors.",
                  "max": null,
                  "min": null,
                  "name": "source_url",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The URL of the driver video to drive the animation, or a provided driver name from D-ID."
                  },
                  "label": {
                    "en_US": "driver url"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "driver_url",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Mutes the driver sound in the animated video result, defaults to true"
                  },
                  "label": {
                    "en_US": "mute"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "mute",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "If enabled, the driver video will be stitched with the animationing head video."
                  },
                  "label": {
                    "en_US": "stitch"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "stitch",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The URL of the logo image to be added to the animation video."
                  },
                  "label": {
                    "en_US": "logo url"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "logo_url",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The x position of the logo image in the animation video. It's required when logo url is provided."
                  },
                  "label": {
                    "en_US": "logo position x"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "logo_x",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The y position of the logo image in the animation video. It's required when logo url is provided."
                  },
                  "label": {
                    "en_US": "logo position y"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "logo_y",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "mp4",
                  "form": "form",
                  "human_description": {
                    "en_US": "The format of the result video."
                  },
                  "label": {
                    "en_US": "result format"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "result_format",
                  "options": [
                    {
                      "label": {
                        "en_US": "mp4"
                      },
                      "value": "mp4"
                    },
                    {
                      "label": {
                        "en_US": "gif"
                      },
                      "value": "gif"
                    },
                    {
                      "label": {
                        "en_US": "mov"
                      },
                      "value": "mov"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Talks enables the creation of realistic talking head videos from text or audio inputs."
                },
                "llm": "Talks enables the creation of realistic talking head videos from text or audio inputs."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Matri Qi",
                "label": {
                  "en_US": "Talks"
                },
                "name": "talks"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The URL of the source image to be animated by the driver video, or a selection from the list of provided studio actors."
                  },
                  "label": {
                    "en_US": "source url"
                  },
                  "llm_description": "The URL of the source image to be animated by the driver video, or a selection from the list of provided studio actors.",
                  "max": null,
                  "min": null,
                  "name": "source_url",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The URL of the driver video to drive the talk, or a provided driver name from D-ID."
                  },
                  "label": {
                    "en_US": "driver url"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "driver_url",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The type of the script."
                  },
                  "label": {
                    "en_US": "script type"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "script_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "text"
                      },
                      "value": "text"
                    },
                    {
                      "label": {
                        "en_US": "audio"
                      },
                      "value": "audio"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The text input to be spoken by the talking head. Required when script type is text."
                  },
                  "label": {
                    "en_US": "text input"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "text_input",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The URL of the audio file to be spoken by the talking head. Required when script type is audio."
                  },
                  "label": {
                    "en_US": "audio url"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "audio_url",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "If enabled, the audio will be processed to reduce noise before being spoken by the talking head. It only works when script type is audio."
                  },
                  "label": {
                    "en_US": "audio reduce noise"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "audio_reduce_noise",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "If enabled, the driver video will be stitched with the talking head video."
                  },
                  "label": {
                    "en_US": "stitch"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "stitch",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "If enabled, the talking head video will be sharpened."
                  },
                  "label": {
                    "en_US": "sharpen"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "sharpen",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The format of the result video."
                  },
                  "label": {
                    "en_US": "result format"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "result_format",
                  "options": [
                    {
                      "label": {
                        "en_US": "mp4"
                      },
                      "value": "mp4"
                    },
                    {
                      "label": {
                        "en_US": "gif"
                      },
                      "value": "gif"
                    },
                    {
                      "label": {
                        "en_US": "mov"
                      },
                      "value": "mov"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Interpolate between the last & first frames of the driver video When used together with pad_audio can create a seamless transition between videos of the same driver"
                  },
                  "label": {
                    "en_US": "fluent"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "fluent",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Pad the audio with silence at the end (given in seconds) Will increase the video duration & the credits it consumes"
                  },
                  "label": {
                    "en_US": "pad audio"
                  },
                  "llm_description": "",
                  "max": 60,
                  "min": 1,
                  "name": "pad_audio",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "timed expressions for animation. It should be an JSON array style string. Take D-ID documentation(https://docs.d-id.com/reference/createtalk) for more information."
                  },
                  "label": {
                    "en_US": "driver expressions"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "driver_expressions",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:04:31Z",
        "version_updated_at": "2025-02-17T07:04:31Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "PerfXCloud"
        },
        "category": "model",
        "created_at": "2025-02-17T07:00:46Z",
        "endpoint": {},
        "icon": "langgenius/packages/perfxcloud/_assets/icon_s_en.svg",
        "index_id": "langgenius___perfxcloud",
        "install_count": 251,
        "introduction": "",
        "label": {
          "en_US": "perfxcloud"
        },
        "latest_package_identifier": "langgenius/perfxcloud:0.0.5@986398c2da42e7edc3a02d9ce69abb7bc60ba8157c50fc249631f2a3674314e6",
        "latest_version": "0.0.5",
        "model": {
          "background": "#e3f0ff",
          "configurate_methods": [
            "predefined-model"
          ],
          "description": {
            "en_US": "PerfXCloud (Pengfeng Technology) is an AI development and deployment platform tailored for developers and enterprises, providing reasoning capabilities for multiple models.",
            "zh_Hans": "PerfXCloud（澎峰科技）为开发者和企业量身打造的AI开发和部署平台，提供多种模型的的推理能力。"
          },
          "help": {
            "title": {
              "en_US": "Get your API Key from PerfXCloud",
              "zh_Hans": "从 PerfXCloud 获取 API Key"
            },
            "url": {
              "en_US": "https://cloud.perfxlab.cn/panel/token"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.svg"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "PerfXCloud",
            "zh_Hans": "PerfXCloud"
          },
          "model_credential_schema": null,
          "models": [
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Llama3-Chinese_v2"
              },
              "model": "Llama3-Chinese_v2",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 600,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 1248,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Meta-Llama-3-70B-Instruct-GPTQ-Int4"
              },
              "model": "Meta-Llama-3-70B-Instruct-GPTQ-Int4",
              "model_properties": {
                "context_size": 1024,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 600,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 1248,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Meta-Llama-3-8B-Instruct"
              },
              "model": "Meta-Llama-3-8B-Instruct",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 600,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 1248,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Meta-Llama-3.1-405B-Instruct-AWQ-INT4"
              },
              "model": "Meta-Llama-3.1-405B-Instruct-AWQ-INT4",
              "model_properties": {
                "context_size": 410960,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 600,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 1248,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Meta-Llama-3.1-8B-Instruct"
              },
              "model": "Meta-Llama-3.1-8B-Instruct",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.1,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 600,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 1248,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen-14B-Chat-Int4"
              },
              "model": "Qwen-14B-Chat-Int4",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 600,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 1248,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen1.5-110B-Chat-GPTQ-Int4"
              },
              "model": "Qwen1.5-110B-Chat-GPTQ-Int4",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 128,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 256,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen1.5-72B-Chat-GPTQ-Int4"
              },
              "model": "Qwen1.5-72B-Chat-GPTQ-Int4",
              "model_properties": {
                "context_size": 2048,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 600,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen1.5-7B"
              },
              "model": "Qwen1.5-7B",
              "model_properties": {
                "context_size": 32768,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 600,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen2-72B-Instruct-AWQ-int4"
              },
              "model": "Qwen2-72B-Instruct-AWQ-int4",
              "model_properties": {
                "context_size": 32768,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 600,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 1248,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0"
              }
            },
            {
              "deprecated": true,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen2-72B-Instruct-GPTQ-Int4"
              },
              "model": "Qwen2-72B-Instruct-GPTQ-Int4",
              "model_properties": {
                "context_size": 2048,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.7,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 600,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen2-72B-Instruct"
              },
              "model": "Qwen2-72B-Instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 600,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 1248,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen2-7B-Instruct"
              },
              "model": "Qwen2-7B-Instruct",
              "model_properties": {
                "context_size": 32768,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 600,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0"
              }
            },
            {
              "deprecated": true,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen2-7B"
              },
              "model": "Qwen2-7B",
              "model_properties": {
                "context_size": 32768,
                "mode": "completion"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.3,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 600,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 2000,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen2.5-72B-Instruct"
              },
              "model": "Qwen2.5-72B-Instruct",
              "model_properties": {
                "context_size": 30720,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 600,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 1248,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Qwen2.5-7B-Instruct"
              },
              "model": "Qwen2.5-7B-Instruct",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 600,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 1248,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Reflection-Llama-3.1-70B"
              },
              "model": "Reflection-Llama-3.1-70B",
              "model_properties": {
                "context_size": 10240,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 600,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 1248,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Yi-1_5-9B-Chat-16K"
              },
              "model": "Yi-1_5-9B-Chat-16K",
              "model_properties": {
                "context_size": 16384,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 600,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 1248,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Yi-Coder-1.5B-Chat"
              },
              "model": "Yi-Coder-1.5B-Chat",
              "model_properties": {
                "context_size": 20480,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 600,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 1248,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "Yi-Coder-9B-Chat"
              },
              "model": "Yi-Coder-9B-Chat",
              "model_properties": {
                "context_size": 20480,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 600,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 1248,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "chatglm3-6b"
              },
              "model": "chatglm3-6b",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 600,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 1248,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "deepseek-v2-chat"
              },
              "model": "deepseek-v2-chat",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 600,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 1248,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "deepseek-v2-lite-chat"
              },
              "model": "deepseek-v2-lite-chat",
              "model_properties": {
                "context_size": 2048,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0.5,
                  "help": {
                    "en_US": "Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.",
                    "zh_Hans": "用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。"
                  },
                  "label": {
                    "en_US": "temperature"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 600,
                  "help": {
                    "en_US": "It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.",
                    "zh_Hans": "用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。"
                  },
                  "label": {
                    "en_US": "max_tokens"
                  },
                  "max": 1248,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                },
                {
                  "default": 0.8,
                  "help": {
                    "en_US": "The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.",
                    "zh_Hans": "生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "top_p"
                  },
                  "max": 0.9,
                  "min": 0.1,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": null,
                  "help": {
                    "en_US": "The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.",
                    "zh_Hans": "生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 99,
                  "min": 0,
                  "name": "top_k",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 1.1,
                  "help": {
                    "en_US": "Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.",
                    "zh_Hans": "用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。"
                  },
                  "label": {
                    "en_US": "Repetition penalty"
                  },
                  "max": null,
                  "min": null,
                  "name": "repetition_penalty",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "float",
                  "use_template": null
                }
              ],
              "pricing": {
                "currency": "RMB",
                "input": "0",
                "output": "0",
                "unit": "0"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "BAAI/bge-large-en-v1.5"
              },
              "model": "BAAI/bge-large-en-v1.5",
              "model_properties": {
                "context_size": 32768
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "BAAI/bge-large-zh-v1.5"
              },
              "model": "BAAI/bge-large-zh-v1.5",
              "model_properties": {
                "context_size": 32768
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "BAAI/bge-m3"
              },
              "model": "BAAI/bge-m3",
              "model_properties": {
                "context_size": 32768
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": null
            },
            {
              "deprecated": true,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gte-Qwen2-7B-instruct"
              },
              "model": "gte-Qwen2-7B-instruct",
              "model_properties": {
                "context_size": 2048
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": null
            }
          ],
          "position": {
            "llm": [
              "Qwen2.5-72B-Instruct",
              "Qwen2.5-7B-Instruct",
              "Qwen2-72B-Instruct",
              "Qwen2-72B-Instruct-AWQ-int4",
              "Qwen2-72B-Instruct-GPTQ-Int4",
              "Qwen2-7B-Instruct",
              "Qwen2-7B",
              "Qwen1.5-110B-Chat-GPTQ-Int4",
              "Qwen1.5-72B-Chat-GPTQ-Int4",
              "Qwen1.5-7B",
              "Qwen-14B-Chat-Int4",
              "Yi-Coder-1.5B-Chat",
              "Yi-Coder-9B-Chat",
              "Yi-1_5-9B-Chat-16K",
              "Reflection-Llama-3.1-70B",
              "Meta-Llama-3.1-8B-Instruct",
              "Meta-Llama-3.1-405B-Instruct-AWQ-INT4",
              "Meta-Llama-3-70B-Instruct-GPTQ-Int4",
              "Meta-Llama-3-8B-Instruct",
              "Llama3-Chinese_v2",
              "deepseek-v2-lite-chat",
              "deepseek-v2-chat",
              "chatglm3-6b"
            ],
            "text_embedding": [
              "gte-Qwen2-7B-instruct",
              "BAAI/bge-large-en-v1.5",
              "BAAI/bge-large-zh-v1.5",
              "BAAI/bge-m3"
            ]
          },
          "provider": "perfxcloud",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Custom API endpoint URL",
                  "zh_Hans": "自定义 API endpoint 地址"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Base URL, e.g. https://cloud.perfxlab.cn/v1",
                  "zh_Hans": "Base URL, e.g. https://cloud.perfxlab.cn/v1"
                },
                "required": false,
                "show_on": [],
                "type": "text-input",
                "variable": "endpoint_url"
              }
            ]
          },
          "supported_model_types": [
            "llm",
            "text-embedding"
          ]
        },
        "name": "perfxcloud",
        "org": "langgenius",
        "plugin_id": "langgenius/perfxcloud",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/perfxcloud.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-16T06:18:13Z",
        "version_updated_at": "2025-04-16T06:18:13Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "An image compression tool",
          "ja_JP": "An image compression tool",
          "pt_BR": "An image compression tool",
          "zh_Hans": "图片压缩工具"
        },
        "category": "tool",
        "created_at": "2025-04-18T20:33:20Z",
        "endpoint": {},
        "icon": "liuxin/packages/image-compression/_assets/icon.svg",
        "index_id": "liuxin___image-compression",
        "install_count": 245,
        "introduction": "## Image Compression Tool 图像压缩工具\n\n**Author:** [liuxin](https://github.com/liuxinjl)\n**Version:** 0.0.1\n**Type:** tool\n\n### Description\nAn image compression tool that effectively reduces file size while preserving image quality. It optimizes the user upload experience and server storage efficiency, significantly improving the processing efficiency of image-related services.\n\n图像压缩工具，能够在保持图像质量的同时有效减小文件大小，优化用户上传体验和服务器存储效率，可有效提升图像相关业务的处理效率。\n![alt text](<_assets/screen_1.png>)\n\n\nThe tool solves the URL exception issue currently encountered in the Dify system when retrieving images, by configuring Dify URLs.\n\n通过Dify URL配置，解决了当前dify系统中获取图片时抛出的URL异常问题。\n![alt text](<_assets/screen_2.png>)\n\n- **Batch** Compression: Supports processing multiple images simultaneously\n- **Format** Compatibility: Compatible with common formats such as JPG and PNG\n- **Custom** Parameters: Allows adjustment of compression quality through configurable size parameters\n\n- **批量压缩**：支持多张图片同时处理\n- **支持多种格式**：兼容JPG、PNG等常见图片格式\n- **自定义参数**：可通过尺寸参数配置，调整压缩质量。\n",
        "label": {
          "en_US": "Image Compression",
          "ja_JP": "Image Compression",
          "pt_BR": "Image Compression",
          "zh_Hans": "图片压缩"
        },
        "latest_package_identifier": "liuxin/image-compression:0.0.1@2d8e41211aba443c97e45080450bd448652212097ab6ed1abb6b3b57468d199d",
        "latest_version": "0.0.1",
        "model": {},
        "name": "image-compression",
        "org": "liuxin",
        "plugin_id": "liuxin/image-compression",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/image-compression.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "liuxin",
            "description": {
              "en_US": "An image compression tool that helps you effectively reduce image file size while maintaining acceptable image quality.",
              "pt_BR": "An image compression tool that helps you effectively reduce image file size while maintaining acceptable image quality.",
              "zh_Hans": "图像压缩工具，可以帮助您有效减小图片文件大小，同时保持可接受的图像质量。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Image Compression",
              "pt_BR": "Image Compression",
              "zh_Hans": "图片压缩"
            },
            "name": "image_compression",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "An image compression tool",
                  "pt_BR": "An image compression tool",
                  "zh_Hans": "图片压缩工具"
                },
                "llm": "An image compression tool"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "liuxin",
                "label": {
                  "en_US": "ImageCompression",
                  "pt_BR": "ImageCompression",
                  "zh_Hans": "图片压缩"
                },
                "name": "image_compression"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "An image compression tool",
                    "pt_BR": "An image compression tool",
                    "zh_Hans": "用于图片压缩"
                  },
                  "label": {
                    "en_US": "Image file",
                    "pt_BR": "Image file",
                    "zh_Hans": "图片文件"
                  },
                  "llm_description": "An image compression tool",
                  "max": null,
                  "min": null,
                  "name": "input_image",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "files"
                },
                {
                  "auto_generate": null,
                  "default": "http://localhost:8000",
                  "form": "form",
                  "human_description": {
                    "en_US": "The host URL for the image compression tool",
                    "pt_BR": "The host URL for the image compression tool",
                    "zh_Hans": "用于图片URL的主机地址"
                  },
                  "label": {
                    "en_US": "Host URL",
                    "pt_BR": "Host URL",
                    "zh_Hans": "Dify 地址"
                  },
                  "llm_description": "The host URL for the image compression tool",
                  "max": null,
                  "min": null,
                  "name": "host_url",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 1,
                  "form": "form",
                  "human_description": {
                    "en_US": "The target size for the image",
                    "pt_BR": "The target size for the image",
                    "zh_Hans": "目标大小"
                  },
                  "label": {
                    "en_US": "Target size (MB)",
                    "pt_BR": "Target size (MB)",
                    "zh_Hans": "目标大小（MB）"
                  },
                  "llm_description": "The target size for the image compression tool",
                  "max": null,
                  "min": null,
                  "name": "target_size",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-18T20:33:32Z",
        "version_updated_at": "2025-04-18T20:33:32Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Models provided by OCI, such as Cohere Command R and Cohere Command R+.",
          "zh_Hans": "OCI 提供的模型，例如 Cohere Command R 和 Cohere Command R+。"
        },
        "category": "model",
        "created_at": "2024-12-06T10:52:25Z",
        "endpoint": {},
        "icon": "langgenius/packages/oci/_assets/icon_s_en.svg",
        "index_id": "langgenius___oci",
        "install_count": 241,
        "introduction": "## Overview\n\n[OCI Generative AI](https://www.oracle.com/ca-en/artificial-intelligence/generative-ai/generative-ai-service/) offers a range of pre-trained large language models (LLMs) and multimodal models for various AI tasks. It enables text generation, code generation, image creation, and content automation. These models support fine-tuning for specific applications. The platform allows users to build custom AI models leveraging these core functionalities. OCI Generative AI provides the infrastructure for secure and scalable deployment. It empowers users across industries with practical and diverse AI capabilities.\n\n## Configure\n\nAfter installing the plugin, configure the API key and API base within the Model Provider settings. Obtain your API key from [here](https://docs.cloud.oracle.com/Content/API/Concepts/sdkconfig.htm). Once saved, you can begin using OCI Generative AI to build your AI agents and agentic workflows.\n\n![](./_assets/oci_config.PNG)",
        "label": {
          "en_US": "OCIGenerativeAI"
        },
        "latest_package_identifier": "langgenius/oci:0.0.3@214e701517ed48edf8bc14a5b9cc310e999de00c5166d1d543f2749c7a650e31",
        "latest_version": "0.0.3",
        "model": {
          "background": "#FFFFFF",
          "configurate_methods": [
            "predefined-model"
          ],
          "description": {
            "en_US": "Models provided by OCI, such as Cohere Command R and Cohere Command R+.",
            "zh_Hans": "OCI 提供的模型，例如 Cohere Command R 和 Cohere Command R+。"
          },
          "help": {
            "title": {
              "en_US": "Get your API Key from OCI",
              "zh_Hans": "从 OCI 获取 API Key"
            },
            "url": {
              "en_US": "https://docs.cloud.oracle.com/Content/API/Concepts/sdkconfig.htm"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.svg"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "OCIGenerativeAI"
          },
          "model_credential_schema": null,
          "models": [
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "cohere.command-r-08-2024 v1.7"
              },
              "model": "cohere.command-r-08-2024",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.75,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "topP",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "topK",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presencePenalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequencyPenalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 600,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 4000,
                  "min": 1,
                  "name": "maxTokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0009",
                "output": "0.0009",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "cohere.command-r-16k v1.2"
              },
              "model": "cohere.command-r-16k",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.75,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "topP",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "topK",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presencePenalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequencyPenalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 600,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 4000,
                  "min": 1,
                  "name": "maxTokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.004",
                "output": "0.004",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "cohere.command-r-plus v1.6"
              },
              "model": "cohere.command-r-plus-08-2024",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.75,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "topP",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "topK",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presencePenalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequencyPenalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 600,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 4000,
                  "min": 1,
                  "name": "maxTokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0156",
                "output": "0.0156",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "multi-tool-call",
                "agent-thought",
                "stream-tool-call"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "cohere.command-r-plus v1.2"
              },
              "model": "cohere.command-r-plus",
              "model_properties": {
                "context_size": 128000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.75,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "topP",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "topK",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "presencePenalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "frequencyPenalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 600,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 4000,
                  "min": 1,
                  "name": "maxTokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0219",
                "output": "0.0219",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": true,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "meta.llama-3-70b-instruct",
                "zh_Hans": "meta.llama-3-70b-instruct"
              },
              "model": "meta.llama-3-70b-instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.75,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "topP",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "topK",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presencePenalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequencyPenalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 600,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 8000,
                  "min": 1,
                  "name": "maxTokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.015",
                "output": "0.015",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "meta.llama-3.1-405b-instruct",
                "zh_Hans": "meta.llama-3.1-405b-instruct"
              },
              "model": "meta.llama-3.1-405b-instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.75,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "topP",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "topK",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presencePenalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequencyPenalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 600,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 4000,
                  "min": 1,
                  "name": "maxTokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0267",
                "output": "0.0267",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "meta.llama-3.2-90b-vision-instruct",
                "zh_Hans": "meta.llama-3.2-90b-vision-instruct"
              },
              "model": "meta.llama-3.2-90b-vision-instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.75,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "topP",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "topK",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presencePenalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequencyPenalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 600,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 4000,
                  "min": 1,
                  "name": "maxTokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.005",
                "output": "0.005",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "meta.llama-3.3-70b-instruct",
                "zh_Hans": "meta.llama-3.3-70b-instruct"
              },
              "model": "meta.llama-3.3-70b-instruct",
              "model_properties": {
                "context_size": 131072,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 2,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 0.75,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "topP",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Only sample from the top K options for each subsequent token.",
                    "zh_Hans": "仅从每个后续标记的前 K 个选项中采样。"
                  },
                  "label": {
                    "en_US": "Top k",
                    "zh_Hans": "取样数量"
                  },
                  "max": 500,
                  "min": 0,
                  "name": "topK",
                  "options": [],
                  "precision": null,
                  "required": false,
                  "type": "int",
                  "use_template": null
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens already in the text.",
                    "ja_JP": "テキストに既に存在するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens já presentes no texto.",
                    "zh_Hans": "对文本中已有的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Presence Penalty",
                    "ja_JP": "存在ペナルティ",
                    "pt_BR": "Penalidade de presença",
                    "zh_Hans": "存在惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "presencePenalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "presence_penalty"
                },
                {
                  "default": 0,
                  "help": {
                    "en_US": "Applies a penalty to the log-probability of tokens that appear in the text.",
                    "ja_JP": "テキストに出現するトークンの対数確率にペナルティを適用します。",
                    "pt_BR": "Aplica uma penalidade à probabilidade logarítmica de tokens que aparecem no texto.",
                    "zh_Hans": "对文本中出现的标记的对数概率施加惩罚。"
                  },
                  "label": {
                    "en_US": "Frequency Penalty",
                    "ja_JP": "頻度ペナルティ",
                    "pt_BR": "Penalidade de frequência",
                    "zh_Hans": "频率惩罚"
                  },
                  "max": 2,
                  "min": -2,
                  "name": "frequencyPenalty",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "frequency_penalty"
                },
                {
                  "default": 600,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 4000,
                  "min": 1,
                  "name": "maxTokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": {
                "currency": "USD",
                "input": "0.0018",
                "output": "0.0018",
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "cohere.embed-english-light-v2.0"
              },
              "model": "cohere.embed-english-light-v2.0",
              "model_properties": {
                "context_size": 1024,
                "max_chunks": 48
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.001",
                "output": null,
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "cohere.embed-english-light-v3.0"
              },
              "model": "cohere.embed-english-light-v3.0",
              "model_properties": {
                "context_size": 384,
                "max_chunks": 48
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.001",
                "output": null,
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "cohere.embed-english-v3.0"
              },
              "model": "cohere.embed-english-v3.0",
              "model_properties": {
                "context_size": 1024,
                "max_chunks": 48
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.001",
                "output": null,
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "cohere.embed-multilingual-light-v3.0"
              },
              "model": "cohere.embed-multilingual-light-v3.0",
              "model_properties": {
                "context_size": 384,
                "max_chunks": 48
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.001",
                "output": null,
                "unit": "0.0001"
              }
            },
            {
              "deprecated": false,
              "features": null,
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "cohere.embed-multilingual-v3.0"
              },
              "model": "cohere.embed-multilingual-v3.0",
              "model_properties": {
                "context_size": 1024,
                "max_chunks": 48
              },
              "model_type": "text-embedding",
              "parameter_rules": [],
              "pricing": {
                "currency": "USD",
                "input": "0.001",
                "output": null,
                "unit": "0.0001"
              }
            }
          ],
          "position": {
            "llm": [
              "cohere.command-r-08-2024",
              "cohere.command-r-plus-08-2024",
              "meta.llama-3.1-405b-instruct",
              "meta.llama-3.2-90b-vision-instruct",
              "meta.llama-3.3-70b-instruct"
            ],
            "text_embedding": [
              "cohere.embed-english-light-v2.0",
              "cohere.embed-english-light-v3.0",
              "cohere.embed-english-v3.0",
              "cohere.embed-multilingual-light-v3.0",
              "cohere.embed-multilingual-v3.0"
            ]
          },
          "provider": "oci",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "oci api key config file's content"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your oci api key config file's content(base64.b64encode(\"user_ocid/fingerprint/tenancy_ocid/region/compartment_ocid\".encode('utf-8')))",
                  "zh_Hans": "在此输入您的 oci api key config 文件的内容(base64.b64encode(\"user_ocid/fingerprint/tenancy_ocid/region/compartment_ocid\".encode('utf-8')))"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "oci_config_content"
              },
              {
                "default": null,
                "label": {
                  "en_US": "oci api key file's content"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your oci api key file's content(base64.b64encode(\"pem file content\".encode('utf-8')))",
                  "zh_Hans": "在此输入您的 oci api key 文件的内容(base64.b64encode(\"pem file content\".encode('utf-8')))"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "oci_key_content"
              }
            ]
          },
          "supported_model_types": [
            "llm",
            "text-embedding"
          ]
        },
        "name": "oci",
        "org": "langgenius",
        "plugin_id": "langgenius/oci",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/oci.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-02-27T12:56:35Z",
        "version_updated_at": "2025-02-27T12:56:35Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Reasoning-Augmented Generation in dify",
          "ja_JP": "Reasoning-Augmented Generation in dify",
          "pt_BR": "Reasoning-Augmented Generation in dify",
          "zh_Hans": "Reasoning-Augmented Generation in dify"
        },
        "category": "tool",
        "created_at": "2025-02-17T09:46:42Z",
        "endpoint": {},
        "icon": "yevanchen/packages/reag/_assets/reag.png",
        "index_id": "yevanchen___reag",
        "install_count": 234,
        "introduction": "# ReAG (Reasoning-Augmented Generation)\n\n**Author:** evan  \n**Version:** 0.0.1\n\n## Overview\n\nReAG is a method that skips the retrieval step entirely. Instead of preprocessing documents into searchable snippets, ReAG feeds raw materials—text files, web pages, spreadsheets—directly to the language model. The model then decides what matters and why, synthesizing answers in one go.\n\n## Traditional RAG vs ReAG\n\n### Traditional RAG System\nTraditional RAG systems typically operate in two phases:\n1. Semantic Search Phase: First uses retrieval techniques to select documents that are superficially similar to the query content\n2. Generation Phase: Then uses language models to generate answers from these documents\n\nHowever, this two-phase approach may overlook deeper contextual relationships in documents and potentially introduce irrelevant content.\n\n### ReAG's Unified Strategy\nReAG adopts a unified approach:\n- It passes raw document content directly to the language model, allowing the model to independently evaluate and integrate the complete context\n- This method produces more accurate, detailed answers that better reflect complex contextual relationships\n\n## How ReAG Cuts Through the Noise\n\nReAG operates on a simple idea: let the language model do the heavy lifting. Instead of relying on pre-built indexes or embeddings, ReAG hands the model raw documents and asks two questions:\n\n1. Is this document useful for the task?\n2. What specific parts of it matter?\n\n### Example\nIf you ask, \"Why are polar bear populations declining?\" a traditional RAG system might fetch documents containing phrases like \"Arctic ice melt\" or \"bear habitats.\" But ReAG goes further. It scans entire documents, considering their full context and meaning rather than just their semantic similarity to the query. A research paper titled \"Thermal Dynamics of Sea Ice\" might be ignored—unless the model notices a section linking ice loss to disruptions in bear feeding patterns.\n\nThis approach mirrors how humans research: we skim sources, discard irrelevant ones, and focus on passages that address our specific question. ReAG replicates this behavior programmatically, using the model's ability to infer connections rather than relying on superficial semantics.\n\n## Understanding the Difference\n\n### Traditional RAG\nOperates like a librarian:\n- Indexes books (documents) by summarizing their covers (embeddings)\n- Uses those summaries to guess which books might answer your question\n- Process is fast but reductive—prioritizes lexical proximity over functional utility\n\n### ReAG\nActs like a scholar:\n- Reads every book in full\n- Underlines relevant paragraphs\n- Synthesizes insights based on the query's deeper intent\n\n## Technical Implementation\n\n### Key Parameters in reag.yaml\nThe following parameters are utilized in reag.py:\n\n#### model\n- Determines the language model used for answer generation\n- Configured through LLMModelConfig with provider, model name, and operation mode\n\n#### query\n- User input string driving the answer generation process\n- Combined with system prompts (e.g., REAG_SYSTEM_PROMPT) to create complete prompt messages\n\n#### files\n- Optional parameter for file uploads\n- File content processed using MarkItDown module for text extraction\n\n### Workflow\n1. Tool trigger: reag.py's _invoke method receives parameters from reag.yaml (model, query, files)\n2. File processing: Creates temporary files and converts content to text using MarkItDown\n3. Parallel processing: Uses ThreadPoolExecutor for document processing\n4. Response structure: Returns JSON object containing:\n   - content: Generated answer\n   - reasoning: Explanation of reasoning process\n   - is_irrelevant: Boolean indicating relevance\n   - document: Original document info (name and content)\n\n## Trade-offs and Considerations\n\n### Challenges\n- **Cost**: Processing entire documents with LLMs is more expensive than vector search\n- **Speed**: Can struggle with massive datasets despite parallelization\n\n### Ideal Use Cases\n1. Complex, open-ended queries\n2. Dynamic data (news, research repositories)\n3. Multimodal data (images, tables, charts)\n\n## Future Prospects\n\n### Key Trends\n1. Cheaper, faster language models\n   - Improvement in open-source models (Llama, DeepSeek)\n   - Advancement in quantization techniques\n\n2. Larger context windows\n   - Expanding from millions to billions of tokens\n   - Enhanced document processing capabilities\n\n3. Hybrid systems\n   - Combining lightweight embedding filters with ReAG\n   - Balancing speed and accuracy\n\n## Resources\n- Twitter: https://x.com/pelaseyed/status/1886448015533089248\n- Blog: https://www.superagent.sh/blog/reag-reasoning-augmented-generation\n- GitHub: https://github.com/superagent-ai/reag/tree/main\n",
        "label": {
          "en_US": "reag",
          "ja_JP": "reag",
          "pt_BR": "reag",
          "zh_Hans": "reag"
        },
        "latest_package_identifier": "yevanchen/reag:0.0.1@721170a9a9ccde6b938c11ba76971f77a38721ea70cbe800ba8139829cf88b04",
        "latest_version": "0.0.1",
        "model": {},
        "name": "reag",
        "org": "yevanchen",
        "plugin_id": "yevanchen/reag",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/reag.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "yevanchen",
            "description": {
              "en_US": "Reasoning-Augmented Generation in dify",
              "pt_BR": "Reasoning-Augmented Generation in dify",
              "zh_Hans": "Reasoning-Augmented Generation in dify"
            },
            "icon": "reag.png",
            "label": {
              "en_US": "reag",
              "pt_BR": "reag",
              "zh_Hans": "reag"
            },
            "name": "reag",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Reasoning-Augmented Generation in dify",
                  "pt_BR": "Reasoning-Augmented Generation in dify",
                  "zh_Hans": "Reasoning-Augmented Generation in dify"
                },
                "llm": "Reasoning-Augmented Generation in dify"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Yevanchen",
                "label": {
                  "en_US": "reag",
                  "pt_BR": "reag",
                  "zh_Hans": "reag"
                },
                "name": "reag"
              },
              "output_schema": {
                "properties": {
                  "relevent_results": {
                    "items": {
                      "properties": {
                        "content": {
                          "type": "string"
                        },
                        "document": {
                          "properties": {
                            "content": {
                              "type": "string"
                            },
                            "name": {
                              "type": "string"
                            }
                          },
                          "type": "object"
                        },
                        "is_irrelevant": {
                          "type": "boolean"
                        },
                        "reasoning": {
                          "type": "string"
                        }
                      },
                      "type": "object"
                    },
                    "type": "array"
                  }
                },
                "type": "object"
              },
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Select the model to use for generation",
                    "pt_BR": "Selecione o modelo para geração",
                    "zh_Hans": "选择用于生成的模型"
                  },
                  "label": {
                    "en_US": "Model",
                    "pt_BR": "Modelo",
                    "zh_Hans": "模型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": "llm",
                  "template": null,
                  "type": "model-selector"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Reasoning-Augmented Generation in dify",
                    "pt_BR": "Reasoning-Augmented Generation in dify",
                    "zh_Hans": "Reasoning-Augmented Generation in dify"
                  },
                  "label": {
                    "en_US": "Query string",
                    "pt_BR": "Query string",
                    "zh_Hans": "查询语句"
                  },
                  "llm_description": "Reasoning-Augmented Generation in dify",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Upload files for processing",
                    "pt_BR": "Carregar arquivos para processamento",
                    "zh_Hans": "上传文件进行处理"
                  },
                  "label": {
                    "en_US": "Files",
                    "pt_BR": "Arquivos",
                    "zh_Hans": "文件"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "files",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "files"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T09:46:53Z",
        "version_updated_at": "2025-02-17T09:46:53Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "LlamaCloud client as API Endpoint to connect Dify External Knowledge Base",
          "ja_JP": "LlamaCloud client as API Endpoint to connect Dify External Knowledge Base",
          "pt_BR": "LlamaCloud client as API Endpoint to connect Dify External Knowledge Base",
          "zh_Hans": "LlamaCloud client as API Endpoint to connect Dify External Knowledge Base"
        },
        "category": "extension",
        "created_at": "2025-03-19T03:47:51Z",
        "endpoint": {
          "endpoints": [
            {
              "hidden": false,
              "method": "POST",
              "path": "/retrieval"
            }
          ],
          "settings": [
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "API key",
                "pt_BR": "API key",
                "zh_Hans": "API key"
              },
              "name": "llama_cloud_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your API key",
                "pt_BR": "Please input your API key",
                "zh_Hans": "请输入你的 API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            }
          ]
        },
        "icon": "langgenius/packages/llamacloud/_assets/icon.svg",
        "index_id": "langgenius___llamacloud",
        "install_count": 233,
        "introduction": "## llamacloud\n\n**Author:** langgenius\n**Version:** 0.0.1\n**Type:** extension\n\n### Description\n\nLlamaCloud is an online version of LlamaIndex with UI. \n\nIf you are trying to build AI Agent with context retrieving capability and you are not primarily using Dify's Knowledge Base, you can use Dify's External Knowledge Base to connect with the RAG solution you prefer. This plugin will help you deploy your LlamaCloud Index as an endpoint so Dify External Knowledge Base can seamlessly connect with it.\n\nTo set up an Index in LlamaCloud, in the **Tools: Index** section, click on Create Index. \n\n<img src=\"./_assets/llamacloud_index_create.png\" width=\"600\" />\n\nIn the Index panel, you can upload your data, connect vector storage and embedding model, configure parse settings.\n<img src=\"./_assets/llamacloud_index_panel.png\" width=\"600\" />\n\nOnce you set up your Index, you will get a Pipeline ID. \n<img src=\"./_assets/llama_cloud_pipeline_id.png\" width=\"600\" />\n\nGenerate an API Key here:\n<img src=\"./_assets/llama_cloud_api_key.png\" width=\"600\" />\n\nNow in Dify's marketplace, find LlamaCloud and install it.\nCreate a new endpoint by clicking here:\n<img src=\"./_assets/llamacloud_add_endpoint.png\" width=\"600\" />\n\nGive your endpoint a name, and paste the API Key we just created.\n<img src=\"./_assets/name_endpoint.png\" width=\"600\" />\n\nCopy the newly created Endpoint URL, go to Knowledge Base, \"External Knowledge API\", \"Add an External Knowledge API\", and paste the URL in \"API Endpoint\". \n\n**NOTICE: You must REMOVE the \"/retrieval\" in your URL!!!!!** For API Key, as we didn't configure any authorization, you can type in anything you want. So **PLEASE MAKE SURE NO ONE KNOWS THE ENDPOINT URL!!!**\n<img src=\"./_assets/paste_url.png\" width=\"600\" />\n\nOnce your external knowledge base is connected, go to \"connect to an external knowledge base\", type in the Pipeline ID in \"Knowledge ID\", give it a name, and we are good to go.\n<img src=\"./_assets/type_pipeline_id.png\" width=\"600\" />\n\nNow you can do a retrieval test of your External Knowledge Base.\n<img src=\"./_assets/retrieval_testing.png\" width=\"600\" />\n",
        "label": {
          "en_US": "Llamacloud",
          "ja_JP": "Llamacloud",
          "pt_BR": "Llamacloud",
          "zh_Hans": "Llamacloud"
        },
        "latest_package_identifier": "langgenius/llamacloud:0.0.1@974e81d3a82258b3d056f4f5430720d3dfc18ab4625a1096385ed83931049a2d",
        "latest_version": "0.0.1",
        "model": {},
        "name": "llamacloud",
        "org": "langgenius",
        "plugin_id": "langgenius/llamacloud",
        "plugins": {
          "agent_strategies": null,
          "endpoints": [
            "group/llamacloud.yaml"
          ],
          "models": null,
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "endpoint": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-03-19T03:48:13Z",
        "version_updated_at": "2025-03-19T03:48:13Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Search articles from the PubMed database.",
          "zh_Hans": "搜索 PubMed 数据库中的文献。"
        },
        "category": "tool",
        "created_at": "2025-03-31T12:51:56Z",
        "endpoint": {},
        "icon": "svcvit/packages/pubmed/_assets/icon.svg",
        "index_id": "svcvit___pubmed",
        "install_count": 231,
        "introduction": "# Dify PubMed Plugin\n\n**Author:** svcvit\n**Version:** 0.0.1\n**Type:** plugin\n\n## Description\n\nThis Dify plugin provides tools to interact with the National Library of Medicine's PubMed database, allowing users to search for biomedical literature and analyze the results directly within Dify workflows.\n\n![](./_assets/001.jpg)\n\n## Features\n\n*   **PubMed Search:** Search articles using keywords, filters (date range), and sorting options. Returns a list of PubMed IDs (PMIDs).\n*   **PubMed Details:** Retrieve detailed information for a specific PubMed article, including title, abstract, authors, journal, and more.\n*   **Advanced Search:** Perform targeted searches using specific fields like author, title, journal, MeSH terms, and more.\n\n![](./_assets/002.jpg)\n\n![](./_assets/003.jpg)\n\n![](./_assets/004.jpg)\n\n## Setup and Authorization\n\n1.  Add this plugin to your Dify application.\n2.  Authorize the plugin by providing:\n    *   **Email Address:** Your valid email address. This is **required** by NCBI for API access identification.\n    *   **NCBI API Key:** Required for PubMed API access.\n        \n        Steps to get an API Key:\n        1. Create an NCBI account (if you don't have one): https://www.ncbi.nlm.nih.gov/account/\n        2. Generate an API key:\n           - Go to https://www.ncbi.nlm.nih.gov/account/settings/\n           - Scroll down to the API Key section\n           - Click to create an API Key\n           - Copy the generated key\n\n## Usage\n\n### Tool: PubMed Search (`search`)\nAllows you to search the PubMed database using keywords and various filters. You can specify the maximum number of results, sort order (by relevance or publication date), and filter by publication date range.\n\n### Tool: PubMed Details (`fetch_details`)\nRetrieves comprehensive information about a specific article using its PubMed ID (PMID). This includes the article's title, abstract, authors, publication date, journal information, keywords, and MeSH terms.\n\n### Tool: Advanced Search (`advanced_search`)\nProvides more precise control over your PubMed searches by allowing you to target specific fields:\n- Author names\n- Article titles\n- Journal names\n- Abstract keywords\n- MeSH terms\n- General keywords\nPlus the same filtering options as the basic search (date range, sorting, etc.)\n\n## Contact\n\nFor support and feedback, please create an issue in the repository.",
        "label": {
          "en_US": "PubMed Search",
          "zh_Hans": "PubMed 搜索"
        },
        "latest_package_identifier": "svcvit/pubmed:0.0.1@0873814532f5918b2dafee86b582421e15dc97f4cbd146be5bb25f9d96f4f953",
        "latest_version": "0.0.1",
        "model": {},
        "name": "pubmed",
        "org": "svcvit",
        "plugin_id": "svcvit/pubmed",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/pubmed.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "endpoint": {
              "enabled": false
            },
            "model": {
              "enabled": false,
              "llm": false,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Your email address required by NCBI for PubMed API access.",
                "zh_Hans": "NCBI PubMed API 访问所需的您的电子邮件地址。"
              },
              "label": {
                "en_US": "Email Address",
                "zh_Hans": "电子邮件地址"
              },
              "name": "email",
              "options": null,
              "placeholder": {
                "en_US": "Please enter your email address",
                "zh_Hans": "请输入您的电子邮件地址"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "help": {
                "en_US": "NCBI API key required for PubMed API access. Get it from NCBI account settings.",
                "zh_Hans": "访问 PubMed API 所需的 NCBI API 密钥。请从 NCBI 账号设置中获取。"
              },
              "label": {
                "en_US": "NCBI API Key",
                "zh_Hans": "NCBI API 密钥"
              },
              "name": "api_key",
              "options": null,
              "placeholder": {
                "en_US": "Enter your NCBI API key (required)",
                "zh_Hans": "请输入 NCBI API 密钥（必填）"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            }
          ],
          "identity": {
            "author": "svcvit",
            "description": {
              "en_US": "Provides tools to interact with the PubMed database.",
              "zh_Hans": "提供与 PubMed 数据库交互的工具。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "PubMed Provider",
              "zh_Hans": "PubMed 提供者"
            },
            "name": "pubmed",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Searches the PubMed database for articles based on a query and optional filters. Returns a list of PubMed IDs (PMIDs).",
                  "zh_Hans": "基于查询和可选过滤器搜索 PubMed 数据库中的文献。返回 PubMed ID (PMID) 列表。"
                },
                "llm": "This tool searches the PubMed database using a query string and optional filters like date range and sorting. It returns a list of matching PubMed IDs (PMIDs). Use this tool when you need to find relevant medical or life sciences articles."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "svcvit",
                "label": {
                  "en_US": "PubMed Search",
                  "zh_Hans": "PubMed 搜索"
                },
                "name": "search"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The search terms (e.g., 'cancer immunotherapy', 'COVID-19 vaccine efficacy').",
                    "zh_Hans": "搜索词（例如，'cancer immunotherapy', 'COVID-19 vaccine efficacy'）。"
                  },
                  "label": {
                    "en_US": "Search Query",
                    "zh_Hans": "搜索查询"
                  },
                  "llm_description": "The main search query string. Can include keywords, author names, MeSH terms, etc. Use boolean operators (AND, OR, NOT) if needed.",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 100,
                  "form": "form",
                  "human_description": {
                    "en_US": "The maximum number of article IDs to return (default: 100).",
                    "zh_Hans": "要返回的文章 ID 的最大数量（默认值：100）。"
                  },
                  "label": {
                    "en_US": "Maximum Results",
                    "zh_Hans": "最大结果数"
                  },
                  "llm_description": "Specify the maximum number of PubMed IDs (PMIDs) to retrieve. Defaults to 100 if not specified.",
                  "max": null,
                  "min": null,
                  "name": "max_results",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "relevance",
                  "form": "form",
                  "human_description": {
                    "en_US": "How to sort the results (default: relevance).",
                    "zh_Hans": "如何对结果进行排序（默认值：相关性）。"
                  },
                  "label": {
                    "en_US": "Sort By",
                    "zh_Hans": "排序方式"
                  },
                  "llm_description": "Specifies the sort order for the results. 'relevance' is usually best, 'pub_date' sorts by publication date (newest first).",
                  "max": null,
                  "min": null,
                  "name": "sort",
                  "options": [
                    {
                      "label": {
                        "en_US": "Relevance",
                        "zh_Hans": "相关性"
                      },
                      "value": "relevance"
                    },
                    {
                      "label": {
                        "en_US": "Publication Date",
                        "zh_Hans": "发表日期"
                      },
                      "value": "pub_date"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Optional earliest publication date filter (format YYYY/MM/DD).",
                    "zh_Hans": "可选的最早发表日期过滤器（格式 YYYY/MM/DD）。"
                  },
                  "label": {
                    "en_US": "Start Date (YYYY/MM/DD)",
                    "zh_Hans": "开始日期 (YYYY/MM/DD)"
                  },
                  "llm_description": "Optional. Filter results to include only articles published on or after this date. Use YYYY/MM/DD format (e.g., '2020/01/01').",
                  "max": null,
                  "min": null,
                  "name": "min_date",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Optional latest publication date filter (format YYYY/MM/DD).",
                    "zh_Hans": "可选的最新发表日期过滤器（格式 YYYY/MM/DD）。"
                  },
                  "label": {
                    "en_US": "End Date (YYYY/MM/DD)",
                    "zh_Hans": "结束日期 (YYYY/MM/DD)"
                  },
                  "llm_description": "Optional. Filter results to include only articles published on or before this date. Use YYYY/MM/DD format (e.g., '2023/12/31').",
                  "max": null,
                  "min": null,
                  "name": "max_date",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Retrieves detailed information (title, abstract, authors, journal, etc.) for a specific PubMed ID (PMID).",
                  "zh_Hans": "检索指定 PubMed ID (PMID) 的详细信息（标题、摘要、作者、期刊等）。"
                },
                "llm": "This tool takes a single PubMed ID (PMID), usually obtained from the 'search' tool, and returns detailed information for the article, including title, abstract, authors, publication date, journal, keywords, and MeSH terms. Use this when you need the actual content summary or metadata of a specific article."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "svcvit",
                "label": {
                  "en_US": "Fetch PubMed Details",
                  "zh_Hans": "获取 PubMed 详情"
                },
                "name": "fetch_details"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Enter a single PubMed ID (e.g., '30622344').",
                    "zh_Hans": "输入单个 PubMed ID（例如，'30622344'）。"
                  },
                  "label": {
                    "en_US": "PubMed ID",
                    "zh_Hans": "PubMed ID"
                  },
                  "llm_description": "Provide a single PubMed ID (PMID) to fetch its detailed information. The PMID should be a valid number assigned by PubMed.",
                  "max": null,
                  "min": null,
                  "name": "pmids",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Performs an advanced search in PubMed targeting specific fields like author, title, journal, MeSH terms, etc. Returns a list of PubMed IDs (PMIDs).",
                  "zh_Hans": "在 PubMed 中执行高级搜索，可指定作者、标题、期刊、MeSH 术语等字段。返回 PubMed ID (PMID) 列表。"
                },
                "llm": "Use this tool for targeted PubMed searches. You can specify terms that must appear in specific fields (Author, Title, Journal, Abstract, MeSH Terms, Keywords). You can also combine these with date ranges and sorting. Returns a list of matching PubMed IDs. At least one search field or a general query is required."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "svcvit",
                "label": {
                  "en_US": "PubMed Advanced Search",
                  "zh_Hans": "PubMed 高级搜索"
                },
                "name": "advanced_search"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Search for specific authors (e.g., 'Fauci AS', 'Zhang Y[AU]').",
                    "zh_Hans": "搜索特定作者（例如，'Fauci AS', 'Zhang Y[AU]'）。"
                  },
                  "label": {
                    "en_US": "Author Name(s)",
                    "zh_Hans": "作者姓名"
                  },
                  "llm_description": "Enter author names to search for. Use format like 'LastName Initials' (e.g., 'Smith J'). You can use boolean operators (AND, OR).",
                  "max": null,
                  "min": null,
                  "name": "author",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Keywords that must appear in the article title.",
                    "zh_Hans": "必须出现在文章标题中的关键词。"
                  },
                  "label": {
                    "en_US": "Title Word(s)",
                    "zh_Hans": "标题词"
                  },
                  "llm_description": "Enter words or phrases that must be present in the article title.",
                  "max": null,
                  "min": null,
                  "name": "title",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Search within specific journals (e.g., 'Nature', 'Lancet').",
                    "zh_Hans": "在特定期刊中搜索（例如，'Nature', 'Lancet'）。"
                  },
                  "label": {
                    "en_US": "Journal Name",
                    "zh_Hans": "期刊名称"
                  },
                  "llm_description": "Enter the name or abbreviation of the journal to search within.",
                  "max": null,
                  "min": null,
                  "name": "journal",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Keywords that must appear in the article abstract.",
                    "zh_Hans": "必须出现在文章摘要中的关键词。"
                  },
                  "label": {
                    "en_US": "Abstract Word(s)",
                    "zh_Hans": "摘要词"
                  },
                  "llm_description": "Enter words or phrases that must be present in the article abstract.",
                  "max": null,
                  "min": null,
                  "name": "abstract_keywords",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Medical Subject Headings (e.g., 'Neoplasms', 'Immunotherapy').",
                    "zh_Hans": "医学主题词（例如，'Neoplasms', 'Immunotherapy'）。"
                  },
                  "label": {
                    "en_US": "MeSH Terms",
                    "zh_Hans": "MeSH 术语"
                  },
                  "llm_description": "Enter specific MeSH terms to find articles indexed with them. Use official MeSH terms.",
                  "max": null,
                  "min": null,
                  "name": "mesh_terms",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "General keywords provided by authors or indexers.",
                    "zh_Hans": "作者或索引员提供的一般关键词。"
                  },
                  "label": {
                    "en_US": "Keywords",
                    "zh_Hans": "关键词"
                  },
                  "llm_description": "Enter general keywords to search for. This searches a broader keyword field than MeSH terms.",
                  "max": null,
                  "min": null,
                  "name": "keywords",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "A general query used if no specific fields (author, title, etc.) are provided.",
                    "zh_Hans": "如果未提供特定字段（作者、标题等），则使用通用查询。"
                  },
                  "label": {
                    "en_US": "General Query (Optional)",
                    "zh_Hans": "通用查询（可选）"
                  },
                  "llm_description": "Optional. If you do not provide terms in specific fields like Author or Title, you can enter a general query here. If specific fields *are* used, this field is ignored.",
                  "max": null,
                  "min": null,
                  "name": "general_query",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 100,
                  "form": "form",
                  "human_description": {
                    "en_US": "The maximum number of article IDs to return (default: 100).",
                    "zh_Hans": "要返回的文章 ID 的最大数量（默认值：100）。"
                  },
                  "label": {
                    "en_US": "Maximum Results",
                    "zh_Hans": "最大结果数"
                  },
                  "llm_description": "Specify the maximum number of PubMed IDs (PMIDs) to retrieve. Defaults to 100 if not specified.",
                  "max": null,
                  "min": null,
                  "name": "max_results",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "relevance",
                  "form": "form",
                  "human_description": {
                    "en_US": "How to sort the results (default: relevance).",
                    "zh_Hans": "如何对结果进行排序（默认值：相关性）。"
                  },
                  "label": {
                    "en_US": "Sort By",
                    "zh_Hans": "排序方式"
                  },
                  "llm_description": "Specifies the sort order for the results.",
                  "max": null,
                  "min": null,
                  "name": "sort",
                  "options": [
                    {
                      "label": {
                        "en_US": "Relevance",
                        "zh_Hans": "相关性"
                      },
                      "value": "relevance"
                    },
                    {
                      "label": {
                        "en_US": "Publication Date",
                        "zh_Hans": "发表日期"
                      },
                      "value": "pub_date"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Optional earliest publication date filter (format YYYY/MM/DD).",
                    "zh_Hans": "可选的最早发表日期过滤器（格式 YYYY/MM/DD）。"
                  },
                  "label": {
                    "en_US": "Start Date (YYYY/MM/DD)",
                    "zh_Hans": "开始日期 (YYYY/MM/DD)"
                  },
                  "llm_description": "Optional. Filter results to include only articles published on or after this date. Use YYYY/MM/DD format.",
                  "max": null,
                  "min": null,
                  "name": "min_date",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Optional latest publication date filter (format YYYY/MM/DD).",
                    "zh_Hans": "可选的最新发表日期过滤器（格式 YYYY/MM/DD）。"
                  },
                  "label": {
                    "en_US": "End Date (YYYY/MM/DD)",
                    "zh_Hans": "结束日期 (YYYY/MM/DD)"
                  },
                  "llm_description": "Optional. Filter results to include only articles published on or before this date. Use YYYY/MM/DD format.",
                  "max": null,
                  "min": null,
                  "name": "max_date",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-31T12:52:13Z",
        "version_updated_at": "2025-03-31T12:52:13Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "The GPUStack tools enables seamless interaction with local large models for rapid development of personalized AI applications.",
          "zh_Hans": "GPUStack 工具集与本地大模型的无缝交互，用于快速构建个性化 AI 应用。"
        },
        "category": "tool",
        "created_at": "2025-02-15T04:28:21Z",
        "endpoint": {},
        "icon": "langgenius/packages/gpustack_tools/_assets/icon.svg",
        "index_id": "langgenius___gpustack_tools",
        "install_count": 231,
        "introduction": "## gpustack\n\n### Description\n\nThis is a plugin for Dify to integrate with GPUStack.\n\n### Features\n\n- Text to Image Generation with GPUStack image models.\n- Image editing with GPUStack image models.\n\n### Usage\n\n1. Install GPUStack. Please refer to the [GPUStack Installation Guide](https://docs.gpustack.ai/latest/quickstart/).\n\n2. Get the API key from the GPUStack Server. [Get API Key](https://docs.gpustack.ai/latest/user-guide/api-key-management/).\n\n3. Configure the API key in the Dify plugin configuration.\n",
        "label": {
          "en_US": "gpustack",
          "zh_Hans": "gpustack"
        },
        "latest_package_identifier": "langgenius/gpustack_tools:0.0.2@d3a61085ae87e3abbde67d41c10896a29208f7d330da82936dc7d03f1f1693c8",
        "latest_version": "0.0.2",
        "model": {},
        "name": "gpustack_tools",
        "org": "langgenius",
        "plugin_id": "langgenius/gpustack_tools",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/gpustack.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "image"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "GPUStack URL",
                "zh_Hans": "GPUStack URL"
              },
              "name": "base_url",
              "options": null,
              "placeholder": {
                "en_US": "GPUStack URL",
                "zh_Hans": "GPUStack 服务器 URL"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "API Key"
              },
              "name": "api_key",
              "options": null,
              "placeholder": {
                "en_US": "GPUStack API Key",
                "zh_Hans": "GPUStack API Key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://docs.gpustack.ai/latest/user-guide/api-key-management/"
            },
            {
              "default": true,
              "helper": null,
              "label": {
                "en_US": "Verify TLS",
                "zh_Hans": "验证证书"
              },
              "name": "tls_verify",
              "options": null,
              "placeholder": null,
              "required": false,
              "scope": null,
              "type": "boolean",
              "url": null
            }
          ],
          "identity": {
            "author": "GPUStack",
            "description": {
              "en_US": "GPUStack is an open-source GPU cluster manager for running AI models, providing efficient resource management and model deployment capabilities.",
              "zh_Hans": "GPUStack 是一款开源的 GPU 集群管理工具，专为 AI 模型部署和运行而设计。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "GPUStack",
              "zh_Hans": "GPUStack"
            },
            "name": "gpustack",
            "tags": [
              "image"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Generatring stunning images from textual descriptions, enabling applications in design, content creation, and more with GPUStack's image generation model.",
                  "zh_Hans": "GPUStack 的图像生成模型可将文字转化为精美图片，为设计和创作领域提供智能化创意工具。"
                },
                "llm": "This tool is used to generate image from textual descriptions."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "gpustack",
                "label": {
                  "en_US": "Text to Image",
                  "zh_Hans": "文本生成图片"
                },
                "name": "text2image"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The text prompt used to generate the image.",
                    "zh_Hans": "用于生成图片的文字提示词"
                  },
                  "label": {
                    "en_US": "prompt",
                    "zh_Hans": "提示词"
                  },
                  "llm_description": "this prompt text will be used to generate image.",
                  "max": null,
                  "min": null,
                  "name": "prompt",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "image model name that running in GPUStack.",
                    "zh_Hans": "在 GPUStack 上运行的图像模型名称。"
                  },
                  "label": {
                    "en_US": "Model",
                    "zh_Hans": "模型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 4.5,
                  "form": "form",
                  "human_description": {
                    "en_US": "Classifier-free guidance scale, affecting the image's adherence to the prompt.",
                    "zh_Hans": "无分类器引导比例，影响图片的对 Prompt 的贴合度。"
                  },
                  "label": {
                    "en_US": "CFG Scale"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "cfg_scale",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 1,
                  "form": "form",
                  "human_description": {
                    "en_US": "Number of images to generate.",
                    "zh_Hans": "生成图片数量。"
                  },
                  "label": {
                    "en_US": "Number",
                    "zh_Hans": "数量"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "n",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "512x512",
                  "form": "form",
                  "human_description": {
                    "en_US": "The maximum size of the generated image is controlled by the deployment parameters of the model.",
                    "zh_Hans": "图片生成的最大尺寸受控于模型的部署参数。"
                  },
                  "label": {
                    "en_US": "Image Size",
                    "zh_Hans": "图片尺寸"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "size",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "euler",
                  "form": "form",
                  "human_description": {
                    "en_US": "The sample method for the image generation model.",
                    "zh_Hans": "图像生成模型的采样方法。"
                  },
                  "label": {
                    "en_US": "Sample Method",
                    "zh_Hans": "采样方法"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "sample_method",
                  "options": [
                    {
                      "label": {
                        "en_US": "euler_a"
                      },
                      "value": "euler_a"
                    },
                    {
                      "label": {
                        "en_US": "euler"
                      },
                      "value": "euler"
                    },
                    {
                      "label": {
                        "en_US": "heun"
                      },
                      "value": "heun"
                    },
                    {
                      "label": {
                        "en_US": "dpm2"
                      },
                      "value": "dpm2"
                    },
                    {
                      "label": {
                        "en_US": "dpm++2s_a"
                      },
                      "value": "dpm++2s_a"
                    },
                    {
                      "label": {
                        "en_US": "dpm++2m"
                      },
                      "value": "dpm++2m"
                    },
                    {
                      "label": {
                        "en_US": "dpm++2mv2"
                      },
                      "value": "dpm++2mv2"
                    },
                    {
                      "label": {
                        "en_US": "ipndm"
                      },
                      "value": "ipndm"
                    },
                    {
                      "label": {
                        "en_US": "ipndm_v"
                      },
                      "value": "ipndm_v"
                    },
                    {
                      "label": {
                        "en_US": "icm"
                      },
                      "value": "icm"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 20,
                  "form": "form",
                  "human_description": {
                    "en_US": "Number of sampling steps to generate the image.",
                    "zh_Hans": "生成图片所需的采样步数。"
                  },
                  "label": {
                    "en_US": "Sampling Steps",
                    "zh_Hans": "采样步数"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "sampling_steps",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 4.5,
                  "form": "form",
                  "human_description": {
                    "en_US": "Guidance scale, affecting the quality and diversity of the image.",
                    "zh_Hans": "引导比例，影响图片的质量和多样性"
                  },
                  "label": {
                    "en_US": "Guidance"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "guidance",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "discrete",
                  "form": "form",
                  "human_description": {
                    "en_US": "Schedule Method",
                    "zh_Hans": "调度方法"
                  },
                  "label": {
                    "en_US": "Schedule Method",
                    "zh_Hans": "调度方法"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "schedule_method",
                  "options": [
                    {
                      "label": {
                        "en_US": "discrete"
                      },
                      "value": "discrete"
                    },
                    {
                      "label": {
                        "en_US": "karras"
                      },
                      "value": "karras"
                    },
                    {
                      "label": {
                        "en_US": "exponential"
                      },
                      "value": "exponential"
                    },
                    {
                      "label": {
                        "en_US": "ays"
                      },
                      "value": "ays"
                    },
                    {
                      "label": {
                        "en_US": "gits"
                      },
                      "value": "gits"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Text prompt that specifies what you don't want to see in the generated image.",
                    "zh_Hans": "指定在生成图片中不希望出现的内容的文本提示词。"
                  },
                  "label": {
                    "en_US": "Negative Prompt",
                    "zh_Hans": "负向提示"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "negative_prompt",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Random seed for image generation. Using the same seed will produce similar results.",
                    "zh_Hans": "图像生成的随机种子。使用相同的种子会产生相似的结果。"
                  },
                  "label": {
                    "en_US": "Seed"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 600,
                  "form": "form",
                  "human_description": {
                    "en_US": "The maximum time to wait for the image generation to complete(seconds).",
                    "zh_Hans": "等待图像生成完成的最大时间(秒)。"
                  },
                  "label": {
                    "en_US": "Timeout(seconds)",
                    "zh_Hans": "超时时间(秒)"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "timeout",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Edit images with GPUStack's image editing model.",
                  "zh_Hans": "使用 GPUStack 的图像编辑模型编辑图片。"
                },
                "llm": "This tool is used to edit image."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "gpustack",
                "label": {
                  "en_US": "Image Edit",
                  "zh_Hans": "图片编辑"
                },
                "name": "image_edit"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The image to be edited.",
                    "zh_Hans": "要编辑的图片。"
                  },
                  "label": {
                    "en_US": "Image",
                    "zh_Hans": "图片"
                  },
                  "llm_description": "You should not input this parameter. just input the image_id.",
                  "max": null,
                  "min": null,
                  "name": "image",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "file"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The text prompt used to edit the image.",
                    "zh_Hans": "用于编辑图片的文字提示词"
                  },
                  "label": {
                    "en_US": "prompt",
                    "zh_Hans": "提示词"
                  },
                  "llm_description": "this prompt text will be used to edit image.",
                  "max": null,
                  "min": null,
                  "name": "prompt",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "image model name that running in GPUStack.",
                    "zh_Hans": "在 GPUStack 上运行的图像模型名称。"
                  },
                  "label": {
                    "en_US": "Model",
                    "zh_Hans": "模型"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 4.5,
                  "form": "form",
                  "human_description": {
                    "en_US": "Classifier-free guidance scale, affecting the image's adherence to the prompt.",
                    "zh_Hans": "无分类器引导比例，影响图片的对 Prompt 的贴合度。"
                  },
                  "label": {
                    "en_US": "CFG Scale"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "cfg_scale",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 1,
                  "form": "form",
                  "human_description": {
                    "en_US": "Number of images to generate.",
                    "zh_Hans": "生成图片数量。"
                  },
                  "label": {
                    "en_US": "Number",
                    "zh_Hans": "数量"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "n",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "512x512",
                  "form": "form",
                  "human_description": {
                    "en_US": "The maximum size of the generated image is controlled by the deployment parameters of the model.",
                    "zh_Hans": "图片生成的最大尺寸受控于模型的部署参数。"
                  },
                  "label": {
                    "en_US": "Image Size",
                    "zh_Hans": "图片尺寸"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "size",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "euler",
                  "form": "form",
                  "human_description": {
                    "en_US": "The sample method for the image generation model.",
                    "zh_Hans": "图像生成模型的采样方法。"
                  },
                  "label": {
                    "en_US": "Sample Method",
                    "zh_Hans": "采样方法"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "sample_method",
                  "options": [
                    {
                      "label": {
                        "en_US": "euler_a"
                      },
                      "value": "euler_a"
                    },
                    {
                      "label": {
                        "en_US": "euler"
                      },
                      "value": "euler"
                    },
                    {
                      "label": {
                        "en_US": "heun"
                      },
                      "value": "heun"
                    },
                    {
                      "label": {
                        "en_US": "dpm2"
                      },
                      "value": "dpm2"
                    },
                    {
                      "label": {
                        "en_US": "dpm++2s_a"
                      },
                      "value": "dpm++2s_a"
                    },
                    {
                      "label": {
                        "en_US": "dpm++2m"
                      },
                      "value": "dpm++2m"
                    },
                    {
                      "label": {
                        "en_US": "dpm++2mv2"
                      },
                      "value": "dpm++2mv2"
                    },
                    {
                      "label": {
                        "en_US": "ipndm"
                      },
                      "value": "ipndm"
                    },
                    {
                      "label": {
                        "en_US": "ipndm_v"
                      },
                      "value": "ipndm_v"
                    },
                    {
                      "label": {
                        "en_US": "icm"
                      },
                      "value": "icm"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 20,
                  "form": "form",
                  "human_description": {
                    "en_US": "Number of sampling steps to generate the image.",
                    "zh_Hans": "生成图片所需的采样步数。"
                  },
                  "label": {
                    "en_US": "Sampling Steps",
                    "zh_Hans": "采样步数"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "sampling_steps",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 4.5,
                  "form": "form",
                  "human_description": {
                    "en_US": "Guidance scale, affecting the quality and diversity of the image.",
                    "zh_Hans": "引导比例，影响图片的质量和多样性"
                  },
                  "label": {
                    "en_US": "Guidance"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "guidance",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "discrete",
                  "form": "form",
                  "human_description": {
                    "en_US": "Schedule Method",
                    "zh_Hans": "调度方法"
                  },
                  "label": {
                    "en_US": "Schedule Method",
                    "zh_Hans": "调度方法"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "schedule_method",
                  "options": [
                    {
                      "label": {
                        "en_US": "discrete"
                      },
                      "value": "discrete"
                    },
                    {
                      "label": {
                        "en_US": "karras"
                      },
                      "value": "karras"
                    },
                    {
                      "label": {
                        "en_US": "exponential"
                      },
                      "value": "exponential"
                    },
                    {
                      "label": {
                        "en_US": "ays"
                      },
                      "value": "ays"
                    },
                    {
                      "label": {
                        "en_US": "gits"
                      },
                      "value": "gits"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 0.75,
                  "form": "form",
                  "human_description": {
                    "en_US": "The higher the value, the greater the modification to the original image.",
                    "zh_Hans": "值越高，它对原图的修改越大。"
                  },
                  "label": {
                    "en_US": "Strength",
                    "zh_Hans": "强度"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "strength",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Random seed for image generation. Using the same seed will produce similar results.",
                    "zh_Hans": "图像生成的随机种子。使用相同的种子会产生相似的结果。"
                  },
                  "label": {
                    "en_US": "Seed"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "seed",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 600,
                  "form": "form",
                  "human_description": {
                    "en_US": "The maximum time to wait for the image generation to complete(seconds).",
                    "zh_Hans": "等待图像生成完成的最大时间(秒)。"
                  },
                  "label": {
                    "en_US": "Timeout(seconds)",
                    "zh_Hans": "超时时间(秒)"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "timeout",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-05T04:49:09Z",
        "version_updated_at": "2025-03-05T04:49:09Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Send messages through SMS or Twilio Messaging Channels.",
          "pt_BR": "Send messages through SMS or Twilio Messaging Channels.",
          "zh_Hans": "通过SMS或Twilio消息通道发送消息。"
        },
        "category": "tool",
        "created_at": "2024-11-29T09:37:14Z",
        "endpoint": {},
        "icon": "langgenius/packages/twilio/_assets/icon.svg",
        "index_id": "langgenius___twilio",
        "install_count": 229,
        "introduction": "# Twilio WhatsApp Integration Tool\n\n## Overview\n\nTwilio is a cloud communications platform that enables businesses to build, scale, and manage communication channels such as SMS, voice, video, email, and chat through its powerful APIs. With Twilio, developers can integrate advanced communication functionalities into their applications and services, facilitating seamless interactions with customers across multiple channels.\n\n## Configure\n\nTo set up Twilio for WhatsApp integration, follow these steps:\n\n### 1. Prerequisites\nBefore starting:\n- Create a free [Twilio account](https://www.twilio.com/try-twilio).\n- Obtain your **Account SID** and **Auth Token** from the Twilio Console.\n- Have a WhatsApp-enabled phone for testing purposes.\n- Install Docker and Docker Compose if using local development.\n\n### 2. Configure Twilio Sandbox for WhatsApp\n1. Log in to your Twilio Console.\n2. Navigate to **Messaging > Senders > WhatsApp Senders**.\n3. Enable the sandbox by sending the provided code to the displayed phone number via WhatsApp.\n4. Note the sandbox phone number (e.g., `+14155238886`).\n\n### 3. Set Up Your Application\n1. Clone a sample repository or create your own backend using frameworks like FastAPI or Node.js.\n2. In your project directory, create an `.env` file with the following variables:\n```\nTWILIO_NUMBER=whatsapp:+14155238886\nTWILIO_ACCOUNT_SID=<Your Account SID>\nTWILIO_AUTH_TOKEN=<Your Auth Token>\n```\n3. Use Twilio's SDK or REST API to handle incoming and outgoing messages:\n  - Example (Node.js):\n    ```javascript\n    const twilio = require('twilio');\n    const client = twilio(process.env.TWILIO_ACCOUNT_SID, process.env.TWILIO_AUTH_TOKEN);\n\n    client.messages.create({\n    body: 'Hello from Twilio!',\n    from: 'whatsapp:+14155238886',\n    to: 'whatsapp:+<Recipient Phone Number>'\n    }).then(message => console.log(message.sid));\n    ```\n### 4. Webhook Configuration\n\n1. Deploy your application on a public server or use tools like Localtunnel for local development.\n2. In the Twilio Console:\n    - Go to Phone Numbers > Active Numbers > Messaging Settings.\n    - Add your webhook URL (e.g., `https://your-server-url/message`) under \"A Message Comes In.\"\n\n### 5. Test Your Integration\n\n1. Send a message to your sandbox number from WhatsApp.\n2. Observe the response from your application (e.g., auto-replies or chatbot interactions).",
        "label": {
          "en_US": "Twilio",
          "pt_BR": "Twilio",
          "zh_Hans": "Twilio"
        },
        "latest_package_identifier": "langgenius/twilio:0.0.2@55ea6168e539d8e441508732a679d6058997d406d710f2e24732051068a91404",
        "latest_version": "0.0.2",
        "model": {},
        "name": "twilio",
        "org": "langgenius",
        "plugin_id": "langgenius/twilio",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/twilio.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "social"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "Account SID",
                "pt_BR": "Account SID",
                "zh_Hans": "账户SID"
              },
              "name": "account_sid",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Twilio Account SID",
                "pt_BR": "Please input your Twilio Account SID",
                "zh_Hans": "请输入您的Twilio账户SID"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "Auth Token",
                "pt_BR": "Auth Token",
                "zh_Hans": "认证令牌"
              },
              "name": "auth_token",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Twilio Auth Token",
                "pt_BR": "Please input your Twilio Auth Token",
                "zh_Hans": "请输入您的Twilio认证令牌"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "From Number",
                "pt_BR": "De Número",
                "zh_Hans": "发信号码"
              },
              "name": "from_number",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Twilio phone number",
                "pt_BR": "Please input your Twilio phone number",
                "zh_Hans": "请输入您的Twilio电话号码"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            }
          ],
          "identity": {
            "author": "Yash Parmar",
            "description": {
              "en_US": "Send messages through SMS or Twilio Messaging Channels.",
              "pt_BR": "Send messages through SMS or Twilio Messaging Channels.",
              "zh_Hans": "通过SMS或Twilio消息通道发送消息。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Twilio",
              "pt_BR": "Twilio",
              "zh_Hans": "Twilio"
            },
            "name": "twilio",
            "tags": [
              "social"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Send SMS or Twilio Messaging Channels messages.",
                  "pt_BR": "Send SMS or Twilio Messaging Channels messages.",
                  "zh_Hans": "发送SMS或Twilio消息通道消息。"
                },
                "llm": "Send SMS or Twilio Messaging Channels messages. Supports different channels including WhatsApp."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Yash Parmar",
                "label": {
                  "en_US": "SendMessage",
                  "pt_BR": "SendMessage",
                  "zh_Hans": "发送消息"
                },
                "name": "send_message"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The content of the message to be sent.",
                    "pt_BR": "The content of the message to be sent.",
                    "zh_Hans": "要发送的消息内容。"
                  },
                  "label": {
                    "en_US": "Message",
                    "pt_BR": "Message",
                    "zh_Hans": "消息内容"
                  },
                  "llm_description": "The content of the message to be sent.",
                  "max": null,
                  "min": null,
                  "name": "message",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The recipient's phone number. Prefix with 'whatsapp:' for WhatsApp messages, e.g., \"whatsapp:+1234567890\".",
                    "pt_BR": "The recipient's phone number. Prefix with 'whatsapp:' for WhatsApp messages, e.g., \"whatsapp:+1234567890\".",
                    "zh_Hans": "收件人的电话号码。WhatsApp消息前缀为'whatsapp:'，例如，\"whatsapp:+1234567890\"。"
                  },
                  "label": {
                    "en_US": "To Number",
                    "pt_BR": "Para Número",
                    "zh_Hans": "收信号码"
                  },
                  "llm_description": "The recipient's phone number. Prefix with 'whatsapp:' for WhatsApp messages, e.g., \"whatsapp:+1234567890\".",
                  "max": null,
                  "min": null,
                  "name": "to_number",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:17:16Z",
        "version_updated_at": "2025-02-17T07:17:16Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Access questions and answers from the Stack Exchange and its sub-sites.",
          "zh_Hans": "从 Stack Exchange 和其子论坛获取问题和答案。"
        },
        "category": "tool",
        "created_at": "2024-12-04T06:44:32Z",
        "endpoint": {},
        "icon": "langgenius/packages/stackexchange/_assets/icon.svg",
        "index_id": "langgenius___stackexchange",
        "install_count": 226,
        "introduction": "# Stack Exchange API Tool\n\n## Overview\n\nThe Stack Exchange API provides programmatic access to the Stack Exchange network, enabling users to fetch answers and search questions across various communities, including Stack Overflow. \n\n## Configuration\n\n### 1. Get Stack Exchange tools from Plugin Marketplace\n\nThe Stack Exchange tools could be found at the Plugin Marketplace, please install it first.\n\n![](./_assets/stack_1.png)\n\n### 2. You can use the Stack Exchange tool in the following application types.\n\n![](./_assets/stack_2.png)\n\n#### Chatflow / Workflow applications\nBoth Chatflow and Workflow applications support adding a Stack Exchange tool node.\n\n#### Agent applications\nAdd both `fetchAnsByStackExQuesID` and `seahStackExQuestions` of the Stack Exchange tool in the Agent application, then enter the search keyword to call this tool.",
        "label": {
          "en_US": "Stack Exchange",
          "zh_Hans": "Stack Exchange"
        },
        "latest_package_identifier": "langgenius/stackexchange:0.0.2@847d42c4e673d2417dac67c3e064733e750b680f3d30d493c4999228bc61173c",
        "latest_version": "0.0.2",
        "model": {},
        "name": "stackexchange",
        "org": "langgenius",
        "plugin_id": "langgenius/stackexchange",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/stackexchange.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "utilities"
          },
          {
            "name": "search"
          }
        ],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "Richards Tu",
            "description": {
              "en_US": "Access questions and answers from the Stack Exchange and its sub-sites.",
              "zh_Hans": "从 Stack Exchange 和其子论坛获取问题和答案。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Stack Exchange",
              "zh_Hans": "Stack Exchange"
            },
            "name": "stackexchange",
            "tags": [
              "search",
              "utilities"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool for retrieving answers for a specific Stack Exchange question ID. Must be used with the searchStackExQuesID tool.",
                  "zh_Hans": "用于检索特定Stack Exchange问题ID的答案的工具。必须与searchStackExQuesID工具一起使用。"
                },
                "llm": "A tool for retrieving answers for Stack Exchange question ID."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Richards Tu",
                "label": {
                  "en_US": "Fetch Stack Exchange Answers",
                  "zh_Hans": "获取 Stack Exchange 答案"
                },
                "name": "fetchAnsByStackExQuesID"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the Stack Exchange question to fetch answers for.",
                    "zh_Hans": "要获取答案的Stack Exchange问题的ID。"
                  },
                  "label": {
                    "en_US": "Question ID",
                    "zh_Hans": "问题ID"
                  },
                  "llm_description": "The ID of the Stack Exchange question.",
                  "max": null,
                  "min": null,
                  "name": "id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The Stack Exchange site the question is from, e.g. stackoverflow, unix, etc.",
                    "zh_Hans": "问题所在的Stack Exchange站点，例如stackoverflow、unix等。"
                  },
                  "label": {
                    "en_US": "Stack Exchange site",
                    "zh_Hans": "Stack Exchange站点"
                  },
                  "llm_description": "Stack Exchange site identifier - 'stackoverflow', 'serverfault', 'superuser', 'askubuntu', 'unix', 'cs', 'softwareengineering', 'codegolf', 'codereview', 'cstheory', 'security', 'cryptography', 'reverseengineering', 'datascience', 'devops', 'ux', 'dba', 'gis', 'webmasters', 'arduino', 'raspberrypi', 'networkengineering', 'iot', 'tor', 'sqa', 'mathoverflow', 'math', 'mathematica', 'dsp', 'gamedev', 'robotics', 'genai', 'computergraphics'.",
                  "max": null,
                  "min": null,
                  "name": "site",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "!nNPvSNdWme",
                  "form": "form",
                  "human_description": {
                    "en_US": "This is required in order to actually get the body of the answer.",
                    "zh_Hans": "为了实际获取答案的正文是必需的。"
                  },
                  "label": {
                    "en_US": "Filter",
                    "zh_Hans": "过滤器"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "filter",
                  "options": [
                    {
                      "label": {
                        "en_US": "Must Select",
                        "zh_Hans": "必须选择"
                      },
                      "value": "!nNPvSNdWme"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "desc",
                  "form": "form",
                  "human_description": {
                    "en_US": "The direction to sort the answers - ascending or descending.",
                    "zh_Hans": "答案的排序方向 - 升序或降序。"
                  },
                  "label": {
                    "en_US": "Sort direction",
                    "zh_Hans": "排序方向"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "order",
                  "options": [
                    {
                      "label": {
                        "en_US": "Ascending",
                        "zh_Hans": "升序"
                      },
                      "value": "asc"
                    },
                    {
                      "label": {
                        "en_US": "Descending",
                        "zh_Hans": "降序"
                      },
                      "value": "desc"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The sort order for the answers - activity, votes, or creation date.",
                    "zh_Hans": "答案的排序顺序 - 活动、投票或创建日期。"
                  },
                  "label": {
                    "en_US": "Sort order",
                    "zh_Hans": "排序"
                  },
                  "llm_description": "activity, votes, or creation.",
                  "max": null,
                  "min": null,
                  "name": "sort",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 1,
                  "form": "form",
                  "human_description": {
                    "en_US": "The number of answers to return per page.",
                    "zh_Hans": "每页返回的答案数。"
                  },
                  "label": {
                    "en_US": "Results per page",
                    "zh_Hans": "每页结果数"
                  },
                  "llm_description": "",
                  "max": 5,
                  "min": 1,
                  "name": "pagesize",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 3,
                  "form": "form",
                  "human_description": {
                    "en_US": "The page number of answers to retrieve.",
                    "zh_Hans": "要检索的答案的页码。"
                  },
                  "label": {
                    "en_US": "Page number",
                    "zh_Hans": "页码"
                  },
                  "llm_description": "",
                  "max": 5,
                  "min": 1,
                  "name": "page",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A tool for searching questions on a Stack Exchange site.",
                  "zh_Hans": "在Stack Exchange站点上搜索问题的工具。"
                },
                "llm": "A tool for searching questions on Stack Exchange site."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Richards Tu",
                "label": {
                  "en_US": "Search Stack Exchange Questions",
                  "zh_Hans": "搜索Stack Exchange问题"
                },
                "name": "searchStackExQuestions"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The search query to use for finding questions.",
                    "zh_Hans": "用于查找问题的搜索查询。"
                  },
                  "label": {
                    "en_US": "Search query",
                    "zh_Hans": "搜索查询"
                  },
                  "llm_description": "The search query.",
                  "max": null,
                  "min": null,
                  "name": "intitle",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The sort order for the search results - relevance, activity, votes, or creation date.",
                    "zh_Hans": "搜索结果的排序顺序 - 相关性、活动、投票或创建日期。"
                  },
                  "label": {
                    "en_US": "Sort order",
                    "zh_Hans": "排序"
                  },
                  "llm_description": "The sort order - 'relevance', 'activity', 'votes', or 'creation'.",
                  "max": null,
                  "min": null,
                  "name": "sort",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "desc",
                  "form": "form",
                  "human_description": {
                    "en_US": "The direction to sort - ascending or descending.",
                    "zh_Hans": "排序方向 - 升序或降序。"
                  },
                  "label": {
                    "en_US": "Sort direction",
                    "zh_Hans": "排序方向"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "order",
                  "options": [
                    {
                      "label": {
                        "en_US": "Ascending",
                        "zh_Hans": "升序"
                      },
                      "value": "asc"
                    },
                    {
                      "label": {
                        "en_US": "Descending",
                        "zh_Hans": "降序"
                      },
                      "value": "desc"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The Stack Exchange site to search, e.g. stackoverflow, unix, etc.",
                    "zh_Hans": "要搜索的Stack Exchange站点，例如stackoverflow、unix等。"
                  },
                  "label": {
                    "en_US": "Stack Exchange site",
                    "zh_Hans": "Stack Exchange 站点"
                  },
                  "llm_description": "Stack Exchange site identifier - 'stackoverflow', 'serverfault', 'superuser', 'askubuntu', 'unix', 'cs', 'softwareengineering', 'codegolf', 'codereview', 'cstheory', 'security', 'cryptography', 'reverseengineering', 'datascience', 'devops', 'ux', 'dba', 'gis', 'webmasters', 'arduino', 'raspberrypi', 'networkengineering', 'iot', 'tor', 'sqa', 'mathoverflow', 'math', 'mathematica', 'dsp', 'gamedev', 'robotics', 'genai', 'computergraphics'.",
                  "max": null,
                  "min": null,
                  "name": "site",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "A semicolon-separated list of tags that questions must have.",
                    "zh_Hans": "问题必须具有的标签的分号分隔列表。"
                  },
                  "label": {
                    "en_US": "Include tags",
                    "zh_Hans": "包含标签"
                  },
                  "llm_description": "Semicolon-separated tags to include. Leave blank if not needed.",
                  "max": null,
                  "min": null,
                  "name": "tagged",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "A semicolon-separated list of tags to exclude from the search.",
                    "zh_Hans": "从搜索中排除的标签的分号分隔列表。"
                  },
                  "label": {
                    "en_US": "Exclude tags",
                    "zh_Hans": "排除标签"
                  },
                  "llm_description": "Semicolon-separated tags to exclude. Leave blank if not needed.",
                  "max": null,
                  "min": null,
                  "name": "nottagged",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "true",
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to limit to only questions that have an accepted answer.",
                    "zh_Hans": "是否限制为只有已接受答案的问题。"
                  },
                  "label": {
                    "en_US": "Has accepted answer",
                    "zh_Hans": "有已接受的答案"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "accepted",
                  "options": [
                    {
                      "label": {
                        "en_US": "Yes",
                        "zh_Hans": "是"
                      },
                      "value": "true"
                    },
                    {
                      "label": {
                        "en_US": "No",
                        "zh_Hans": "否"
                      },
                      "value": "false"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": 10,
                  "form": "form",
                  "human_description": {
                    "en_US": "The number of results to return per page.",
                    "zh_Hans": "每页返回的结果数。"
                  },
                  "label": {
                    "en_US": "Results per page",
                    "zh_Hans": "每页结果数"
                  },
                  "llm_description": "The number of results per page.",
                  "max": 50,
                  "min": 1,
                  "name": "pagesize",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:03:33Z",
        "version_updated_at": "2025-02-17T07:03:33Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Lepton AI",
          "zh_Hans": "Lepton AI"
        },
        "category": "model",
        "created_at": "2024-12-05T12:43:01Z",
        "endpoint": {},
        "icon": "langgenius/packages/leptonai/_assets/icon_s_en.png",
        "index_id": "langgenius___leptonai",
        "install_count": 226,
        "introduction": "",
        "label": {
          "en_US": "Lepton AI",
          "zh_Hans": "Lepton AI"
        },
        "latest_package_identifier": "langgenius/leptonai:0.0.2@5c7adc65938898b6f2160a45bb095d461ce79826c73d74dd6c2573e5fa60f578",
        "latest_version": "0.0.2",
        "model": {
          "background": "#F5F5F4",
          "configurate_methods": [
            "predefined-model"
          ],
          "description": {
            "en_US": "Lepton AI",
            "zh_Hans": "Lepton AI"
          },
          "help": {
            "title": {
              "en_US": "Get your API Key from Lepton AI",
              "zh_Hans": "从 Lepton AI 获取 API Key"
            },
            "url": {
              "en_US": "https://dashboard.lepton.ai"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.png"
          },
          "icon_small": {
            "en_US": "icon_s_en.png"
          },
          "label": {
            "en_US": "Lepton AI",
            "zh_Hans": "Lepton AI"
          },
          "model_credential_schema": null,
          "models": [
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "gemma-7b",
                "zh_Hans": "gemma-7b"
              },
              "model": "gemma-7b",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 1024,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "llama2-13b",
                "zh_Hans": "llama2-13b"
              },
              "model": "llama2-13b",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 1024,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "llama2-7b",
                "zh_Hans": "llama2-7b"
              },
              "model": "llama2-7b",
              "model_properties": {
                "context_size": 4096,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 1024,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "llama3-70b",
                "zh_Hans": "llama3-70b"
              },
              "model": "llama3-70b",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 1024,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "mistral-7b",
                "zh_Hans": "mistral-7b"
              },
              "model": "mistral-7b",
              "model_properties": {
                "context_size": 8192,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 1024,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": null
            },
            {
              "deprecated": false,
              "features": [
                "agent-thought"
              ],
              "fetch_from": "predefined-model",
              "label": {
                "en_US": "mixtral-8x7b",
                "zh_Hans": "mixtral-8x7b"
              },
              "model": "mixtral-8x7b",
              "model_properties": {
                "context_size": 32000,
                "mode": "chat"
              },
              "model_type": "llm",
              "parameter_rules": [
                {
                  "default": 0,
                  "help": {
                    "en_US": "Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
                    "ja_JP": "温度はランダム性を制御します。温度が低いほどランダムな完成が少なくなります。温度がゼロに近づくと、モデルは決定論的で繰り返しになります。温度が高いほどランダムな完成が多くなります。",
                    "pt_BR": "A temperatura controla a aleatoriedade. Menores temperaturas resultam em menos conclusões aleatórias. À medida que a temperatura se aproxima de zero, o modelo se tornará determinístico e repetitivo. Temperaturas mais altas resultam em mais conclusões aleatórias.",
                    "zh_Hans": "温度控制随机性。较低的温度会导致较少的随机完成。随着温度接近零，模型将变得确定性和重复性。较高的温度会导致更多的随机完成。"
                  },
                  "label": {
                    "en_US": "Temperature",
                    "ja_JP": "温度",
                    "pt_BR": "Temperatura",
                    "zh_Hans": "温度"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "temperature",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "temperature"
                },
                {
                  "default": 1,
                  "help": {
                    "en_US": "Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered.",
                    "ja_JP": "核サンプリングを通じて多様性を制御します：0.5は、すべての可能性加权オプションの半分を考慮します。",
                    "pt_BR": "Controla a diversidade via amostragem de núcleo: 0.5 significa que metade das opções com maior probabilidade são consideradas.",
                    "zh_Hans": "通过核心采样控制多样性：0.5表示考虑了一半的所有可能性加权选项。"
                  },
                  "label": {
                    "en_US": "Top P",
                    "ja_JP": "Top P",
                    "pt_BR": "Top P",
                    "zh_Hans": "Top P"
                  },
                  "max": 1,
                  "min": 0,
                  "name": "top_p",
                  "options": [],
                  "precision": 2,
                  "required": false,
                  "type": "float",
                  "use_template": "top_p"
                },
                {
                  "default": 1024,
                  "help": {
                    "en_US": "Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.",
                    "ja_JP": "生成結果の長さの上限を指定します。生成結果が切り捨てられた場合は、このパラメータを大きくすることができます。",
                    "pt_BR": "Especifica o limite superior para o comprimento dos resultados gerados. Se os resultados gerados forem truncados, você pode aumentar este parâmetro.",
                    "zh_Hans": "指定生成结果长度的上限。如果生成结果截断，可以调大该参数。"
                  },
                  "label": {
                    "en_US": "Max Tokens",
                    "ja_JP": "最大トークン",
                    "pt_BR": "Máximo de tokens",
                    "zh_Hans": "最大标记"
                  },
                  "max": 1024,
                  "min": 1,
                  "name": "max_tokens",
                  "options": [],
                  "precision": 0,
                  "required": false,
                  "type": "int",
                  "use_template": "max_tokens"
                }
              ],
              "pricing": null
            }
          ],
          "position": {
            "llm": [
              "gemma-7b",
              "mistral-7b",
              "mixtral-8x7b",
              "llama2-7b",
              "llama2-13b",
              "llama3-70b"
            ]
          },
          "provider": "leptonai",
          "provider_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              }
            ]
          },
          "supported_model_types": [
            "llm"
          ]
        },
        "name": "leptonai",
        "org": "langgenius",
        "plugin_id": "langgenius/leptonai",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/leptonai.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-02-17T06:54:04Z",
        "version_updated_at": "2025-02-17T06:54:04Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "A plugin for implementing access frequency limiting, external user authentication",
          "zh_Hans": "一个用于实现访问频率限制、外部用户认证的插件"
        },
        "category": "tool",
        "created_at": "2025-04-18T19:23:45Z",
        "endpoint": {},
        "icon": "axdlee/packages/safety_chat/_assets/icon.svg",
        "index_id": "axdlee___safety_chat",
        "install_count": 226,
        "introduction": "# Safety Chat Plugin\n\nA powerful Dify plugin that provides comprehensive safety and access control features for your applications.\n\n## Features\n\n### Rate Limiting\n- Multiple rate limiting algorithms:\n  - Token Bucket Algorithm\n  - Fixed Window Algorithm\n  - Sliding Window Algorithm\n  - Leaky Bucket Algorithm\n  - Multiple Buckets Limitation\n\n### Storage Options\n- Flexible storage backends:\n  - Redis Storage\n  - Dify Plugin Built-in Storage\n\n### User Authentication\n- Multi-dimensional user identification:\n  - User ID\n  - Operation Type\n  - Custom Parameters\n\n## Installation & Develop\n\n1. Clone the repository:\n```bash\ngit clone https://github.com/axdlee/safety-chat.git\n```\n\n2. Install dependencies:\n```bash\npip install -r requirements.txt\n```\n\n3. Configure your environment:\n```bash\ncp .env.example .env\n# Edit .env with your configuration\n```\n\n## Usage\n\n### Step 1: Install the Plugin\nInstall the Safety Chat plugin in your Dify application through the plugin marketplace.\n\n### Step 2: Configure the Plugin\nConfigure the plugin settings in your Dify application.\n\n![Plugin Configuration](_assets/config.png)\n\n### Step 3: Set Up Rate Limiting\nConfigure your preferred rate limiting algorithm and parameters.\n\n![Rate Limiting Setup](_assets/usage-01.png)\n\n![Rate Limiting Setup](_assets/usage-03.png)\n\n### Step 4: Configure External Authentication\n![External Authentication](_assets/usage-02.png)\n\n### Step 5: Define Access Rules\nCreate and manage your access control rules based on your requirements.\n\n## Configuration\n\nThe plugin can be configured through the following methods:\n- Environment variables\n- Configuration file\n- Dify plugin settings\n\n## License\n\nMIT License\n\n## Contributing\n\nContributions are welcome! Please feel free to submit a Pull Request.\n\n## Support\n\nFor support, please open an issue in the GitHub repository.\n\n\n\n",
        "label": {
          "en_US": "Safety Chat",
          "zh_Hans": "安全聊天"
        },
        "latest_package_identifier": "axdlee/safety_chat:0.0.1@30413ced4622dc68fe38990462d3dcc0fbd12a45d1af451c74d0f610de7ccb09",
        "latest_version": "0.0.1",
        "model": {},
        "name": "safety_chat",
        "org": "axdlee",
        "plugin_id": "axdlee/safety_chat",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/safety_chat.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "storage": {
              "enabled": true,
              "size": 10485760
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "utilities"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": "plugin_storage",
              "help": {
                "en_US": "Select the storage type for rate limiting data",
                "zh_Hans": "选择限流数据的存储类型"
              },
              "label": {
                "en_US": "Storage Type",
                "zh_Hans": "存储类型"
              },
              "name": "storage_type",
              "options": [
                {
                  "label": {
                    "en_US": "Redis",
                    "zh_Hans": "Redis"
                  },
                  "value": "redis"
                },
                {
                  "label": {
                    "en_US": "Plugin System Storage",
                    "zh_Hans": "插件系统持久化存储"
                  },
                  "value": "plugin_storage"
                }
              ],
              "placeholder": {
                "en_US": "Please select storage type",
                "zh_Hans": "请选择存储类型"
              },
              "required": true,
              "scope": null,
              "type": "select",
              "url": null
            },
            {
              "default": "localhost",
              "help": {
                "en_US": "Redis host address",
                "zh_Hans": "Redis主机地址"
              },
              "label": {
                "en_US": "Redis Host",
                "zh_Hans": "Redis主机"
              },
              "name": "redis_host",
              "options": null,
              "placeholder": {
                "en_US": "Please input Redis host",
                "zh_Hans": "请输入Redis主机地址"
              },
              "required": false,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": "6379",
              "help": {
                "en_US": "Redis port number",
                "zh_Hans": "Redis端口号"
              },
              "label": {
                "en_US": "Redis Port",
                "zh_Hans": "Redis端口"
              },
              "name": "redis_port",
              "options": null,
              "placeholder": {
                "en_US": "Please input Redis port",
                "zh_Hans": "请输入Redis端口"
              },
              "required": false,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "help": {
                "en_US": "Redis password (optional)",
                "zh_Hans": "Redis密码（可选）"
              },
              "label": {
                "en_US": "Redis Password",
                "zh_Hans": "Redis密码"
              },
              "name": "redis_password",
              "options": null,
              "placeholder": {
                "en_US": "Please input Redis password",
                "zh_Hans": "请输入Redis密码"
              },
              "required": false,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": "0",
              "help": {
                "en_US": "Redis database number",
                "zh_Hans": "Redis数据库编号"
              },
              "label": {
                "en_US": "Redis Database",
                "zh_Hans": "Redis数据库"
              },
              "name": "redis_db",
              "options": null,
              "placeholder": {
                "en_US": "Please input Redis database number",
                "zh_Hans": "请输入Redis数据库编号"
              },
              "required": false,
              "scope": null,
              "type": "text-input",
              "url": null
            }
          ],
          "identity": {
            "author": "axdlee",
            "description": {
              "en_US": "A plugin for implementing access frequency limiting, external user authentication, and sensitive content review",
              "zh_Hans": "一个用于实现访问频率限制、外部用户认证的插件"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Safety Chat",
              "zh_Hans": "安全聊天"
            },
            "name": "safety_chat",
            "tags": [
              "utilities"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Check if the current request is allowed based on rate limiting rules",
                  "zh_Hans": "根据速率限制规则检查当前请求是否允许"
                },
                "llm": "Check if the current request is allowed based on configured rate limiting rules and algorithms"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "axdlee",
                "label": {
                  "en_US": "Rate Limiter Check",
                  "zh_Hans": "频率限制检查"
                },
                "name": "rate_limiter_check"
              },
              "output_schema": {
                "$schema": "http://json-schema.org/draft-07/schema#",
                "additionalProperties": false,
                "properties": {
                  "allowed": {
                    "description": "Whether the request is allowed, \"true\" or \"false\"",
                    "title": "Allowed",
                    "type": "string"
                  },
                  "remaining": {
                    "description": "Number of remaining requests",
                    "minimum": 0,
                    "title": "Remaining Requests",
                    "type": "integer"
                  },
                  "reset_time": {
                    "description": "Time until the next reset in seconds",
                    "minimum": 0,
                    "title": "Reset Time",
                    "type": "integer"
                  }
                },
                "required": [
                  "allowed",
                  "remaining",
                  "reset_time"
                ],
                "type": "object"
              },
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Please provide the user ID for rate limit checking",
                    "zh_Hans": "请提供需要进行频率限制检查的用户ID"
                  },
                  "label": {
                    "en_US": "User ID",
                    "zh_Hans": "用户ID"
                  },
                  "llm_description": "The user identifier to check rate limit against",
                  "max": null,
                  "min": null,
                  "name": "user_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Select the type of action to check rate limit for",
                    "zh_Hans": "选择需要进行频率限制检查的操作类型, 例如聊天或函数调用, 可以自定义"
                  },
                  "label": {
                    "en_US": "Action Type",
                    "zh_Hans": "操作类型"
                  },
                  "llm_description": "The type of action to check rate limit for",
                  "max": null,
                  "min": null,
                  "name": "action_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "Chat",
                        "zh_Hans": "聊天"
                      },
                      "value": "chat"
                    },
                    {
                      "label": {
                        "en_US": "Function Call",
                        "zh_Hans": "函数调用"
                      },
                      "value": "function"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "token_bucket",
                  "form": "form",
                  "human_description": {
                    "en_US": "Select the rate limiting algorithm to use, token bucket (token_bucket, token generation rate per second), fixed window (fixed_window, maximum number of requests allowed within the specified time window), sliding window (sliding_window, continuous moving time window), leaky bucket (leaky_bucket, request processing rate per second)",
                    "zh_Hans": "选择要使用的限流算法, 令牌桶算法(token_bucket, 每秒生成令牌数)、固定窗口算法(fixed_window, 指定时间窗口内允许的最大请求数)、滑动窗口算法(sliding_window, 连续移动的时间窗口)、漏桶算法(leaky_bucket, 每秒处理请求数)"
                  },
                  "label": {
                    "en_US": "Algorithm Type",
                    "zh_Hans": "算法类型"
                  },
                  "llm_description": "The type of rate limiting algorithm to use",
                  "max": null,
                  "min": null,
                  "name": "algorithm_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "Token Bucket",
                        "zh_Hans": "令牌桶"
                      },
                      "value": "token_bucket"
                    },
                    {
                      "label": {
                        "en_US": "Fixed Window",
                        "zh_Hans": "固定窗口"
                      },
                      "value": "fixed_window"
                    },
                    {
                      "label": {
                        "en_US": "Sliding Window",
                        "zh_Hans": "滑动窗口"
                      },
                      "value": "sliding_window"
                    },
                    {
                      "label": {
                        "en_US": "Leaky Bucket",
                        "zh_Hans": "漏桶"
                      },
                      "value": "leaky_bucket"
                    },
                    {
                      "label": {
                        "en_US": "Multiple Buckets",
                        "zh_Hans": "混合窗口"
                      },
                      "value": "multiple_buckets"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 10,
                  "form": "form",
                  "human_description": {
                    "en_US": "For token bucket - how many tokens are generated per second; For leaky bucket - how many requests can be processed per second; For multiple buckets - how many requests can be processed per second",
                    "zh_Hans": "令牌桶算法 - 每秒生成多少令牌; 漏桶算法 - 每秒可以处理多少请求; 混合算法 - 每秒可以处理多少请求"
                  },
                  "label": {
                    "en_US": "Rate",
                    "zh_Hans": "速率"
                  },
                  "llm_description": "Rate parameter with different meanings for token bucket (token generation rate) and leaky bucket (request processing rate) and multiple buckets (request processing rate)",
                  "max": null,
                  "min": null,
                  "name": "rate",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 100,
                  "form": "form",
                  "human_description": {
                    "en_US": "For token bucket - maximum number of tokens that can be accumulated; For leaky bucket - maximum number of requests that can be queued; For multiple buckets - maximum requests in queue and maximum tokens the bucket can hold",
                    "zh_Hans": "令牌桶算法 - 可以累积的最大令牌数; 漏桶算法 - 可以排队的最大请求数; 混合算法 - 桶可以存储的最大令牌数及队列中可以等待的最大请求数"
                  },
                  "label": {
                    "en_US": "Capacity",
                    "zh_Hans": "容量"
                  },
                  "llm_description": "Capacity parameter with different meanings for token bucket (max tokens) and leaky bucket (max queued requests) and multiple buckets (max queued requests and max tokens)",
                  "max": null,
                  "min": null,
                  "name": "capacity",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 100,
                  "form": "form",
                  "human_description": {
                    "en_US": "For fixed/sliding/multiple buckets window - maximum number of requests allowed within the specified time window",
                    "zh_Hans": "固定/滑动/混合窗口算法 - 指定时间窗口内允许的最大请求数"
                  },
                  "label": {
                    "en_US": "Max Requests",
                    "zh_Hans": "最大请求数"
                  },
                  "llm_description": "Maximum requests allowed in the window for fixed and sliding window algorithms and multiple buckets (maximum requests in queue)",
                  "max": null,
                  "min": null,
                  "name": "max_requests",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 60,
                  "form": "form",
                  "human_description": {
                    "en_US": "For fixed window - discrete time intervals (e.g. per minute); For sliding/multiple buckets window - continuous moving time window",
                    "zh_Hans": "固定窗口 - 离散的时间区间(如每分钟); 滑动/混合窗口 - 连续移动的时间窗口"
                  },
                  "label": {
                    "en_US": "Window Size",
                    "zh_Hans": "窗口大小"
                  },
                  "llm_description": "Window size with different behaviors for fixed window (discrete) and sliding/multiple buckets window (continuous) algorithms",
                  "max": null,
                  "min": null,
                  "name": "window_size",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Check if the current user is authenticated by external authentication service",
                  "zh_Hans": "检查当前用户是否通过外部认证服务认证"
                },
                "llm": "Check if the current user is authenticated by external authentication service based on configured authentication rules"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "axdlee",
                "label": {
                  "en_US": "External Auth Check",
                  "zh_Hans": "外部认证检查"
                },
                "name": "external_auth_check"
              },
              "output_schema": {
                "$schema": "http://json-schema.org/draft-07/schema#",
                "additionalProperties": false,
                "properties": {
                  "authenticated": {
                    "description": "Whether the user is authenticated, \"true\" or \"false\"",
                    "title": "Authenticated",
                    "type": "string"
                  },
                  "user_info": {
                    "description": "Extracted user information from the response",
                    "title": "User Info",
                    "type": "string"
                  }
                },
                "required": [
                  "authenticated",
                  "user_info"
                ],
                "type": "object"
              },
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Please provide the URL of the external authentication service",
                    "zh_Hans": "请提供外部认证服务的URL"
                  },
                  "label": {
                    "en_US": "Authentication URL",
                    "zh_Hans": "认证URL"
                  },
                  "llm_description": "The URL of the external authentication service",
                  "max": null,
                  "min": null,
                  "name": "auth_url",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "{}",
                  "form": "llm",
                  "human_description": {
                    "en_US": "Header parameters in JSON format, e.g. {\"Authorization\": \"Bearer token\", \"X-API-Key\": \"key\"}",
                    "zh_Hans": "请求头参数的JSON格式,例如 {\"Authorization\": \"Bearer token\", \"X-API-Key\": \"key\"}"
                  },
                  "label": {
                    "en_US": "Header Parameters",
                    "zh_Hans": "请求头参数"
                  },
                  "llm_description": "Header parameters in JSON format",
                  "max": null,
                  "min": null,
                  "name": "header_params",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "{}",
                  "form": "llm",
                  "human_description": {
                    "en_US": "Query parameters in JSON format, e.g. {\"api_key\": \"key\", \"token\": \"value\"}",
                    "zh_Hans": "查询参数的JSON格式,例如 {\"api_key\": \"key\", \"token\": \"value\"}"
                  },
                  "label": {
                    "en_US": "Query Parameters",
                    "zh_Hans": "查询参数"
                  },
                  "llm_description": "Query parameters in JSON format",
                  "max": null,
                  "min": null,
                  "name": "query_params",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "{}",
                  "form": "llm",
                  "human_description": {
                    "en_US": "Body parameters in JSON format, e.g. {\"auth_key\": \"value\", \"token\": \"value\"}",
                    "zh_Hans": "请提供JSON格式的请求体参数,例如 {\"auth_key\": \"value\", \"token\": \"value\"}"
                  },
                  "label": {
                    "en_US": "Body Parameters",
                    "zh_Hans": "请求体参数"
                  },
                  "llm_description": "Body parameters in JSON format",
                  "max": null,
                  "min": null,
                  "name": "body_params",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Select the HTTP method to use for the authentication request",
                    "zh_Hans": "选择认证请求使用的HTTP方法"
                  },
                  "label": {
                    "en_US": "Request Method",
                    "zh_Hans": "请求方法"
                  },
                  "llm_description": "The HTTP method to use for the authentication request",
                  "max": null,
                  "min": null,
                  "name": "request_method",
                  "options": [
                    {
                      "label": {
                        "en_US": "GET",
                        "zh_Hans": "GET"
                      },
                      "value": "GET"
                    },
                    {
                      "label": {
                        "en_US": "POST",
                        "zh_Hans": "POST"
                      },
                      "value": "POST"
                    },
                    {
                      "label": {
                        "en_US": "PUT",
                        "zh_Hans": "PUT"
                      },
                      "value": "PUT"
                    },
                    {
                      "label": {
                        "en_US": "DELETE",
                        "zh_Hans": "DELETE"
                      },
                      "value": "DELETE"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Select the type of response to expect",
                    "zh_Hans": "选择期望的响应类型"
                  },
                  "label": {
                    "en_US": "Response Type",
                    "zh_Hans": "响应类型"
                  },
                  "llm_description": "The type of response to expect",
                  "max": null,
                  "min": null,
                  "name": "response_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "JSON",
                        "zh_Hans": "JSON"
                      },
                      "value": "json"
                    },
                    {
                      "label": {
                        "en_US": "Text",
                        "zh_Hans": "文本"
                      },
                      "value": "text"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Select how to check for authentication success",
                    "zh_Hans": "选择如何检查认证是否成功"
                  },
                  "label": {
                    "en_US": "Success Check Method",
                    "zh_Hans": "成功检查方式"
                  },
                  "llm_description": "How to check for authentication success",
                  "max": null,
                  "min": null,
                  "name": "success_check",
                  "options": [
                    {
                      "label": {
                        "en_US": "JSON Path",
                        "zh_Hans": "JSON路径"
                      },
                      "value": "json_path"
                    },
                    {
                      "label": {
                        "en_US": "Regular Expression",
                        "zh_Hans": "正则表达式"
                      },
                      "value": "regex"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Please provide the JSON path or regex pattern to check for success, for json_path, please provide the JSON path, for regex, please provide the regex pattern",
                    "zh_Hans": "请提供用于检查成功的JSON路径或正则表达式, 对json_path, 请提供JSON路径, 对regex, 请提供正则表达式"
                  },
                  "label": {
                    "en_US": "Success Pattern",
                    "zh_Hans": "成功模式"
                  },
                  "llm_description": "JSON path or regex pattern to check for success",
                  "max": null,
                  "min": null,
                  "name": "success_pattern",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Please provide the value to match for success",
                    "zh_Hans": "请提供用于匹配成功的值"
                  },
                  "label": {
                    "en_US": "Success Value",
                    "zh_Hans": "成功值"
                  },
                  "llm_description": "Value to match for success",
                  "max": null,
                  "min": null,
                  "name": "success_value",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Select how to extract user information",
                    "zh_Hans": "选择如何提取用户信息"
                  },
                  "label": {
                    "en_US": "User Info Extract Method",
                    "zh_Hans": "用户信息提取方式"
                  },
                  "llm_description": "How to extract user information",
                  "max": null,
                  "min": null,
                  "name": "user_info_extract",
                  "options": [
                    {
                      "label": {
                        "en_US": "JSON Path",
                        "zh_Hans": "JSON路径"
                      },
                      "value": "json_path"
                    },
                    {
                      "label": {
                        "en_US": "Regular Expression",
                        "zh_Hans": "正则表达式"
                      },
                      "value": "regex"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Please provide the JSON path or regex pattern to extract user information",
                    "zh_Hans": "请提供用于提取用户信息的JSON路径或正则表达式"
                  },
                  "label": {
                    "en_US": "User Info Pattern",
                    "zh_Hans": "用户信息模式"
                  },
                  "llm_description": "JSON path or regex pattern to extract user information",
                  "max": null,
                  "min": null,
                  "name": "user_info_pattern",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-18T19:24:00Z",
        "version_updated_at": "2025-04-18T19:24:00Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "163 SMTP Mail Sender",
          "ja_JP": "163 SMTPメール送信者エラー",
          "pt_BR": "envio de email 163SMTP",
          "zh_Hans": "163SMTP邮件发送"
        },
        "category": "tool",
        "created_at": "2025-04-13T17:11:49Z",
        "endpoint": {},
        "icon": "wjdsg/packages/163-smtp-send-mail/_assets/icon.svg",
        "index_id": "wjdsg___163-smtp-send-mail",
        "install_count": 225,
        "introduction": "## send-mail\r\n\r\n**Author:** wjdsg\r\n**Version:** 0.0.1\r\n**Type:** tool\r\n\r\n### Description\r\n\r\nBy default, the email service of smtp.163.com is used without any data processing. Multiple email recipients can be used, separated by commas in English\r\n\r\n![image-20250401155552539](https://github.com/user-attachments/assets/eab521d2-bfbc-4be7-8cab-883a5a19fc63)\r\n\r\n\r\n\r\n\r\nHow to activate SMTP service and obtain authorization code：\r\n\r\n![image-20250401160201899](https://github.com/user-attachments/assets/299b5c88-ad5f-4168-95fb-3caa22184518)\r\n\r\n\r\n",
        "label": {
          "en_US": "163 SMTP Mail Sender",
          "ja_JP": "163 SMTPメール送信者エラー",
          "pt_BR": "envio de email 163SMTP",
          "zh_Hans": "163SMTP邮件发送"
        },
        "latest_package_identifier": "wjdsg/163-smtp-send-mail:0.0.1@2d82d59b1bc83d80fcfd414dee8771295ab84a30704322fa53752703e5862e61",
        "latest_version": "0.0.1",
        "model": {},
        "name": "163-smtp-send-mail",
        "org": "wjdsg",
        "plugin_id": "wjdsg/163-smtp-send-mail",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/send-mail.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "wjdsg",
            "description": {
              "en_US": "163 SMTP Mail Sender",
              "pt_BR": "envio de email 163SMTP",
              "zh_Hans": "163SMTP邮件发送"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "163 SMTP Mail Sender",
              "pt_BR": "envio de email 163SMTP",
              "zh_Hans": "163SMTP邮件发送"
            },
            "name": "163-smtp-send-mail",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "163 e-mails para enviar um e-mail",
                  "pt_BR": "envio de email 163SMTP",
                  "zh_Hans": "163SMTP邮件发送"
                },
                "llm": "163 e-mails para enviar um e-mail"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "wjdsg",
                "label": {
                  "en_US": "163 e-mails para enviar um e-mail",
                  "pt_BR": "envio de email 163SMTP",
                  "zh_Hans": "163SMTP邮件发送"
                },
                "name": "163-smtp-send-mail"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Email username",
                    "pt_BR": "Email username",
                    "zh_Hans": "邮箱用户名"
                  },
                  "label": {
                    "en_US": "Email username",
                    "pt_BR": "Email username",
                    "zh_Hans": "邮箱用户名"
                  },
                  "llm_description": "Email username",
                  "max": null,
                  "min": null,
                  "name": "username_send",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "AUTHORIZE CODE",
                    "pt_BR": "CODE DE AUTORIZAÇÃO",
                    "zh_Hans": "授权码"
                  },
                  "label": {
                    "en_US": "AUTHORIZE CODE",
                    "pt_BR": "CODE DE AUTORIZAÇÃO",
                    "zh_Hans": "授权码"
                  },
                  "llm_description": "AUTHORIZE CODE",
                  "max": null,
                  "min": null,
                  "name": "authorization_code",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Recipient mailbox, multiple mailboxes separated by commas",
                    "pt_BR": "Recipiente de correio electrónico, endereços de correio electrónico múltiplos separados por vírgulas",
                    "zh_Hans": "收件人邮箱，多个邮箱逗号隔开"
                  },
                  "label": {
                    "en_US": "Recipient mailbox, multiple mailboxes separated by commas",
                    "pt_BR": "Recipiente de correio electrónico, endereços de correio electrónico múltiplos separados por vírgulas",
                    "zh_Hans": "收件人邮箱，多个邮箱逗号隔开"
                  },
                  "llm_description": "Recipient mailbox, multiple mailboxes separated by commas",
                  "max": null,
                  "min": null,
                  "name": "username_recv",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "subject",
                    "pt_BR": "tema",
                    "zh_Hans": "主题"
                  },
                  "label": {
                    "en_US": "subject",
                    "pt_BR": "tema",
                    "zh_Hans": "主题"
                  },
                  "llm_description": "subject",
                  "max": null,
                  "min": null,
                  "name": "subject",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "content",
                    "pt_BR": "conteúdo",
                    "zh_Hans": "内容"
                  },
                  "label": {
                    "en_US": "content",
                    "pt_BR": "conteúdo",
                    "zh_Hans": "内容"
                  },
                  "llm_description": "内容",
                  "max": null,
                  "min": null,
                  "name": "content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-13T17:11:56Z",
        "version_updated_at": "2025-04-13T17:11:56Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "return start date and end date mentioned in the time related words just like last week,last month,in \"%Y-%m-%d\" pattern",
          "ja_JP": "return start date and end date mentioned in the time related words just like last week,last month,in \"%Y-%m-%d\" pattern",
          "pt_BR": "return start date and end date mentioned in the time related words just like last week,last month,in \"%Y-%m-%d\" pattern",
          "zh_Hans": "返回有关时间的自然语言短语中涉及的开始和结束时间，例如上周，上个月。以\"%Y-%m-%d\"格式返回"
        },
        "category": "tool",
        "created_at": "2025-04-18T20:40:22Z",
        "endpoint": {},
        "icon": "dendy/packages/nlp_time_trans/_assets/ddicon.png",
        "index_id": "dendy___nlp_time_trans",
        "install_count": 225,
        "introduction": "## nlp_time_trans\n\n**Author:** dendy\n**Version:** 0.0.1\n**Type:** tool\n\n# 📅 Time Phrase Parser Plugin for Dify\n\nThis plugin is designed for the [Dify](https://dify.ai/) platform to process **natural language time-related phrases or keywords**. It uses a large language model (LLM) to parse the input and return the corresponding **start date** and **end date** in the `%Y-%m-%d` format.\n\n---\n\n## ✨ Features\n\n- ⏱ Parse natural language time expressions, such as:\n  - \"next Monday\"\n  - \"last quarter\"\n  - \"Q3 2023\"\n- 🌐 Supports **custom time zones** via the `tz` parameter (e.g., `UTC-8`, `UTC+5`)\n- 📆 Returns standardized start and end dates, e.g., `2023-07-01` to `2023-09-30`\n- 🤖 Optional selection of the LLM model to use\n- 🧠 Understands both English and Chinese time phrases\n\n---\n\n## 🛠 How to Use\n\n1. Install this plugin inside your Dify application.\n2. In the plugin settings, choose the LLM model you want to use (e.g., GPT-4).\n3. Parse natural language time expressions\n\n\n---\n\n## ⚠️ Important Notes\n\n- ✅ The `query` input **must be a time-related phrase or keyword only**, not a full sentence.\n  - ✔️ Valid: `next Friday`, `2024 Q1`, `Christmas`\n  - ❌ Invalid: `I want to go next Friday`, `What does 2024 Q1 mean?`\n- 🌍 The `tz` (timezone) field is **optional** but recommended for accurate date ranges across time zones.\n- ❌ This plugin does **not** extract date expressions from complex or full sentences.\n\n---\n\n## 📸 Plugin Screenshot\n\n\n![Plugin Screenshot](./_assets/screenshot1.png)\n![Plugin Screenshot](./_assets/screenshot2.png)\n\n---\n\n## 💡 Example Use Cases\n\n- Smart calendar assistants\n- Time range selectors for dashboards\n- AI-powered scheduling tools\n- Context-aware date parsing in chatbots\n- Applications with global users needing time zone awareness\n\n---\n\n## 📬 Contact\n\nFor questions or feedback, feel free to reach out to the plugin developer or leave a comment in the Dify plugin marketplace.\n\n---\n",
        "label": {
          "en_US": "nlp_time_trans",
          "ja_JP": "nlp_time_trans",
          "pt_BR": "nlp_time_trans",
          "zh_Hans": "nlp_time_trans"
        },
        "latest_package_identifier": "dendy/nlp_time_trans:0.0.1@6058fa531f677becda03d4bb98eb49765bff23219f502e50fe426afab0b27068",
        "latest_version": "0.0.1",
        "model": {},
        "name": "nlp_time_trans",
        "org": "dendy",
        "plugin_id": "dendy/nlp_time_trans",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/nlp_time_trans.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "endpoint": {
              "enabled": true
            },
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "dendy",
            "description": {
              "en_US": "return start date and end date mentioned in the time related words just like last week,last month,in \"%Y-%m-%d\" pattern",
              "pt_BR": "return start date and end date mentioned in the time related words just like last week,last month,in \"%Y-%m-%d\" pattern",
              "zh_Hans": "返回有关时间的自然语言短语中涉及的开始和结束时间，例如上周，上个月。以\"%Y-%m-%d\"格式返回"
            },
            "icon": "ddicon.png",
            "label": {
              "en_US": "nlp_time_trans",
              "pt_BR": "nlp_time_trans",
              "zh_Hans": "nlp_time_trans"
            },
            "name": "nlp_time_trans",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "return start date and end date mentioned in the time related words just like last week,last month,in \"%Y-%m-%d\" pattern",
                  "pt_BR": "return start date and end date mentioned in the time related words just like last week,last month,in \"%Y-%m-%d\" pattern",
                  "zh_Hans": "返回有关时间的自然语言短语中涉及的开始和结束时间，例如上周，上个月。以\"%Y-%m-%d\"格式返回"
                },
                "llm": "return start date and end date mentioned in the time related words just like last week,last month,in \"%Y-%m-%d\" pattern"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "dendy",
                "label": {
                  "en_US": "nlp_time_trans",
                  "pt_BR": "nlp_time_trans",
                  "zh_Hans": "nlp_time_trans"
                },
                "name": "nlp_time_trans"
              },
              "output_schema": {
                "properties": {
                  "end_date": {
                    "type": "string"
                  },
                  "start_date": {
                    "type": "string"
                  }
                },
                "type": "object"
              },
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "time related words or phrases",
                    "pt_BR": "time related words or phrases",
                    "zh_Hans": "时间相关的短语输入"
                  },
                  "label": {
                    "en_US": "Query string",
                    "pt_BR": "Query string",
                    "zh_Hans": "查询语句"
                  },
                  "llm_description": "return start date and end date mentioned in the time related words just like last week,last month,in \"%Y-%m-%d\" pattern",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "set environ TimeZone,eg. UTC-8",
                    "pt_BR": "set environ TimeZone,eg. UTC-8",
                    "zh_Hans": "设置系统时区，例如：UTC-8"
                  },
                  "label": {
                    "en_US": "TimeZone",
                    "pt_BR": "TimeZone",
                    "zh_Hans": "时区"
                  },
                  "llm_description": "environ TimeZone",
                  "max": null,
                  "min": null,
                  "name": "TZ",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Model",
                    "pt_BR": "Model",
                    "zh_Hans": "使用的模型"
                  },
                  "label": {
                    "en_US": "Model",
                    "pt_BR": "Model",
                    "zh_Hans": "使用的模型"
                  },
                  "llm_description": "which Model to invoke",
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": "llm",
                  "template": null,
                  "type": "model-selector"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-18T20:40:39Z",
        "version_updated_at": "2025-04-18T20:40:39Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Translate text using Google",
          "zh_Hans": "使用 Google 进行翻译"
        },
        "category": "tool",
        "created_at": "2025-02-26T09:42:58Z",
        "endpoint": {},
        "icon": "svcvit/packages/google_translate/_assets/icon.svg",
        "index_id": "svcvit___google_translate",
        "install_count": 224,
        "introduction": "# Google Translate Plugin\n\n## google_translate\n\n**Author:** svcvit\n**Version:** 0.0.1\n**Type:** plugin\n\n### Description\n\nA powerful translation tool plugin based on Google Translate service, supporting text translation between multiple languages.\n\n### Features\n\n- Automatic source language detection\n- Support for multiple target languages\n- No API key required\n- Fast response and accurate translation\n\n### Usage Guide\n\n#### Parameters\n\n1. **content** (Required)\n   - Type: string\n   - Description: Text content to be translated\n   - Example: `\"Hello World\"`\n\n2. **dest** (Required)\n   - Type: string\n   - Description: Target language code\n   - Supported language codes:\n     - ar: Arabic\n     - bg: Bulgarian\n     - ca: Catalan\n     - zh-cn: Chinese (Simplified)\n     - zh-tw: Chinese (Traditional)\n     - cs: Czech\n     - da: Danish\n     - nl: Dutch\n     - en: English\n     ...\n\n#### Response Format\n\nThe plugin returns the translated text content. In case of any errors during translation, it will return the corresponding error message.\n\n#### Example Usage\n\n```python\n# Example parameters\nparameters = {\n    \"content\": \"Hello, world\",\n    \"dest\": \"zh-cn\"\n}\n\n# Expected output\n\"你好，世界\"",
        "label": {
          "en_US": "Google Translate",
          "zh_Hans": "谷歌翻译"
        },
        "latest_package_identifier": "svcvit/google_translate:0.0.1@e13744b1e8397bfc7f9e4271ac4b842fdd1056016475d95cdbb151efadbfdd71",
        "latest_version": "0.0.1",
        "model": {},
        "name": "google_translate",
        "org": "svcvit",
        "plugin_id": "svcvit/google_translate",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/google_translate.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "svcvit",
            "description": {
              "en_US": "Translate text using Google",
              "zh_Hans": "使用 Google 进行翻译"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Google Translate",
              "zh_Hans": "谷歌翻译"
            },
            "name": "google_translate",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool for Google Translate",
                  "zh_Hans": "Google 翻译"
                },
                "llm": "A tool for Google Translate"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "svcvit",
                "label": {
                  "en_US": "Translate",
                  "zh_Hans": "翻译"
                },
                "name": "translate"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Text content",
                    "zh_Hans": "需要翻译的文本内容"
                  },
                  "label": {
                    "en_US": "Text content",
                    "zh_Hans": "文本内容"
                  },
                  "llm_description": "Text content",
                  "max": null,
                  "min": null,
                  "name": "content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "en",
                  "form": "form",
                  "human_description": {
                    "en_US": "The destination language you want to translate.",
                    "zh_Hans": "你想翻译的目标语言"
                  },
                  "label": {
                    "en_US": "destination language",
                    "zh_Hans": "目标语言"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "dest",
                  "options": [
                    {
                      "label": {
                        "en_US": "Arabic",
                        "zh_Hans": "阿拉伯语"
                      },
                      "value": "ar"
                    },
                    {
                      "label": {
                        "en_US": "Bulgarian",
                        "zh_Hans": "保加利亚语"
                      },
                      "value": "bg"
                    },
                    {
                      "label": {
                        "en_US": "Catalan",
                        "zh_Hans": "加泰罗尼亚语"
                      },
                      "value": "ca"
                    },
                    {
                      "label": {
                        "en_US": "Chinese (Simplified)",
                        "zh_Hans": "中文（简体）"
                      },
                      "value": "zh-cn"
                    },
                    {
                      "label": {
                        "en_US": "Chinese (Traditional)",
                        "zh_Hans": "中文（繁体）"
                      },
                      "value": "zh-tw"
                    },
                    {
                      "label": {
                        "en_US": "Czech",
                        "zh_Hans": "捷克语"
                      },
                      "value": "cs"
                    },
                    {
                      "label": {
                        "en_US": "Danish",
                        "zh_Hans": "丹麦语"
                      },
                      "value": "da"
                    },
                    {
                      "label": {
                        "en_US": "Dutch",
                        "zh_Hans": "荷兰语"
                      },
                      "value": "nl"
                    },
                    {
                      "label": {
                        "en_US": "English",
                        "zh_Hans": "英语"
                      },
                      "value": "en"
                    },
                    {
                      "label": {
                        "en_US": "Estonian",
                        "zh_Hans": "爱沙尼亚语"
                      },
                      "value": "et"
                    },
                    {
                      "label": {
                        "en_US": "Finnish",
                        "zh_Hans": "芬兰语"
                      },
                      "value": "fi"
                    },
                    {
                      "label": {
                        "en_US": "French",
                        "zh_Hans": "法语"
                      },
                      "value": "fr"
                    },
                    {
                      "label": {
                        "en_US": "German",
                        "zh_Hans": "德语"
                      },
                      "value": "de"
                    },
                    {
                      "label": {
                        "en_US": "Greek",
                        "zh_Hans": "希腊语"
                      },
                      "value": "el"
                    },
                    {
                      "label": {
                        "en_US": "Hebrew",
                        "zh_Hans": "希伯来语"
                      },
                      "value": "iw"
                    },
                    {
                      "label": {
                        "en_US": "Hindi",
                        "zh_Hans": "印地语"
                      },
                      "value": "hi"
                    },
                    {
                      "label": {
                        "en_US": "Hungarian",
                        "zh_Hans": "匈牙利语"
                      },
                      "value": "hu"
                    },
                    {
                      "label": {
                        "en_US": "Indonesian",
                        "zh_Hans": "印尼语"
                      },
                      "value": "id"
                    },
                    {
                      "label": {
                        "en_US": "Italian",
                        "zh_Hans": "意大利语"
                      },
                      "value": "it"
                    },
                    {
                      "label": {
                        "en_US": "Japanese",
                        "zh_Hans": "日语"
                      },
                      "value": "ja"
                    },
                    {
                      "label": {
                        "en_US": "Kannada",
                        "zh_Hans": "卡纳达语"
                      },
                      "value": "kn"
                    },
                    {
                      "label": {
                        "en_US": "Korean",
                        "zh_Hans": "韩语"
                      },
                      "value": "ko"
                    },
                    {
                      "label": {
                        "en_US": "Latvian",
                        "zh_Hans": "拉脱维亚语"
                      },
                      "value": "lv"
                    },
                    {
                      "label": {
                        "en_US": "Lithuanian",
                        "zh_Hans": "立陶宛语"
                      },
                      "value": "lt"
                    },
                    {
                      "label": {
                        "en_US": "Malay",
                        "zh_Hans": "马来语"
                      },
                      "value": "my"
                    },
                    {
                      "label": {
                        "en_US": "Malayalam",
                        "zh_Hans": "马拉雅拉姆语"
                      },
                      "value": "ml"
                    },
                    {
                      "label": {
                        "en_US": "Marathi",
                        "zh_Hans": "马拉地语"
                      },
                      "value": "mr"
                    },
                    {
                      "label": {
                        "en_US": "Norwegian",
                        "zh_Hans": "挪威语"
                      },
                      "value": "no"
                    },
                    {
                      "label": {
                        "en_US": "Polish",
                        "zh_Hans": "波兰语"
                      },
                      "value": "pl"
                    },
                    {
                      "label": {
                        "en_US": "Portuguese (Brazil)",
                        "zh_Hans": "葡萄牙语（巴西）"
                      },
                      "value": "pt-br"
                    },
                    {
                      "label": {
                        "en_US": "Portuguese (Portugal)",
                        "zh_Hans": "葡萄牙语（葡萄牙）"
                      },
                      "value": "pt-pt"
                    },
                    {
                      "label": {
                        "en_US": "Punjabi",
                        "zh_Hans": "旁遮普语"
                      },
                      "value": "pa"
                    },
                    {
                      "label": {
                        "en_US": "Romanian",
                        "zh_Hans": "罗马尼亚语"
                      },
                      "value": "ro"
                    },
                    {
                      "label": {
                        "en_US": "Russian",
                        "zh_Hans": "俄语"
                      },
                      "value": "ru"
                    },
                    {
                      "label": {
                        "en_US": "Serbian",
                        "zh_Hans": "塞尔维亚语"
                      },
                      "value": "sr"
                    },
                    {
                      "label": {
                        "en_US": "Slovak",
                        "zh_Hans": "斯洛伐克语"
                      },
                      "value": "sk"
                    },
                    {
                      "label": {
                        "en_US": "Slovenian",
                        "zh_Hans": "斯洛文尼亚语"
                      },
                      "value": "sl"
                    },
                    {
                      "label": {
                        "en_US": "Spanish",
                        "zh_Hans": "西班牙语"
                      },
                      "value": "es"
                    },
                    {
                      "label": {
                        "en_US": "Swedish",
                        "zh_Hans": "瑞典语"
                      },
                      "value": "sv"
                    },
                    {
                      "label": {
                        "en_US": "Tamil",
                        "zh_Hans": "泰米尔语"
                      },
                      "value": "ta"
                    },
                    {
                      "label": {
                        "en_US": "Telugu",
                        "zh_Hans": "泰卢固语"
                      },
                      "value": "te"
                    },
                    {
                      "label": {
                        "en_US": "Thai",
                        "zh_Hans": "泰语"
                      },
                      "value": "th"
                    },
                    {
                      "label": {
                        "en_US": "Turkish",
                        "zh_Hans": "土耳其语"
                      },
                      "value": "tr"
                    },
                    {
                      "label": {
                        "en_US": "Ukrainian",
                        "zh_Hans": "乌克兰语"
                      },
                      "value": "uk"
                    },
                    {
                      "label": {
                        "en_US": "Vietnamese",
                        "zh_Hans": "越南语"
                      },
                      "value": "vi"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-26T09:43:03Z",
        "version_updated_at": "2025-02-26T09:43:03Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Cooking on tabular data, smooth Q&A",
          "ja_JP": "Cooking on tabular data, smooth Q&A",
          "pt_BR": "Cooking on tabular data, smooth Q&A",
          "zh_Hans": "Cooking on tabular data, smooth Q&A"
        },
        "category": "tool",
        "created_at": "2025-03-31T11:59:54Z",
        "endpoint": {},
        "icon": "qin2dim/packages/table_cooking/_assets/icon.png",
        "index_id": "qin2dim___table_cooking",
        "install_count": 213,
        "introduction": "## table_cooking\r\n\r\n```yaml\r\nAuthor: QIN2DIM\r\nVersion: 0.0.3\r\nType: tool\r\n```\r\n\r\n### Demo Chatflow\r\n\r\n- [dsl_demo.yml](_assets/table-cooking.yml)\r\n  \r\nhttps://github.com/user-attachments/assets/60d46a37-48b0-471b-a60c-146391ca87be\r\n\r\n\r\n![image-20250321154044819](_assets/image-20250321154044819.png)\r\n\r\n\r\n### Package\r\n\r\n```bash\r\n./dify-plugin-windows-amd64.exe plugin package ../table-cooking/ -o difypkg/table-cooking-0.0.3.difypkg\r\n```\r\n",
        "label": {
          "en_US": "table_cooking",
          "ja_JP": "table_cooking",
          "pt_BR": "table_cooking",
          "zh_Hans": "table_cooking"
        },
        "latest_package_identifier": "qin2dim/table_cooking:0.0.3@bec312615d67f2851adba03f3acc87d31b30f3d60fb2dffe5182c36a9bbe96a7",
        "latest_version": "0.0.3",
        "model": {},
        "name": "table_cooking",
        "org": "qin2dim",
        "plugin_id": "qin2dim/table_cooking",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/table_cooking.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "endpoint": {
              "enabled": true
            },
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "storage": {
              "enabled": true,
              "size": 2048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "qin2dim",
            "description": {
              "en_US": "Cooking on tabular data, smooth Q&amp;A",
              "pt_BR": "Cooking on tabular data, smooth Q&amp;A",
              "zh_Hans": "Cooking on tabular data, smooth Q&amp;A"
            },
            "icon": "icon.png",
            "label": {
              "en_US": "Table Cooking",
              "pt_BR": "Table Cooking",
              "zh_Hans": "表格数据分析"
            },
            "name": "table_cooking",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Cook your tabular data to perfection! Smooth Q&A with just a few clicks",
                  "ja_JP": "表データを完璧に調理！クリック数回で滑らかなQ&A体験",
                  "pt_BR": "Cozinhe seus dados tabulares à perfeição! Q&A suave com apenas alguns cliques",
                  "zh_Hans": "完美烹饪您的表格数据！轻松点击，流畅问答"
                },
                "llm": "Cook your tabular data to perfection! Smooth Q&A with just a few clicks"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "qin2dim",
                "label": {
                  "en_US": "Table Data Analysis",
                  "ja_JP": "表データ分析",
                  "pt_BR": "Análise de Dados Tabulares",
                  "zh_Hans": "表格数据分析"
                },
                "name": "table_cooking"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The information you want to get from the table data",
                    "ja_JP": "表データから取得したい情報",
                    "pt_BR": "A informação que você deseja obter dos dados da tabela",
                    "zh_Hans": "想从表格数据中获取的信息"
                  },
                  "label": {
                    "en_US": "Natural language query",
                    "ja_JP": "自然言語クエリ",
                    "pt_BR": "Consulta em linguagem natural",
                    "zh_Hans": "查询语句"
                  },
                  "llm_description": "Cooking on tabular data, smooth Q&amp;A",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Document form for Q&A (.csv/.xlsx/.xls)",
                    "ja_JP": "Q&A用のドキュメントフォーム（.csv/.xlsx/.xls）",
                    "pt_BR": "Formulário de documento para Q&A (.csv/.xlsx/.xls)",
                    "zh_Hans": "提供数据支持的的表格文件（.csv/.xlsx/.xls）"
                  },
                  "label": {
                    "en_US": "Table file",
                    "ja_JP": "表ファイル",
                    "pt_BR": "Arquivo de tabela",
                    "zh_Hans": "表格文件"
                  },
                  "llm_description": "Document form for Q&amp;A",
                  "max": null,
                  "min": null,
                  "name": "table",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "file"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Model",
                    "ja_JP": "使用するモデル",
                    "pt_BR": "Modelo a ser usado",
                    "zh_Hans": "使用的模型 test"
                  },
                  "label": {
                    "en_US": "Model",
                    "ja_JP": "モデル",
                    "pt_BR": "Modelo",
                    "zh_Hans": "使用的模型"
                  },
                  "llm_description": "which Model to invoke",
                  "max": null,
                  "min": null,
                  "name": "chef",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": "llm",
                  "template": null,
                  "type": "model-selector"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-03T08:52:10Z",
        "version_updated_at": "2025-04-03T08:52:10Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "pdfminer_six extracts the text from a page directly from the sourcecode of the PDF.",
          "ja_JP": "pdfminer_six extracts the text from a page directly from the sourcecode of the PDF.",
          "pt_BR": "pdfminer_six extracts the text from a page directly from the sourcecode of the PDF.",
          "zh_Hans": "pdfminer_six extracts the text from a page directly from the sourcecode of the PDF."
        },
        "category": "tool",
        "created_at": "2025-04-10T14:05:13Z",
        "endpoint": {},
        "icon": "tavan/packages/pdfminer_six/_assets/icon.jpg",
        "index_id": "tavan___pdfminer_six",
        "install_count": 213,
        "introduction": "## pdfminer_six\n\n**Author:** tavan\n**Version:** 0.0.1\n**Type:** Tool plugin\n\n### Introduction\n\npdfminer.six is ​​a powerful PDF document parsing tool that focuses on text extraction and analysis. It can directly extract text content from PDF source code and supports obtaining the precise location, font and color information of the text.\n\n### Main features\n\n* Support PDF-1.7 specification\n* Support CJK languages ​​and vertical writing scripts\n* Support multiple font types (Type1, TrueType, Type3, CID)\n* Support RC4 and AES encryption\n* Support form extraction\n* Support directory extraction\n* Support automatic layout analysis\n\n### Supported output formats\n\nThe plugin supports the following output formats:\n\n* `markdown` - Markdown format (MIME: text/markdown)\n\n* `html` - HTML format (MIME: text/html)\n\n* `text` - Plain text format (MIME: text/plain)\n\n* `tag` - Tagged text format (MIME: text/plain)\n\n* `xml` - XML ​​format (MIME: application/xml)\n\n### Usage Guide\n\n1. **Upload file**\n- Support single PDF file upload\n- The file must be in valid PDF format\n\n2. **Select output format**\n- Specify `output_type` in the parameter\n- Optional values: markdown, html, text, tag, xml\n- Text format is used by default\n\n![Tool Configuration](./_assets/config.png)\n\n3. **Processing results**\nThe plugin will return responses in three formats:\n- Text message: Processing status description\n- Blob message: Converted content\n- JSON message: Processing result metadata\n\n### Future Enhancements\n- Support `hocr`\n\n### License\n\nThis project is licensed under the [MIT License](./LICENSE).\n\n---",
        "label": {
          "en_US": "pdfminer_six",
          "ja_JP": "pdfminer_six",
          "pt_BR": "pdfminer_six",
          "zh_Hans": "pdfminer_six"
        },
        "latest_package_identifier": "tavan/pdfminer_six:0.0.1@b475ca5fac0895841a249902cca512edc1e1491f84549511ea2ed9f99c3a4db4",
        "latest_version": "0.0.1",
        "model": {},
        "name": "pdfminer_six",
        "org": "tavan",
        "plugin_id": "tavan/pdfminer_six",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/pdfminer_six.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "tavan",
            "description": {
              "en_US": "pdfminer_six extracts the text from a page directly from the sourcecode of the PDF.",
              "pt_BR": "pdfminer_six extracts the text from a page directly from the sourcecode of the PDF.",
              "zh_Hans": "pdfminer_six extracts the text from a page directly from the sourcecode of the PDF."
            },
            "icon": "icon.jpg",
            "label": {
              "en_US": "pdfminer_six",
              "pt_BR": "pdfminer_six",
              "zh_Hans": "pdfminer_six"
            },
            "name": "pdfminer_six",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "pdfminer_six extracts the text from a page directly from the sourcecode of the PDF.",
                  "pt_BR": "pdfminer_six extracts the text from a page directly from the sourcecode of the PDF.",
                  "zh_Hans": "pdfminer_six extracts the text from a page directly from the sourcecode of the PDF."
                },
                "llm": "pdfminer_six extracts the text from a page directly from the sourcecode of the PDF."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "tavan",
                "label": {
                  "en_US": "pdfminer_six",
                  "pt_BR": "pdfminer_six",
                  "zh_Hans": "pdfminer_six"
                },
                "name": "pdfminer_six"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Upload a file to extract text from the PDF.",
                    "zh_Hans": "上传要提取文本的PDF文件。"
                  },
                  "label": {
                    "en_US": "File",
                    "zh_Hans": "文件"
                  },
                  "llm_description": "File to extract text from the PDF.",
                  "max": null,
                  "min": null,
                  "name": "files",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "file"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Select the output format.",
                    "zh_Hans": "选择输出格式。"
                  },
                  "label": {
                    "en_US": "Output Format",
                    "zh_Hans": "输出格式"
                  },
                  "llm_description": "Output format to extract text from the PDF.",
                  "max": null,
                  "min": null,
                  "name": "output_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "text",
                        "zh_Hans": "text"
                      },
                      "value": "text"
                    },
                    {
                      "label": {
                        "en_US": "xml",
                        "zh_Hans": "xml"
                      },
                      "value": "xml"
                    },
                    {
                      "label": {
                        "en_US": "html",
                        "zh_Hans": "html"
                      },
                      "value": "html"
                    },
                    {
                      "label": {
                        "en_US": "tag",
                        "zh_Hans": "tag"
                      },
                      "value": "tag"
                    },
                    {
                      "label": {
                        "en_US": "markdown",
                        "zh_Hans": "markdown"
                      },
                      "value": "markdown"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-10T14:05:20Z",
        "version_updated_at": "2025-04-10T14:05:20Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Used to push messages to the Bark application",
          "zh_Hans": "用于推送消息到Bark应用程序中。"
        },
        "category": "tool",
        "created_at": "2025-03-11T17:57:16Z",
        "endpoint": {},
        "icon": "itning/packages/bark-notify/_assets/icon.png",
        "index_id": "itning___bark-notify",
        "install_count": 208,
        "introduction": "# Bark Notify\n\nThe Bark Notify tool plugin can push your notifications to your device.\n\nRepository: https://github.com/itning/dify-bark-notify-plugin\n\n![Hits](https://hitcount.itning.com?u=itning&r=dify-bark-notify-plugin)\n\n## Overview\n\n![Overview](./_assets/a.png)\n\n## Usage\n\nInstall the plugin\n\nAfter installation, you need to fill in the KEY and server address.\n\n![Setup](./_assets/b.png)\n\nTo be used as a tool.\n\n![Use1](./_assets/c.png)\n\n![Use2](./_assets/d.png)\n",
        "label": {
          "en_US": "BarkNotify",
          "zh_Hans": "Bark通知"
        },
        "latest_package_identifier": "itning/bark-notify:0.0.4@ba4b6b5ba15b06148a25d0fed76378171118c7e0c6d8af2bbe906e2542abf16d",
        "latest_version": "0.0.4",
        "model": {},
        "name": "bark-notify",
        "org": "itning",
        "plugin_id": "itning/bark-notify",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/bark-notify.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Bark KEY",
                "zh_Hans": "Bark KEY"
              },
              "name": "bark-key",
              "options": null,
              "placeholder": null,
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://github.com/itning/dify-bark-notify-plugin/blob/master/HOW_TO_GET_KEY.md"
            },
            {
              "default": "https://api.day.app",
              "help": null,
              "label": {
                "en_US": "Server URL",
                "zh_Hans": "服务器地址"
              },
              "name": "server-url",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Bark server URL",
                "zh_Hans": "请输入你的Bark服务器地址"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Custom query parameters carried when initiating a request",
                "zh_Hans": "发起请求时携带的自定义查询参数"
              },
              "name": "default-query-params",
              "options": null,
              "placeholder": {
                "en_US": "?sound=minuet&call=1&isArchive=1",
                "zh_Hans": "?sound=minuet&call=1&isArchive=1"
              },
              "required": false,
              "scope": null,
              "type": "text-input",
              "url": null
            }
          ],
          "identity": {
            "author": "itning",
            "description": {
              "en_US": "Used to push messages to the Bark application",
              "zh_Hans": "用于推送消息到Bark应用程序中"
            },
            "icon": "icon.png",
            "label": {
              "en_US": "BarkNotify",
              "zh_Hans": "Bark通知"
            },
            "name": "bark-notify",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Used to push messages to the Bark application",
                  "zh_Hans": "用于推送消息到Bark应用程序中"
                },
                "llm": "Used to push messages to the Bark application"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "itning",
                "label": {
                  "en_US": "SendNotify",
                  "zh_Hans": "发送通知"
                },
                "name": "send_to_bark"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Title that needs to be pushed to the Bark application",
                    "zh_Hans": "需要推送到Bark应用程序的标题"
                  },
                  "label": {
                    "en_US": "Push title",
                    "zh_Hans": "推送标题"
                  },
                  "llm_description": "Title that needs to be pushed to the Bark application (not required)",
                  "max": null,
                  "min": null,
                  "name": "title",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Content that needs to be pushed to the Bark application",
                    "zh_Hans": "需要推送到Bark应用程序的内容"
                  },
                  "label": {
                    "en_US": "Push content",
                    "zh_Hans": "推送内容"
                  },
                  "llm_description": "Content that needs to be pushed to the Bark application (required)",
                  "max": null,
                  "min": null,
                  "name": "content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The configuration here will override the query parameters configured during authorization by KEY. For example, if the configuration during authorization is ?sound=minuet&call=1&isArchive=1, and the configuration here is ?sound=alarm, then the final effective configuration will be ?sound=alarm&call=1&isArchive=1",
                    "zh_Hans": "此处配置会按KEY覆盖授权时配置的查询参数，例如授权时配置为?sound=minuet&call=1&isArchive=1，此处配置?sound=alarm，则最终生效为?sound=alarm&call=1&isArchive=1"
                  },
                  "label": {
                    "en_US": "Custom Query Param",
                    "zh_Hans": "自定义查询参数"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "query_params",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The configuration here will override the KEY set during authorization",
                    "zh_Hans": "此处配置会覆盖授权时配置的KEY"
                  },
                  "label": {
                    "en_US": "Bark KEY",
                    "zh_Hans": "Bark KEY"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "bark_key",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The configuration here will override the Server URL set during authorization",
                    "zh_Hans": "此处配置会覆盖授权时配置的服务器地址"
                  },
                  "label": {
                    "en_US": "Server URL",
                    "zh_Hans": "服务器地址"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "server_url",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-15T12:23:35Z",
        "version_updated_at": "2025-04-15T12:23:35Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Lark Wiki, requires the following permissions: wiki:wiki:readonly.\n",
          "zh_Hans": "Lark 知识库，需要开通以下权限: wiki:wiki:readonly。\n"
        },
        "category": "tool",
        "created_at": "2025-02-26T10:38:03Z",
        "endpoint": {},
        "icon": "langgenius/packages/lark_wiki/_assets/icon.png",
        "index_id": "langgenius___lark_wiki",
        "install_count": 203,
        "introduction": "",
        "label": {
          "en_US": "Lark Wiki",
          "zh_Hans": "Lark 知识库"
        },
        "latest_package_identifier": "langgenius/lark_wiki:0.0.1@b8569c4e7a2b0bb289280eab00e83fee931c3fc5e66b780f0b87cb72a8cb8416",
        "latest_version": "0.0.1",
        "model": {},
        "name": "lark_wiki",
        "org": "langgenius",
        "plugin_id": "langgenius/lark_wiki",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/lark_wiki.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "social"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "APP ID"
              },
              "name": "app_id",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Lark app id",
                "zh_Hans": "请输入你的 Lark app id"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": "https://open.larksuite.com/app"
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "APP Secret"
              },
              "name": "app_secret",
              "options": null,
              "placeholder": {
                "en_US": "Please input your app secret",
                "zh_Hans": "请输入你的 Lark app secret"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            }
          ],
          "identity": {
            "author": "langgenius",
            "description": {
              "en_US": "Lark Wiki, requires the following permissions: wiki:wiki:readonly.\n",
              "zh_Hans": "Lark 知识库，需要开通以下权限: wiki:wiki:readonly。\n"
            },
            "icon": "icon.png",
            "label": {
              "en_US": "Lark Wiki",
              "zh_Hans": "Lark 知识库"
            },
            "name": "lark_wiki",
            "tags": [
              "social",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Get the list of child nodes in Wiki, make sure the app/bot is a member of the wiki space. See How to add an app as a wiki base administrator (member). https://open.larksuite.com/document/server-docs/docs/wiki-v2/wiki-qa\n",
                  "zh_Hans": "获取知识库全部子节点列表，请确保应用/机器人为知识空间成员。参阅如何将应用添加为知识库管理员（成员）。https://open.larksuite.com/document/server-docs/docs/wiki-v2/wiki-qa\n"
                },
                "llm": "A tool for getting all sub-nodes of a knowledge base.(获取知识空间子节点列表)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Get Wiki Nodes",
                  "zh_Hans": "获取知识空间子节点列表"
                },
                "name": "get_wiki_nodes"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the knowledge space. Supports space link URL, for example: https://lark-japan.jp.larksuite.com/wiki/settings/7431084851517718561\n",
                    "zh_Hans": "知识空间 ID，支持空间链接 URL，例如：https://lark-japan.jp.larksuite.com/wiki/settings/7431084851517718561"
                  },
                  "label": {
                    "en_US": "Space Id",
                    "zh_Hans": "知识空间 ID"
                  },
                  "llm_description": "知识空间 ID，支持空间链接 URL，例如：https://lark-japan.jp.larksuite.com/wiki/settings/7431084851517718561",
                  "max": null,
                  "min": null,
                  "name": "space_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 10,
                  "form": "form",
                  "human_description": {
                    "en_US": "The size of each page, with a maximum value of 50.",
                    "zh_Hans": "分页大小，最大值 50。"
                  },
                  "label": {
                    "en_US": "Page Size",
                    "zh_Hans": "分页大小"
                  },
                  "llm_description": "分页大小，最大值 50。",
                  "max": null,
                  "min": null,
                  "name": "page_size",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The pagination token. Leave empty for the first request to start from the beginning; if the paginated query result has more items, a new page_token will be returned, which can be used to get the next set of results.",
                    "zh_Hans": "分页标记，第一次请求不填，表示从头开始遍历；分页查询结果还有更多项时会同时返回新的 page_token，下次遍历可采用该 page_token 获取查询结果。"
                  },
                  "label": {
                    "en_US": "Page Token",
                    "zh_Hans": "分页标记"
                  },
                  "llm_description": "分页标记，第一次请求不填，表示从头开始遍历；分页查询结果还有更多项时会同时返回新的 page_token，下次遍历可采用该 page_token 获取查询结果。",
                  "max": null,
                  "min": null,
                  "name": "page_token",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The token of the parent node.",
                    "zh_Hans": "父节点 token"
                  },
                  "label": {
                    "en_US": "Parent Node Token",
                    "zh_Hans": "父节点 token"
                  },
                  "llm_description": "父节点 token",
                  "max": null,
                  "min": null,
                  "name": "parent_node_token",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-26T10:38:07Z",
        "version_updated_at": "2025-02-26T10:38:07Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Convert audio to text with OpenAI's Audio API, supporting transcription and translation across multiple languages with high accuracy.",
          "ja_JP": "Convert audio to text with OpenAI's Audio API, supporting transcription and translation across multiple languages with high accuracy.",
          "pt_BR": "Convert audio to text with OpenAI's Audio API, supporting transcription and translation across multiple languages with high accuracy.",
          "zh_Hans": "Convert audio to text with OpenAI's Audio API, supporting transcription and translation across multiple languages with high accuracy."
        },
        "category": "tool",
        "created_at": "2025-04-15T12:23:09Z",
        "endpoint": {},
        "icon": "lysonober/packages/openai_audio/_assets/icon.svg",
        "index_id": "lysonober___openai_audio",
        "install_count": 193,
        "introduction": "## OpenAI Audio STT\n\n**Author:** lysonober\n**Version:** 0.0.4\n**Type:** Tool\n\n### Description\n\nThe OpenAI Audio tool is a powerful speech-to-text conversion solution that leverages OpenAI's Audio API to transform audio content into accurate text transcriptions and translations. This tool supports multiple audio formats (mp3, mp4, mpeg, mpga, m4a, wav, webm) and can process files up to 25MB in size. It offers both transcription (keeping the original language) and translation (converting to English) capabilities across a wide range of languages.\n\nThe tool integrates three powerful models: GPT-4o Transcribe for high-quality transcription, GPT-4o Mini Transcribe for faster processing, and Whisper-1 for legacy support with additional formatting options. Advanced features include streaming output for real-time transcription with GPT-4o models, timestamp generation at segment or word level with Whisper-1, and multiple output formats including plain text, JSON, SRT, and VTT subtitles.\n\n### Use Cases\n\n1️⃣ Today, for **content creators and video producers**,\n2️⃣ when **working with hours of interview footage or multilingual content**,\n3️⃣ they are forced to **spend excessive time manually transcribing audio or hiring expensive transcription services**,\n4️⃣ therefore, the customer needs a way to **quickly and accurately convert speech to text while preserving timestamps and supporting multiple languages**.\n\n---\n\n1️⃣ Today, for **accessibility specialists and educational institutions**,\n2️⃣ when **creating accessible content for diverse audiences with hearing impairments**,\n3️⃣ they are forced to **navigate complex subtitle creation tools or outsource caption generation**,\n4️⃣ therefore, the customer needs a way to **efficiently generate accurate subtitles in various formats (SRT, VTT) with precise timestamps**.\n\n### Parameters\n\n| Parameter               | Type    | Required | Description                                                                                                                                                                                                                      |\n| ----------------------- | ------- | -------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| file                    | file    | Yes      | The audio file to transcribe. Supports mp3, mp4, mpeg, mpga, m4a, wav, and webm formats with a maximum size of 25MB.                                                                                                             |\n| transcription_type      | select  | No       | Determines whether to transcribe the audio in its original language (\"transcribe\") or translate it to English (\"translate\"). Note that translation is only available with the Whisper-1 model and will disable streaming output. |\n| model                   | select  | No       | The AI model to use for processing. Options include GPT-4o Transcribe (high quality), GPT-4o Mini Transcribe (faster), and Whisper-1 (legacy with more format options). Default is GPT-4o Transcribe.                            |\n| response_format         | select  | No       | The format of the transcript output. Options include text, JSON, verbose JSON (Whisper-1 only), SRT subtitles (Whisper-1 only), and VTT subtitles (Whisper-1 only). Default is text.                                             |\n| prompt                  | string  | No       | Optional guidance for the model's transcription. Useful for improving accuracy with uncommon words, acronyms, or specific terminology by providing context.                                                                      |\n| language                | string  | No       | ISO-639-1 language code (e.g., 'en', 'zh', 'ja') to help improve accuracy if the audio language is known. This helps the model focus on the specific language patterns.                                                          |\n| timestamp_granularities | select  | No       | Adds timestamps to the transcript at segment or word level. Only available with the Whisper-1 model and requires verbose_json response format. Options are none, segment, or word.                                               |\n| stream                  | boolean | No       | Enables streaming output where transcription results are delivered as they're generated. This feature is only available with GPT-4o Transcribe and GPT-4o Mini Transcribe models. Default is true.                               |\n| output_format           | select  | No       | Controls how the plugin formats its output in Dify. Options include Default (JSON + Text), JSON Only, or Text Only. This affects how the results are presented to the user in the interface.                                     |\n\n### Parameter Interactions: What Happens When You Change Settings\n\nThe OpenAI Audio tool has several settings that affect each other. Understanding these relationships will help you get the results you want:\n\n#### Automatic Setting Adjustments\n\n1. **When You Choose Translation Mode**\n\n   - **What happens:** If you select \"Translate to English\" as your transcription type, the tool will automatically switch to the Whisper-1 model, even if you selected a different model.\n2. **When You Choose Special Output Formats**\n\n   - **What happens:** If you select formats like \"Verbose JSON\", \"SRT Subtitles\", or \"VTT Subtitles\" but are using a GPT-4o model, the tool will automatically switch back to plain text format.\n   - **Why it's designed this way:** The newer GPT-4o models focus on speed and accuracy for basic transcription, while Whisper-1 offers more formatting options.\n3. **When You Request Timestamps**\n\n   - **What happens:** If you ask for word or segment timestamps but are using a GPT-4o model, the timestamp feature will be turned off.\n4. **When You Enable Streaming**\n\n   - **What happens:** If you turn on streaming (getting results in real-time) but are using the Whisper-1 model, streaming will be automatically disabled.\n5. **When You Enable Timestamps with Whisper-1**\n\n   - **What happens:** If you turn on timestamps and are using the Whisper-1 model, the output format will automatically switch to \"Verbose JSON\".\n   - **Why it's designed this way:** Timestamps contain extra information that doesn't fit in simple text formats, so the tool uses a format that can include all the details.\n\n#### Summary of Automatic Adjustments\n\n| If you set                                | And              | Then automatically                | Reason                                    |\n| ----------------------------------------- | ---------------- | --------------------------------- | ----------------------------------------- |\n| `transcription_type: translate`         | any model        | `model: whisper-1`              | Translation only works with Whisper-1     |\n| `response_format: verbose_json/srt/vtt` | not Whisper-1    | `response_format: text`         | Advanced formats only work with Whisper-1 |\n| `timestamp_granularities: segment/word` | not Whisper-1    | `timestamp_granularities: none` | Timestamps only work with Whisper-1       |\n| `timestamp_granularities: segment/word` | Whisper-1        | `response_format: verbose_json` | Timestamps require verbose JSON format    |\n| `stream: true`                          | not GPT-4o model | `stream: false`                 | Streaming only works with GPT-4o models   |\n\n### Technical Details\n\nThe OpenAI Audio tool communicates with OpenAI's Audio API endpoints:\n\n- Transcription: `https://api.openai.com/v1/audio/transcriptions`\n- Translation: `https://api.openai.com/v1/audio/translations`\n\nThe tool handles various file input methods, creates temporary files for processing, and manages the API communication including streaming responses. It automatically applies appropriate parameter validation and model compatibility checks to ensure optimal results.\n\n### Output Examples\n\n**Text Output:**\n\n```\nHello, this is a sample transcription of spoken audio content that demonstrates the accuracy of the OpenAI Audio tool.\n```\n\n**JSON Output (simplified):**\n\n```json\n{\n  \"result\": {\n    \"text\": \"Hello, this is a sample transcription of spoken audio content that demonstrates the accuracy of the OpenAI Audio tool.\"\n  }\n}\n```\n\n### Support\n\nIf you have any questions, please contact me at: lysonober@gmail.com\n\nFollow me on X (Twitter): https://x.com/lyson_ober\n\n### Privacy\n\nPlease refer to the [PRIVACY.md](./PRIVACY.md) file for information about how your data is handled when using this plugin. This plugin does not collect any data directly, but your audio is processed through OpenAI's services subject to their privacy policies.\n",
        "label": {
          "en_US": "openai_audio",
          "ja_JP": "openai_audio",
          "pt_BR": "openai_audio",
          "zh_Hans": "openai_audio"
        },
        "latest_package_identifier": "lysonober/openai_audio:0.0.4@1b9b171b35f13a185d843f2d73fab52d3aa0ed4b2df17a258a116a16e1e7bd38",
        "latest_version": "0.0.4",
        "model": {},
        "name": "openai_audio",
        "org": "lysonober",
        "plugin_id": "lysonober/openai_audio",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/openai_audio.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": true,
              "rerank": true,
              "speech2text": true,
              "text_embedding": true,
              "tts": true
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Your OpenAI API key. You can find it in your OpenAI account settings.",
                "ja_JP": "あなたのOpenAI APIキーです。OpenAIアカウント設定で確認できます。",
                "pt_BR": "Sua chave API da OpenAI. Você pode encontrá-la nas configurações da sua conta OpenAI.",
                "zh_Hans": "您的 OpenAI API 密钥。您可以在 OpenAI 账户设置中找到它。"
              },
              "label": {
                "en_US": "API Key",
                "ja_JP": "API キー",
                "pt_BR": "Chave API",
                "zh_Hans": "API 密钥"
              },
              "name": "api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your OpenAI API key",
                "ja_JP": "OpenAI API キーを入力してください",
                "pt_BR": "Por favor, insira sua chave API da OpenAI",
                "zh_Hans": "请输入您的 OpenAI API 密钥"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://platform.openai.com/api-keys"
            }
          ],
          "identity": {
            "author": "logicober",
            "description": {
              "en_US": "Convert audio to text with OpenAI's Audio API, supporting transcription and translation across multiple languages with high accuracy. Supports Whisper-1 model as well as GPT-4o Transcribe and GPT-4o Mini Transcribe models with streaming output capability.",
              "ja_JP": "OpenAIのAudio APIを使用して音声をテキストに変換し、複数言語での高精度な文字起こしと翻訳をサポートします。Whisper-1モデルに加え、ストリーミング出力機能を備えたGPT-4o TranscribeおよびGPT-4o Mini Transcribeモデルもサポートしています。",
              "pt_BR": "Converta áudio em texto com a API de Áudio da OpenAI, suportando transcrição e tradução em vários idiomas com alta precisão. Suporta o modelo Whisper-1, bem como os modelos GPT-4o Transcribe e GPT-4o Mini Transcribe com capacidade de saída em streaming.",
              "zh_Hans": "使用 OpenAI 的 Audio API 将音频转换为文本，支持多种语言的高精度转录和翻译。支持 Whisper-1 模型以及具有流式输出能力的 GPT-4o Transcribe 和 GPT-4o Mini Transcribe 模型。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "OpenAI Audio STT",
              "ja_JP": "OpenAI Audio STT",
              "pt_BR": "OpenAI Audio STT",
              "zh_Hans": "OpenAI Audio STT"
            },
            "name": "openai_audio_stt",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Transcribe or translate audio files to text using OpenAI's Audio API.",
                  "ja_JP": "OpenAIのAudio APIを使用して音声ファイルをテキストに文字起こしまたは翻訳します。",
                  "pt_BR": "Transcreva ou traduza arquivos de áudio para texto usando a API de Áudio da OpenAI.",
                  "zh_Hans": "使用 OpenAI 的 Audio API 将音频文件转录或翻译为文本。"
                },
                "llm": "Transcribe or translate audio files to text using OpenAI's Audio API with high accuracy across multiple languages."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "logicober",
                "label": {
                  "en_US": "Audio Transcription",
                  "ja_JP": "音声文字起こし",
                  "pt_BR": "Transcrição de Áudio",
                  "zh_Hans": "音频转录"
                },
                "name": "openai_audio_stt"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The audio file to transcribe. Supported formats include mp3, mp4, mpeg, mpga, m4a, wav, and webm. Max 25MB.",
                    "ja_JP": "文字起こしする音声ファイル。サポートされている形式はmp3、mp4、mpeg、mpga、m4a、wav、webmです。最大サイズは25MBです。",
                    "pt_BR": "O arquivo de áudio para transcrever. Formatos suportados incluem mp3, mp4, mpeg, mpga, m4a, wav e webm. Máximo 25MB.",
                    "zh_Hans": "要转录的音频文件。支持的格式包括 mp3、mp4、mpeg、mpga、m4a、wav 和 webm。最大 25MB。"
                  },
                  "label": {
                    "en_US": "Audio File",
                    "ja_JP": "音声ファイル",
                    "pt_BR": "Arquivo de Áudio",
                    "zh_Hans": "音频文件"
                  },
                  "llm_description": "The audio file to transcribe. Supported formats include mp3, mp4, mpeg, mpga, m4a, wav, and webm. Maximum file size is 25MB.",
                  "max": null,
                  "min": null,
                  "name": "file",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "file"
                },
                {
                  "auto_generate": null,
                  "default": "transcribe",
                  "form": "form",
                  "human_description": {
                    "en_US": "Choose whether to transcribe the audio in its original language or translate it to English. Note that 'Translate to English' only supports the whisper-1 model and will disable streaming output.",
                    "ja_JP": "音声を原語のまま文字起こしするか、英語に翻訳するかを選択します。「英語に翻訳」はwhisper-1モデルのみをサポートし、ストリーミング出力が無効になります。",
                    "pt_BR": "Escolha entre transcrever o áudio em seu idioma original ou traduzi-lo para inglês.",
                    "zh_Hans": "选择是以原始语言转录音频还是将其翻译成英语。请注意，\"翻译成英语\"选项仅支持 whisper-1 模型，并且会禁用流式输出。"
                  },
                  "label": {
                    "en_US": "Transcription Type",
                    "ja_JP": "文字起こしタイプ",
                    "pt_BR": "Tipo de Transcrição",
                    "zh_Hans": "转录类型"
                  },
                  "llm_description": "Choose whether to transcribe the audio in its original language or translate it to English. Note that translation only supports whisper-1 model.",
                  "max": null,
                  "min": null,
                  "name": "transcription_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "Transcribe (Keep Original Language)",
                        "ja_JP": "文字起こし（原語を維持）",
                        "pt_BR": "Transcrever (Manter Idioma Original)",
                        "zh_Hans": "转录（保持原始语言）"
                      },
                      "value": "transcribe"
                    },
                    {
                      "label": {
                        "en_US": "Translate to English",
                        "ja_JP": "英語に翻訳",
                        "pt_BR": "Traduzir para Inglês",
                        "zh_Hans": "翻译成英语"
                      },
                      "value": "translate"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "gpt-4o-transcribe",
                  "form": "form",
                  "human_description": {
                    "en_US": "Select the model to use. Note that translations only support whisper-1.",
                    "ja_JP": "使用するモデルを選択します。翻訳機能はwhisper-1モデルのみをサポートしていることに注意してください。",
                    "pt_BR": "Selecione o modelo a ser usado. Note que traduções só suportam whisper-1.",
                    "zh_Hans": "选择要使用的模型。请注意，翻译功能仅支持 whisper-1。"
                  },
                  "label": {
                    "en_US": "Model",
                    "ja_JP": "モデル",
                    "pt_BR": "Modelo",
                    "zh_Hans": "模型"
                  },
                  "llm_description": "Select the model to use for transcription or translation. GPT-4o models provide higher quality but translations only support whisper-1.",
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": [
                    {
                      "label": {
                        "en_US": "GPT-4o Transcribe (High Quality)",
                        "ja_JP": "GPT-4o Transcribe (高品質)",
                        "pt_BR": "GPT-4o Transcribe (Alta Qualidade)",
                        "zh_Hans": "GPT-4o Transcribe (高质量)"
                      },
                      "value": "gpt-4o-transcribe"
                    },
                    {
                      "label": {
                        "en_US": "GPT-4o Mini Transcribe (Faster)",
                        "ja_JP": "GPT-4o Mini Transcribe (高速)",
                        "pt_BR": "GPT-4o Mini Transcribe (Mais Rápido)",
                        "zh_Hans": "GPT-4o Mini Transcribe (更快)"
                      },
                      "value": "gpt-4o-mini-transcribe"
                    },
                    {
                      "label": {
                        "en_US": "Whisper-1 (Legacy, More Formats)",
                        "ja_JP": "Whisper-1 (レガシー、複数フォーマット対応)",
                        "pt_BR": "Whisper-1 (Legado, Mais Formatos)",
                        "zh_Hans": "Whisper-1 (旧版，更多格式)"
                      },
                      "value": "whisper-1"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "text",
                  "form": "form",
                  "human_description": {
                    "en_US": "The format of the transcript output. Note that some formats are only available with whisper-1.",
                    "ja_JP": "文字起こし出力のフォーマット。一部のフォーマットはWhisper-1モデルでのみ利用可能です。",
                    "pt_BR": "O formato da saída da transcrição. Note que alguns formatos só estão disponíveis com whisper-1.",
                    "zh_Hans": "转录输出的格式。请注意，某些格式仅适用于 whisper-1。"
                  },
                  "label": {
                    "en_US": "Response Format",
                    "ja_JP": "レスポンスフォーマット",
                    "pt_BR": "Formato de Resposta",
                    "zh_Hans": "响应格式"
                  },
                  "llm_description": "The format of the transcript output. verbose_json, srt, and vtt formats are only available with the whisper-1 model.",
                  "max": null,
                  "min": null,
                  "name": "response_format",
                  "options": [
                    {
                      "label": {
                        "en_US": "Text",
                        "ja_JP": "テキスト",
                        "pt_BR": "Texto",
                        "zh_Hans": "文本"
                      },
                      "value": "text"
                    },
                    {
                      "label": {
                        "en_US": "JSON",
                        "ja_JP": "JSON",
                        "pt_BR": "JSON",
                        "zh_Hans": "JSON"
                      },
                      "value": "json"
                    },
                    {
                      "label": {
                        "en_US": "Verbose JSON (Whisper-1 only)",
                        "ja_JP": "詳細JSON (Whisper-1のみ)",
                        "pt_BR": "JSON Detalhado (Apenas Whisper-1)",
                        "zh_Hans": "详细 JSON (仅 Whisper-1)"
                      },
                      "value": "verbose_json"
                    },
                    {
                      "label": {
                        "en_US": "SRT Subtitles (Whisper-1 only)",
                        "ja_JP": "SRT字幕 (Whisper-1のみ)",
                        "pt_BR": "Legendas SRT (Apenas Whisper-1)",
                        "zh_Hans": "SRT 字幕 (仅 Whisper-1)"
                      },
                      "value": "srt"
                    },
                    {
                      "label": {
                        "en_US": "VTT Subtitles (Whisper-1 only)",
                        "ja_JP": "VTT字幕 (Whisper-1のみ)",
                        "pt_BR": "Legendas VTT (Apenas Whisper-1)",
                        "zh_Hans": "VTT 字幕 (仅 Whisper-1)"
                      },
                      "value": "vtt"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional prompt to guide transcription. Can help with uncommon words, acronyms, or context.",
                    "pt_BR": "Prompt opcional para guiar a transcrição. Pode ajudar com palavras incomuns, siglas ou contexto.",
                    "zh_Hans": "可选的提示词，指导转录。有助于处理不常见的单词、缩写词或上下文。"
                  },
                  "label": {
                    "en_US": "Prompt",
                    "ja_JP": "プロンプト",
                    "pt_BR": "Prompt",
                    "zh_Hans": "提示词"
                  },
                  "llm_description": "Optional prompt to guide the model's transcription. This can help with uncommon words, acronyms, or providing context for better accuracy.",
                  "max": null,
                  "min": null,
                  "name": "prompt",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "ISO-639-1 language code (e.g. 'en', 'zh', 'ja'). Helps improve accuracy if audio language is known.",
                    "ja_JP": "ISO-639-1言語コード（例：'en'、'zh'、'ja'）。音声の言語が分かっている場合、精度を向上させるのに役立ちます。",
                    "pt_BR": "Código de idioma ISO-639-1 (ex. 'en', 'pt', 'es'). Ajuda a melhorar a precisão se o idioma do áudio for conhecido.",
                    "zh_Hans": "ISO-639-1 语言代码（例如 'en'、'zh'、'ja'）。如果知道音频语言，有助于提高准确性。"
                  },
                  "label": {
                    "en_US": "Language Code",
                    "ja_JP": "言語コード",
                    "pt_BR": "Código de Idioma",
                    "zh_Hans": "语言代码"
                  },
                  "llm_description": "ISO-639-1 language code of the input audio. Supplying the input language will improve accuracy if the audio language is known.",
                  "max": null,
                  "min": null,
                  "name": "language",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "none",
                  "form": "form",
                  "human_description": {
                    "en_US": "Add timestamps to transcript. Only available with whisper-1 and verbose_json response format.",
                    "ja_JP": "文字起こしにタイムスタンプを追加します。Whisper-1モデルとverbose_jsonレスポンスフォーマットでのみ利用可能です。",
                    "pt_BR": "Adicionar marcações de tempo à transcrição. Disponível apenas com whisper-1 e formato de resposta verbose_json.",
                    "zh_Hans": "向转录添加时间戳。仅适用于 whisper-1 和 verbose_json 响应格式。"
                  },
                  "label": {
                    "en_US": "Timestamp Granularities (Whisper-1 only)",
                    "ja_JP": "タイムスタンプ粒度 (Whisper-1のみ)",
                    "pt_BR": "Granularidade de Timestamp (Apenas Whisper-1)",
                    "zh_Hans": "时间戳粒度 (仅 Whisper-1)"
                  },
                  "llm_description": "Add timestamps to the transcript at segment or word level. This is only available with the whisper-1 model and requires verbose_json response format.",
                  "max": null,
                  "min": null,
                  "name": "timestamp_granularities",
                  "options": [
                    {
                      "label": {
                        "en_US": "None",
                        "ja_JP": "なし",
                        "pt_BR": "Nenhum",
                        "zh_Hans": "无"
                      },
                      "value": "none"
                    },
                    {
                      "label": {
                        "en_US": "Segment",
                        "ja_JP": "セグメント",
                        "pt_BR": "Segmento",
                        "zh_Hans": "段落"
                      },
                      "value": "segment"
                    },
                    {
                      "label": {
                        "en_US": "Word",
                        "ja_JP": "単語",
                        "pt_BR": "Palavra",
                        "zh_Hans": "单词"
                      },
                      "value": "word"
                    },
                    {
                      "label": {
                        "en_US": "Segment and Word",
                        "ja_JP": "セグメントと単語",
                        "pt_BR": "Segmento e Palavra",
                        "zh_Hans": "段落和单词"
                      },
                      "value": "segment_and_word"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": true,
                  "form": "form",
                  "human_description": {
                    "en_US": "Stream transcription results as they're generated. Only available with gpt-4o models.",
                    "ja_JP": "生成されると同時に文字起こし結果をストリーミングします。GPT-4oモデルでのみ利用可能です。",
                    "pt_BR": "Transmitir resultados da transcrição à medida que são gerados. Disponível apenas com modelos gpt-4o.",
                    "zh_Hans": "在生成结果时流式输出转录内容。仅适用于 gpt-4o 模型。"
                  },
                  "label": {
                    "en_US": "Stream Output (GPT-4o models only)",
                    "ja_JP": "ストリーミング出力 (GPT-4oモデルのみ)",
                    "pt_BR": "Saída em Stream (Apenas modelos GPT-4o)",
                    "zh_Hans": "流式输出 (仅 GPT-4o 模型)"
                  },
                  "llm_description": "Stream transcription results as they're generated. This feature is only available with gpt-4o-transcribe and gpt-4o-mini-transcribe models.",
                  "max": null,
                  "min": null,
                  "name": "stream",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": "default",
                  "form": "form",
                  "human_description": {
                    "en_US": "Choose how the plugin should format its output in Dify. Default returns both JSON and text, while the other options return only one format.",
                    "pt_BR": "Escolha como o plug-in deve formatar sua saída no Dify. O padrão retorna ambos JSON e texto, enquanto as outras op es retornam apenas um formato.",
                    "zh_Hans": "选择插件在 Dify 中的输出格式。默认返回 JSON 和文本，而其他选项只能返回一种格式。"
                  },
                  "label": {
                    "en_US": "Output Format",
                    "ja_JP": "出力形式",
                    "pt_BR": "Formato de Saída",
                    "zh_Hans": "输出格式"
                  },
                  "llm_description": "Choose how the plugin should format its output in Dify. Default returns both JSON and text, while the other options return only one format.",
                  "max": null,
                  "min": null,
                  "name": "output_format",
                  "options": [
                    {
                      "label": {
                        "en_US": "Default (JSON + Text)",
                        "ja_JP": "デフォルト (JSON + テキスト)",
                        "pt_BR": "Padrão (JSON + Texto)",
                        "zh_Hans": "默认 (JSON + 文本)"
                      },
                      "value": "default"
                    },
                    {
                      "label": {
                        "en_US": "JSON Only",
                        "ja_JP": "JSONのみ",
                        "pt_BR": "Apenas JSON",
                        "zh_Hans": "仅 JSON"
                      },
                      "value": "json_only"
                    },
                    {
                      "label": {
                        "en_US": "Text Only",
                        "ja_JP": "テキストのみ",
                        "pt_BR": "Apenas Texto",
                        "zh_Hans": "仅文本"
                      },
                      "value": "text_only"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-15T12:49:08Z",
        "version_updated_at": "2025-04-15T12:49:08Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Lark Spreadsheet, requires the following permissions: sheets:spreadsheet.\n",
          "zh_Hans": "Lark 电子表格，需要开通以下权限: sheets:spreadsheet。\n"
        },
        "category": "tool",
        "created_at": "2025-02-26T10:38:54Z",
        "endpoint": {},
        "icon": "langgenius/packages/lark_spreadsheet/_assets/icon.png",
        "index_id": "langgenius___lark_spreadsheet",
        "install_count": 192,
        "introduction": "",
        "label": {
          "en_US": "Lark Spreadsheet",
          "zh_Hans": "Lark 电子表格"
        },
        "latest_package_identifier": "langgenius/lark_spreadsheet:0.0.1@cf67d632766070033b5f1d692e4a731fd4ae6315105995c4f79d1e073c3af3ed",
        "latest_version": "0.0.1",
        "model": {},
        "name": "lark_spreadsheet",
        "org": "langgenius",
        "plugin_id": "langgenius/lark_spreadsheet",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/lark_spreadsheet.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "social"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "APP ID"
              },
              "name": "app_id",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Lark app id",
                "zh_Hans": "请输入你的 Lark app id"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": "https://open.larksuite.com/app"
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "APP Secret"
              },
              "name": "app_secret",
              "options": null,
              "placeholder": {
                "en_US": "Please input your app secret",
                "zh_Hans": "请输入你的 Lark app secret"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            }
          ],
          "identity": {
            "author": "langgenius",
            "description": {
              "en_US": "Lark Spreadsheet, requires the following permissions: sheets:spreadsheet.\n",
              "zh_Hans": "Lark 电子表格，需要开通以下权限: sheets:spreadsheet。\n"
            },
            "icon": "icon.png",
            "label": {
              "en_US": "Lark Spreadsheet",
              "zh_Hans": "Lark 电子表格"
            },
            "name": "lark_spreadsheet",
            "tags": [
              "social",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Create Spreadsheet",
                  "zh_Hans": "创建电子表格"
                },
                "llm": "A tool for creating spreadsheets. (创建电子表格)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Create Spreadsheet",
                  "zh_Hans": "创建电子表格"
                },
                "name": "create_spreadsheet"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The title of the spreadsheet",
                    "zh_Hans": "电子表格的标题"
                  },
                  "label": {
                    "en_US": "Spreadsheet Title",
                    "zh_Hans": "电子表格标题"
                  },
                  "llm_description": "电子表格的标题",
                  "max": null,
                  "min": null,
                  "name": "title",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The token of the folder, supports folder URL input, e.g., https://bytedance.larkoffice.com/drive/folder/CxHEf4DCSlNkL2dUTCJcPRgentg",
                    "zh_Hans": "文件夹 token，支持文件夹 URL 输入，如：https://bytedance.larkoffice.com/drive/folder/CxHEf4DCSlNkL2dUTCJcPRgentg"
                  },
                  "label": {
                    "en_US": "Folder Token",
                    "zh_Hans": "文件夹 token"
                  },
                  "llm_description": "文件夹 token，支持文件夹 URL 输入，如：https://bytedance.larkoffice.com/drive/folder/CxHEf4DCSlNkL2dUTCJcPRgentg",
                  "max": null,
                  "min": null,
                  "name": "folder_token",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Add Rows",
                  "zh_Hans": "新增多行至工作表最后"
                },
                "llm": "A tool for adding multiple rows to the end of a spreadsheet. (新增多行至工作表最后)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Add Rows",
                  "zh_Hans": "新增多行至工作表最后"
                },
                "name": "add_rows"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Spreadsheet token, supports input of spreadsheet URL.",
                    "zh_Hans": "电子表格 token，支持输入电子表格 url。"
                  },
                  "label": {
                    "en_US": "spreadsheet_token",
                    "zh_Hans": "电子表格 token"
                  },
                  "llm_description": "电子表格 token，支持输入电子表格 url。",
                  "max": null,
                  "min": null,
                  "name": "spreadsheet_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet ID, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表 ID，与 sheet_name 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_id",
                    "zh_Hans": "工作表 ID"
                  },
                  "llm_description": "工作表 ID，与 sheet_name 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet name, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表名称，与 sheet_id 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_name",
                    "zh_Hans": "工作表名称"
                  },
                  "llm_description": "工作表名称，与 sheet_id 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Number of rows to add, range (0-5000].",
                    "zh_Hans": "要增加行数，范围(0-5000]。"
                  },
                  "label": {
                    "en_US": "length",
                    "zh_Hans": "要增加行数"
                  },
                  "llm_description": "要增加行数，范围(0-5000]。",
                  "max": null,
                  "min": null,
                  "name": "length",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Content of the new rows, array of objects in string format, each array represents a row of table data, format like: [ [ \"ID\",\"Name\",\"Age\" ],[ 1,\"Zhang San\",10 ],[ 2,\"Li Si\",11 ] ].\n",
                    "zh_Hans": "新增行的表格内容，数组对象字符串，每个数组一行表格数据，格式,如：[[\"编号\",\"姓名\",\"年龄\"],[1,\"张三\",10],[2,\"李四\",11]]。"
                  },
                  "label": {
                    "en_US": "values",
                    "zh_Hans": "新增行的表格内容"
                  },
                  "llm_description": "新增行的表格内容，数组对象字符串，每个数组一行表格数据，格式,如：[[\"编号\",\"姓名\",\"年龄\"],[1,\"张三\",10],[2,\"李四\",11]]。",
                  "max": null,
                  "min": null,
                  "name": "values",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Read Rows",
                  "zh_Hans": "读取工作表行数据"
                },
                "llm": "A tool for reading row data from a spreadsheet. (读取工作表行数据)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Read Rows",
                  "zh_Hans": "读取工作表行数据"
                },
                "name": "read_rows"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Spreadsheet token, supports input of spreadsheet URL.",
                    "zh_Hans": "电子表格 token，支持输入电子表格 url。"
                  },
                  "label": {
                    "en_US": "spreadsheet_token",
                    "zh_Hans": "电子表格 token"
                  },
                  "llm_description": "电子表格 token，支持输入电子表格 url。",
                  "max": null,
                  "min": null,
                  "name": "spreadsheet_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet ID, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表 ID，与 sheet_name 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_id",
                    "zh_Hans": "工作表 ID"
                  },
                  "llm_description": "工作表 ID，与 sheet_name 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet name, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表名称，与 sheet_id 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_name",
                    "zh_Hans": "工作表名称"
                  },
                  "llm_description": "工作表名称，与 sheet_id 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "open_id",
                  "form": "form",
                  "human_description": {
                    "en_US": "User ID type, optional values are open_id, union_id, user_id, with a default value of open_id.",
                    "zh_Hans": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。"
                  },
                  "label": {
                    "en_US": "user_id_type",
                    "zh_Hans": "用户 ID 类型"
                  },
                  "llm_description": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。",
                  "max": null,
                  "min": null,
                  "name": "user_id_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "open_id",
                        "zh_Hans": "open_id"
                      },
                      "value": "open_id"
                    },
                    {
                      "label": {
                        "en_US": "union_id",
                        "zh_Hans": "union_id"
                      },
                      "value": "union_id"
                    },
                    {
                      "label": {
                        "en_US": "user_id",
                        "zh_Hans": "user_id"
                      },
                      "value": "user_id"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Starting row number, starting from 1.",
                    "zh_Hans": "起始行号，从 1 开始。"
                  },
                  "label": {
                    "en_US": "start_row",
                    "zh_Hans": "起始行号"
                  },
                  "llm_description": "起始行号，从 1 开始。",
                  "max": null,
                  "min": null,
                  "name": "start_row",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Number of rows to read.",
                    "zh_Hans": "读取行数"
                  },
                  "label": {
                    "en_US": "num_rows",
                    "zh_Hans": "读取行数"
                  },
                  "llm_description": "读取行数",
                  "max": null,
                  "min": null,
                  "name": "num_rows",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Read Table",
                  "zh_Hans": "自定义读取电子表格行列数据"
                },
                "llm": "A tool for custom reading of row and column data from a spreadsheet. (自定义读取电子表格行列数据)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Read Table",
                  "zh_Hans": "自定义读取电子表格行列数据"
                },
                "name": "read_table"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Spreadsheet token, supports input of spreadsheet URL.",
                    "zh_Hans": "电子表格 token，支持输入电子表格 url。"
                  },
                  "label": {
                    "en_US": "spreadsheet_token",
                    "zh_Hans": "电子表格 token"
                  },
                  "llm_description": "电子表格 token，支持输入电子表格 url。",
                  "max": null,
                  "min": null,
                  "name": "spreadsheet_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet ID, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表 ID，与 sheet_name 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_id",
                    "zh_Hans": "工作表 ID"
                  },
                  "llm_description": "工作表 ID，与 sheet_name 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet name, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表名称，与 sheet_id 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_name",
                    "zh_Hans": "工作表名称"
                  },
                  "llm_description": "工作表名称，与 sheet_id 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "open_id",
                  "form": "form",
                  "human_description": {
                    "en_US": "User ID type, optional values are open_id, union_id, user_id, with a default value of open_id.",
                    "zh_Hans": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。"
                  },
                  "label": {
                    "en_US": "user_id_type",
                    "zh_Hans": "用户 ID 类型"
                  },
                  "llm_description": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。",
                  "max": null,
                  "min": null,
                  "name": "user_id_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "open_id",
                        "zh_Hans": "open_id"
                      },
                      "value": "open_id"
                    },
                    {
                      "label": {
                        "en_US": "union_id",
                        "zh_Hans": "union_id"
                      },
                      "value": "union_id"
                    },
                    {
                      "label": {
                        "en_US": "user_id",
                        "zh_Hans": "user_id"
                      },
                      "value": "user_id"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Starting row number, starting from 1.",
                    "zh_Hans": "起始行号，从 1 开始。"
                  },
                  "label": {
                    "en_US": "start_row",
                    "zh_Hans": "起始行号"
                  },
                  "llm_description": "起始行号，从 1 开始。",
                  "max": null,
                  "min": null,
                  "name": "start_row",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Number of rows to read.",
                    "zh_Hans": "读取行数"
                  },
                  "label": {
                    "en_US": "num_rows",
                    "zh_Hans": "读取行数"
                  },
                  "llm_description": "读取行数",
                  "max": null,
                  "min": null,
                  "name": "num_rows",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Data range, format like: A1:B2, can be empty when query=all.\n",
                    "zh_Hans": "取数范围,格式如:A1:B2，query=all 时可为空。"
                  },
                  "label": {
                    "en_US": "range",
                    "zh_Hans": "取数范围"
                  },
                  "llm_description": "取数范围,格式如:A1:B2，query=all 时可为空。",
                  "max": null,
                  "min": null,
                  "name": "range",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Pass \"all\" to query all data in the table, but no more than 100 columns.",
                    "zh_Hans": "传 all，表示查询表格所有数据，但最多查询 100 列数据。"
                  },
                  "label": {
                    "en_US": "query",
                    "zh_Hans": "查询"
                  },
                  "llm_description": "传 all，表示查询表格所有数据，但最多查询 100 列数据。",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get Spreadsheet",
                  "zh_Hans": "获取电子表格信息"
                },
                "llm": "A tool for getting information from spreadsheets. (获取电子表格信息)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Get Spreadsheet",
                  "zh_Hans": "获取电子表格信息"
                },
                "name": "get_spreadsheet"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Spreadsheet token, supports input of spreadsheet URL.",
                    "zh_Hans": "电子表格 token，支持输入电子表格 URL。"
                  },
                  "label": {
                    "en_US": "Spreadsheet Token",
                    "zh_Hans": "电子表格 token"
                  },
                  "llm_description": "电子表格 token，支持输入电子表格 URL。",
                  "max": null,
                  "min": null,
                  "name": "spreadsheet_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "open_id",
                  "form": "form",
                  "human_description": {
                    "en_US": "User ID type, optional values are open_id, union_id, user_id, with a default value of open_id.",
                    "zh_Hans": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。"
                  },
                  "label": {
                    "en_US": "user_id_type",
                    "zh_Hans": "用户 ID 类型"
                  },
                  "llm_description": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。",
                  "max": null,
                  "min": null,
                  "name": "user_id_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "open_id",
                        "zh_Hans": "open_id"
                      },
                      "value": "open_id"
                    },
                    {
                      "label": {
                        "en_US": "union_id",
                        "zh_Hans": "union_id"
                      },
                      "value": "union_id"
                    },
                    {
                      "label": {
                        "en_US": "user_id",
                        "zh_Hans": "user_id"
                      },
                      "value": "user_id"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Read Cols",
                  "zh_Hans": "读取工作表列数据"
                },
                "llm": "A tool for reading column data from a spreadsheet. (读取工作表列数据)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Read Cols",
                  "zh_Hans": "读取工作表列数据"
                },
                "name": "read_cols"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Spreadsheet token, supports input of spreadsheet URL.",
                    "zh_Hans": "电子表格 token，支持输入电子表格 url。"
                  },
                  "label": {
                    "en_US": "spreadsheet_token",
                    "zh_Hans": "电子表格 token"
                  },
                  "llm_description": "电子表格 token，支持输入电子表格 url。",
                  "max": null,
                  "min": null,
                  "name": "spreadsheet_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet ID, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表 ID，与 sheet_name 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_id",
                    "zh_Hans": "工作表 ID"
                  },
                  "llm_description": "工作表 ID，与 sheet_name 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet name, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表名称，与 sheet_id 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_name",
                    "zh_Hans": "工作表名称"
                  },
                  "llm_description": "工作表名称，与 sheet_id 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "open_id",
                  "form": "form",
                  "human_description": {
                    "en_US": "User ID type, optional values are open_id, union_id, user_id, with a default value of open_id.",
                    "zh_Hans": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。"
                  },
                  "label": {
                    "en_US": "user_id_type",
                    "zh_Hans": "用户 ID 类型"
                  },
                  "llm_description": "用户 ID 类型，可选值有 open_id、union_id、user_id，默认值为 open_id。",
                  "max": null,
                  "min": null,
                  "name": "user_id_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "open_id",
                        "zh_Hans": "open_id"
                      },
                      "value": "open_id"
                    },
                    {
                      "label": {
                        "en_US": "union_id",
                        "zh_Hans": "union_id"
                      },
                      "value": "union_id"
                    },
                    {
                      "label": {
                        "en_US": "user_id",
                        "zh_Hans": "user_id"
                      },
                      "value": "user_id"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Starting column number, starting from 1.",
                    "zh_Hans": "起始列号，从 1 开始。"
                  },
                  "label": {
                    "en_US": "start_col",
                    "zh_Hans": "起始列号"
                  },
                  "llm_description": "起始列号，从 1 开始。",
                  "max": null,
                  "min": null,
                  "name": "start_col",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Number of columns to read.",
                    "zh_Hans": "读取列数"
                  },
                  "label": {
                    "en_US": "num_cols",
                    "zh_Hans": "读取列数"
                  },
                  "llm_description": "读取列数",
                  "max": null,
                  "min": null,
                  "name": "num_cols",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Add Cols",
                  "zh_Hans": "新增多列至工作表最后"
                },
                "llm": "A tool for adding multiple columns to the end of a spreadsheet. (新增多列至工作表最后)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Add Cols",
                  "zh_Hans": "新增多列至工作表最后"
                },
                "name": "add_cols"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Spreadsheet token, supports input of spreadsheet URL.",
                    "zh_Hans": "电子表格 token，支持输入电子表格 url。"
                  },
                  "label": {
                    "en_US": "spreadsheet_token",
                    "zh_Hans": "电子表格 token"
                  },
                  "llm_description": "电子表格 token，支持输入电子表格 url。",
                  "max": null,
                  "min": null,
                  "name": "spreadsheet_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet ID, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表 ID，与 sheet_name 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_id",
                    "zh_Hans": "工作表 ID"
                  },
                  "llm_description": "工作表 ID，与 sheet_name 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet name, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表名称，与 sheet_id 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_name",
                    "zh_Hans": "工作表名称"
                  },
                  "llm_description": "工作表名称，与 sheet_id 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Number of columns to add, range (0-5000].",
                    "zh_Hans": "要增加的列数，范围(0-5000]。"
                  },
                  "label": {
                    "en_US": "length",
                    "zh_Hans": "要增加的列数"
                  },
                  "llm_description": "要增加的列数，范围(0-5000]。",
                  "max": null,
                  "min": null,
                  "name": "length",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Content of the new columns, array of objects in string format, each array represents a row of table data, format like: [ [ \"ID\",\"Name\",\"Age\" ],[ 1,\"Zhang San\",10 ],[ 2,\"Li Si\",11 ] ].\n",
                    "zh_Hans": "新增列的单元格内容，数组对象字符串，每个数组一行表格数据，格式：[[\"编号\",\"姓名\",\"年龄\"],[1,\"张三\",10],[2,\"李四\",11]]。"
                  },
                  "label": {
                    "en_US": "values",
                    "zh_Hans": "新增列的单元格内容"
                  },
                  "llm_description": "新增列的单元格内容，数组对象字符串，每个数组一行表格数据，格式：[[\"编号\",\"姓名\",\"年龄\"],[1,\"张三\",10],[2,\"李四\",11]]。",
                  "max": null,
                  "min": null,
                  "name": "values",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "List Spreadsheet Sheets",
                  "zh_Hans": "列出电子表格所有工作表"
                },
                "llm": "A tool for listing all sheets in a spreadsheet. (列出电子表格所有工作表)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "List Spreadsheet Sheets",
                  "zh_Hans": "列出电子表格所有工作表"
                },
                "name": "list_spreadsheet_sheets"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Spreadsheet token, supports input of spreadsheet URL.",
                    "zh_Hans": "电子表格 token，支持输入电子表格 URL。"
                  },
                  "label": {
                    "en_US": "Spreadsheet Token",
                    "zh_Hans": "电子表格 token"
                  },
                  "llm_description": "电子表格 token，支持输入电子表格 URL。",
                  "max": null,
                  "min": null,
                  "name": "spreadsheet_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-26T10:38:58Z",
        "version_updated_at": "2025-02-26T10:38:58Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "AWS Bedrock Knowledge Base API Endpoint for Dify External Knowledge Base",
          "ja_JP": "AWS Bedrock Knowledge Base API Endpoint for Dify External Knowledge Base",
          "pt_BR": "AWS Bedrock Knowledge Base API Endpoint for Dify External Knowledge Base",
          "zh_Hans": "AWS Bedrock Knowledge Base API Endpoint for Dify External Knowledge Base"
        },
        "category": "extension",
        "created_at": "2025-03-17T11:14:02Z",
        "endpoint": {
          "endpoints": [
            {
              "hidden": false,
              "method": "POST",
              "path": "/retrieval"
            }
          ],
          "settings": [
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "AWS Secret Access Key",
                "pt_BR": "Chave de Acesso Secreta da AWS",
                "zh_Hans": "AWS 秘密访问密钥"
              },
              "name": "aws_secret_access_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your AWS Secret Access Key",
                "pt_BR": "Por favor, insira sua Chave de Acesso Secreta da AWS",
                "zh_Hans": "请输入你的 AWS 秘密访问密钥"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "AWS Access Key ID",
                "pt_BR": "ID da Chave de Acesso da AWS",
                "zh_Hans": "AWS 访问密钥 ID"
              },
              "name": "aws_access_key_id",
              "options": null,
              "placeholder": {
                "en_US": "Please input your AWS Access Key ID",
                "pt_BR": "Por favor, insira seu ID da Chave de Acesso da AWS",
                "zh_Hans": "请输入你的 AWS 访问密钥 ID"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "AWS Region Name",
                "pt_BR": "Nome da Região AWS",
                "zh_Hans": "AWS 区域名称"
              },
              "name": "region_name",
              "options": null,
              "placeholder": {
                "en_US": "Please input your AWS Region Name (e.g., us-east-1)",
                "pt_BR": "Please input your AWS Region Name (e.g., us-east-1)",
                "zh_Hans": "请输入你的 AWS 区域名称（例如：us-east-1）"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            }
          ]
        },
        "icon": "langgenius/packages/aws_bedrock_knowledge_base/_assets/icon.svg",
        "index_id": "langgenius___aws_bedrock_knowledge_base",
        "install_count": 188,
        "introduction": "## aws_bedrock_knowledge_base\n\n**Author:** yungler\n**Version:** 0.0.1\n**Type:** tool\n\n### Description\n\nIf you are trying to build AI Agent with context retrieving capability and you are not primarily using Dify's Knowledge Base, you can use Dify's External Knowledge Base to connect with the RAG solution you prefer. This plugin will help you deploy your AWS Bedrock Knowledge Base client as an endpoint so Dify External Knowledge Base can seamlessly connect with it. \n\nBefore we start, make sure you have set up your AWS Bedrock Knowledge Base. You can learn how to use AWS Bedrock Knowledge Base by https://aws.amazon.com/bedrock/knowledge-bases/.\n\nHere's what we need from AWS:\n\nAWS Access Key and AWS Access Key ID. You can get these in the right upper corner,security credential, of your AWS console See https://docs.aws.amazon.com/keyspaces/latest/devguide/create.keypair.html to learn how to get these.\n<img src=\"./_assets/aws_security_credential.png\" width=\"600\" />\n\nThe Knowledge ID of your knowledge base, which you will get when your AWS Bedrock Knowledge Base is configured.\n<img src=\"./_assets/knowledge_id.png\" width=\"600\" />\n\nFollow these steps to connect your Dify Knowledge Base with AWS Bedrock Knowledge Base:\n1. Go to AWS Bedrock Knowledge Base Endpoint and setup your endpoint with AWS Access Key, AWS Access Key ID, and the Region.\n<img src=\"./_assets/setup_endpoint.png\" width=\"600\" />\n\n2. Copy the URL of the created endpoint\n<img src=\"./_assets/copy_endpoint_url.png\" width=\"600\" />\n\n3. Go to Dify Knowledge Base and click on the right upper corner External Knowledge API. Paste the URL into API Endpoint. Give the endpoint a name. \n**NOTICE: You must REMOVE the \"/retrieval\" in your URL!!!!!** For API Key, as we didn't configure any authorization, you can type in anything you want. So **PLEASE MAKE SURE NO ONE KNOWS THE ENDPOINT URL!!!**\n<img src=\"./_assets/paste_endpoint_url.png\" width=\"600\" />\n\n4. Once it's set up, click on connect to an external knowledge base. Choose the external knowledge API you just created, and put the Knowledge ID here. You can configure the top k and threshold here before connection.\n\n5. Now try a retrieval testing. You can see a chunk is retrieved from your Bedrock Knowledge Base\n<img src=\"./_assets/retrieval_test.png\" width=\"600\" />\n\n\n",
        "label": {
          "en_US": "Aws Bedrock Knowledge Base",
          "ja_JP": "Aws Bedrock Knowledge Base",
          "pt_BR": "Aws Bedrock Knowledge Base",
          "zh_Hans": "Aws Bedrock Knowledge Base"
        },
        "latest_package_identifier": "langgenius/aws_bedrock_knowledge_base:0.0.3@4933af446e967d0cdb36507a7bd3e63706d692fb06f3554f6dd702471146737b",
        "latest_version": "0.0.3",
        "model": {},
        "name": "aws_bedrock_knowledge_base",
        "org": "langgenius",
        "plugin_id": "langgenius/aws_bedrock_knowledge_base",
        "plugins": {
          "agent_strategies": null,
          "endpoints": [
            "provider/aws_bedrock_knowledge_base.yaml"
          ],
          "models": null,
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "endpoint": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-03-20T09:25:17Z",
        "version_updated_at": "2025-03-20T09:25:17Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "VESSL AI"
        },
        "category": "model",
        "created_at": "2024-12-06T11:33:52Z",
        "endpoint": {},
        "icon": "langgenius/packages/vessl_ai/_assets/icon_s_en.svg",
        "index_id": "langgenius___vessl_ai",
        "install_count": 186,
        "introduction": "## Overview\n\n[Vessl AI](https://vessl.ai/) is a platform that streamlines the machine learning workflow, offering tools for data, models, training, and deployment. The platform supports multiple frameworks and facilitates end-to-end AI development.\n\n## Configure\n\nInstall the Vessl AI plugin, then configure it in Model Provider settings with the Model Name, Endpoint Url, API Key, and choose the Completion Mode. Get your API key from [Vessl AI](https://dashboard.cohere.com/api-keys) and save your settings.\n\n![](./_assets/vessl_config.PNG)",
        "label": {
          "en_US": "VESSL AI"
        },
        "latest_package_identifier": "langgenius/vessl_ai:0.0.2@461d0cd7bd290eea23c9f673c873496bf9b2dd02e57d8870283ad63a3ddd4090",
        "latest_version": "0.0.2",
        "model": {
          "background": "#F1EFED",
          "configurate_methods": [
            "customizable-model"
          ],
          "description": {
            "en_US": "VESSL AI"
          },
          "help": {
            "title": {
              "en_US": "How to deploy VESSL AI LLM Model Endpoint"
            },
            "url": {
              "en_US": "https://docs.vessl.ai/guides/get-started/llama3-deployment"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.png"
          },
          "icon_small": {
            "en_US": "icon_s_en.svg"
          },
          "label": {
            "en_US": "VESSL AI"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "Endpoint Url"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter VESSL AI service endpoint url"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "endpoint_url"
              },
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter VESSL AI secret key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              },
              {
                "default": "chat",
                "label": {
                  "en_US": "Completion Mode"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Completion"
                    },
                    "show_on": [],
                    "value": "completion"
                  },
                  {
                    "label": {
                      "en_US": "Chat"
                    },
                    "show_on": [],
                    "value": "chat"
                  }
                ],
                "placeholder": {
                  "en_US": "Select completion mode"
                },
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "select",
                "variable": "mode"
              }
            ],
            "model": {
              "label": {
                "en_US": "Model Name"
              },
              "placeholder": {
                "en_US": "Enter model name"
              }
            }
          },
          "models": [],
          "provider": "vessl_ai",
          "provider_credential_schema": null,
          "supported_model_types": [
            "llm"
          ]
        },
        "name": "vessl_ai",
        "org": "langgenius",
        "plugin_id": "langgenius/vessl_ai",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/vessl_ai.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-02-17T06:55:54Z",
        "version_updated_at": "2025-02-17T06:55:54Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "DingTalk Spreadsheet, requires the following permissions (dingtalk-document, user/get.)",
          "ja_JP": "釘釘电子表格，需要开通以下权限： 钉钉表格权限，个人信息；登录钉钉开发者后台 > 企业内部开发 > 找到需添加权限的应用 > 权限管理 > 通讯录管理页面，勾选企业员工手机号信息和邮箱等个人信息，单击申请权限",
          "pt_BR": "DingTalk Spreadsheet, requires the following permissions (dingtalk-document, user/get.)",
          "zh_Hans": "釘釘电子表格，需要开通以下权限： 钉钉表格权限，个人信息；登录钉钉开发者后台 > 企业内部开发 > 找到需添加权限的应用 > 权限管理 > 通讯录管理页面，勾选企业员工手机号信息和邮箱等个人信息，单击申请权限"
        },
        "category": "tool",
        "created_at": "2025-04-10T14:00:08Z",
        "endpoint": {},
        "icon": "witmeng/packages/dingtalk_spreadsheet/_assets/ding.png",
        "index_id": "witmeng___dingtalk_spreadsheet",
        "install_count": 184,
        "introduction": "# DingTalk Spreadsheet Plugin\r\n\r\n\r\n\r\n## Introduction\r\n\r\nThe DingTalk Spreadsheet Plugin is a collection of tools for operating on spreadsheets in DingTalk documents. Through this plugin, you can read, write, and modify DingTalk spreadsheets on the Dify platform without manually opening DingTalk documents to complete data processing.\r\n\r\n\r\n\r\n## Prerequisites\r\n\r\nUsing this plugin requires the following DingTalk permissions:\r\n- DingTalk spreadsheet permission\r\n- Personal information permission\r\n- Permission to obtain member basic information by phone number\r\n\r\nConfiguration method: Log in to the DingTalk developer backend > Enterprise internal development > Find the application that needs to add permissions > Permission management > Address book management page, check enterprise employee phone number information and email and other personal information, click Apply for permission.\r\n\r\n\r\n\r\n## Credential Configuration\r\n\r\nThe following credentials need to be configured to use this plugin:\r\n- `app_key`: The AppKey of the DingTalk application\r\n- `app_secret`: The AppSecret of the DingTalk application\r\n\r\n\r\n\r\n## Feature List\r\n\r\n### 1. Create Sheet (create_sheet)\r\nCreate a new worksheet.\r\n\r\n**Parameters**:\r\n- `operator_id`: The unionId of the operator\r\n- `table_id`: The ID of the table, supports table URL input\r\n- `sheet_name`: The name of the new worksheet\r\n\r\n**Example**:\r\n```python\r\n# Create a new worksheet named \"Sales Data\"\r\n{\r\n  \"operator_id\": \"your_operator_id\",\r\n  \"table_id\": \"https://alidocs.dingtalk.com/i/nodes/AbCdEfGh\",\r\n  \"sheet_name\": \"Sales Data\"\r\n}\r\n```\r\n**Returns**:\r\n- JSON data of the creation result\r\n\r\n\r\n\r\n### 2. Read Sheet Information (read_sheet)\r\n\r\nGet basic information about the worksheet, including the number of rows, columns, and other metadata.\r\n\r\n**Parameters**:\r\n- `operator_id`: The unionId of the operator\r\n- `table_id`: The ID of the table, supports table URL input\r\n- `sheet_id`: Worksheet ID (choose one between sheet_id and sheet_name)\r\n- `sheet_name`: Worksheet name (choose one between sheet_id and sheet_name)\r\n\r\n**Example**:\r\n```python\r\n# Get information about the worksheet named \"Sales Data\"\r\n{\r\n  \"operator_id\": \"your_operator_id\",\r\n  \"table_id\": \"https://alidocs.dingtalk.com/i/nodes/AbCdEfGh\",\r\n  \"sheet_id\": \"your_sheet_id\",\r\n  \"sheet_name\": \"Sales Data\"\r\n}\r\n```\r\n**Returns**:\r\n- JSON data of worksheet information\r\n\r\n\r\n\r\n### 3. Read Table Data (read_table)\r\n\r\nRead the entire table's data content.\r\n\r\n**Parameters**:\r\n- `operator_id`: The unionId of the operator\r\n- `table_id`: The ID of the table, supports table URL input\r\n\r\n**Example**:\r\n```python\r\n# Read the entire table's data\r\n{\r\n  \"operator_id\": \"your_operator_id\",\r\n  \"table_id\": \"https://alidocs.dingtalk.com/i/nodes/AbCdEfGh\"\r\n}\r\n```\r\n**Returns**:\r\n- JSON array of all table data\r\n\r\n\r\n\r\n### 4. Read Cell Area (read_area)\r\n\r\nRead cell data within a specified area.\r\n\r\n**Parameters**:\r\n- `operator_id`: The unionId of the operator\r\n- `table_id`: The ID of the table, supports table URL input\r\n- `sheet_id`: Worksheet ID (choose one between sheet_id and sheet_name)\r\n- `sheet_name`: Worksheet name (choose one between sheet_id and sheet_name)\r\n- `range_address`: Cell area, e.g., \"A1:C5\"\r\n\r\n**Example**:\r\n```python\r\n# Read data within the cell area \"A1:C5\"\r\n{\r\n  \"operator_id\": \"your_operator_id\",\r\n  \"table_id\": \"https://alidocs.dingtalk.com/i/nodes/AbCdEfGh\",\r\n  \"sheet_id\": \"your_sheet_id\",\r\n  \"sheet_name\": \"Sales Data\",\r\n  \"range_address\": \"A1:C5\"\r\n}\r\n```\r\n**Returns**:\r\n- JSON array of cell data within the specified area\r\n\r\n\r\n\r\n### 5. Update Cell Area (update_area)\r\n\r\nUpdate cell data within a specified area.\r\n\r\n**Parameters**:\r\n- `operator_id`: The unionId of the operator\r\n- `table_id`: The ID of the table, supports table URL input\r\n- `sheet_id`: Worksheet ID (choose one between sheet_id and sheet_name)\r\n- `sheet_name`: Worksheet name (choose one between sheet_id and sheet_name)\r\n- `range_address`: Cell area, e.g., \"A1:C5\"\r\n- `values`: Data to update, in two-dimensional array format\r\n\r\n**Example**:\r\n```python\r\n# Update data within the cell area \"A1:C2\"\r\n{\r\n  \"operator_id\": \"your_operator_id\",\r\n  \"table_id\": \"https://alidocs.dingtalk.com/i/nodes/AbCdEfGh\",\r\n  \"operator_id\": \"your_operator_id\",\r\n  \"sheet_id\": \"your_sheet_id\",\r\n  \"sheet_name\": \"Sales Data\",\r\n  \"range_address\": \"A1:C2\",\r\n  \"values\": [\r\n    [\"New Data 1\", \"New Data 2\", \"New Data 3\"],\r\n    [\"New Data 4\", \"New Data 5\", \"New Data 6\"]\r\n  ]\r\n}\r\n```\r\n**Returns**:\r\n- JSON data of the operation result\r\n\r\n\r\n### 6. Clear Cell Area (clear_area)\r\n\r\nClear cell data within a specified area, preserving cell formatting.\r\n\r\n**Parameters**:\r\n- `operator_id`: The unionId of the operator\r\n- `table_id`: The ID of the table, supports table URL input\r\n- `sheet_id`: Worksheet ID (choose one between sheet_id and sheet_name)\r\n- `sheet_name`: Worksheet name (choose one between sheet_id and sheet_name)\r\n- `range_address`: Cell area, e.g., \"A1:C5\"\r\n\r\n**Example**:\r\n```python\r\n# Clear data within the cell area \"A1:C5\"\r\n{\r\n  \"operator_id\": \"your_operator_id\",\r\n   \"table_id\": \"https://alidocs.dingtalk.com/i/nodes/AbCdEfGh\",\r\n  \"sheet_id\": \"your_sheet_id\",\r\n  \"sheet_name\": \"Sales Data\",\r\n  \"range_address\": \"A1:C5\"\r\n}\r\n```\r\n**Returns**:\r\n- JSON data of the operation result\r\n\r\n\r\n\r\n### 7. Get Operator ID (get_operator_id)\r\n\r\nGet the DingTalk user's operator ID through their phone number.\r\n\r\n**Parameters**:\r\n- `mobile`: User's phone number\r\n\r\n**Example**:\r\n```python\r\n# Get the DingTalk user's operator ID through their phone number\r\n{\r\n  \"mobile\": \"12345678901\"\r\n}\r\n```\r\n**Returns**:\r\n- User's operator ID (unionId)\r\n\r\n\r\n\r\n### 8. Insert Data Before Row (insert_data_befor_row)\r\n\r\nInsert new rows before a specified row and fill with data.\r\n\r\n**Parameters**:\r\n- `operator_id`: The unionId of the operator\r\n- `table_id`: The ID of the table, supports table URL input\r\n- `sheet_id`: Worksheet ID (choose one between sheet_id and sheet_name)\r\n- `sheet_name`: Worksheet name (choose one between sheet_id and sheet_name)\r\n- `start_row`: Specified starting row number\r\n- `row_count`: Number of rows to insert\r\n- `start_col`: Starting column, default is 'A'\r\n- `values`: Data to insert, in two-dimensional array format\r\n\r\n**Example**:\r\n```python\r\n# Insert new rows before row 3 and fill with data\r\n{\r\n  \"operator_id\": \"your_operator_id\",\r\n   \"table_id\": \"https://alidocs.dingtalk.com/i/nodes/AbCdEfGh\",\r\n  \"sheet_id\": \"your_sheet_id\",\r\n  \"sheet_name\": \"Sales Data\",\r\n  \"start_row\": 3,\r\n  \"row_count\": 2,\r\n  \"start_col\": \"A\",\r\n  \"values\": [\r\n    [\"New Data 1\", \"New Data 2\", \"New Data 3\"],\r\n    [\"New Data 4\", \"New Data 5\", \"New Data 6\"]\r\n  ]\r\n}\r\n```\r\n**Returns**:\r\n- JSON data of the operation result\r\n\r\n\r\n\r\n### 9. Insert Data Before Column (insert_data_befor_col)\r\n\r\nInsert new columns before a specified column and fill with data.\r\n\r\n**Parameters**:\r\n- `operator_id`: The unionId of the operator\r\n- `table_id`: The ID of the table, supports table URL input\r\n- `sheet_id`: Worksheet ID (choose one between sheet_id and sheet_name)\r\n- `sheet_name`: Worksheet name (choose one between sheet_id and sheet_name)\r\n- `start_col`: Specified starting column, such as 'A', 'B', etc.\r\n- `col_count`: Number of columns to insert\r\n- `start_row`: Starting row number\r\n- `values`: Data to insert, in two-dimensional array format\r\n\r\n**Example**:\r\n```python\r\n# Insert new columns before column B and fill with data\r\n{\r\n  \"operator_id\": \"your_operator_id\",\r\n   \"table_id\": \"https://alidocs.dingtalk.com/i/nodes/AbCdEfGh\",\r\n  \"sheet_id\": \"your_sheet_id\",\r\n  \"sheet_name\": \"Sales Data\",\r\n  \"start_col\": \"B\",\r\n  \"col_count\": 2,\r\n  \"start_row\": 1,\r\n  \"values\": [\r\n    [\"New Data 1\", \"New Data 2\", \"New Data 3\"],\r\n    [\"New Data 4\", \"New Data 5\", \"New Data 6\"]\r\n  ]\r\n}\r\n```\r\n**Returns**:\r\n- JSON data of the operation result\r\n\r\n\r\n\r\n### 10. Delete Row (del_row)\r\n\r\nDelete specified rows.\r\n\r\n**Parameters**:\r\n- `operator_id`: The unionId of the operator\r\n- `table_id`: The ID of the table, supports table URL input\r\n- `sheet_id`: Worksheet ID (choose one between sheet_id and sheet_name)\r\n- `sheet_name`: Worksheet name (choose one between sheet_id and sheet_name)\r\n- `start_row`: Starting row number\r\n- `row_count`: Number of rows to delete\r\n\r\n**Example**:\r\n```python\r\n# Delete rows from row 3 to row 5\r\n{\r\n  \"operator_id\": \"your_operator_id\",\r\n  \"table_id\": \"https://alidocs.dingtalk.com/i/nodes/AbCdEfGh\",\r\n  \"sheet_id\": \"your_sheet_id\",\r\n  \"sheet_name\": \"Sales Data\",\r\n  \"start_row\": 3,\r\n  \"row_count\": 2\r\n}\r\n```\r\n**Returns**:\r\n- JSON data of the operation result\r\n\r\n\r\n\r\n### 11. Delete Column (del_col)\r\n\r\nDelete specified columns.\r\n\r\n**Parameters**:\r\n- `operator_id`: The unionId of the operator\r\n- `table_id`: The ID of the table, supports table URL input\r\n- `sheet_id`: Worksheet ID (choose one between sheet_id and sheet_name)\r\n- `sheet_name`: Worksheet name (choose one between sheet_id and sheet_name)\r\n- `start_col`: Starting column, such as 'A', 'B', etc.\r\n- `col_count`: Number of columns to delete\r\n\r\n**Example**:\r\n```python\r\n# Delete columns from column B to column D\r\n\r\n{\r\n  \"operator_id\": \"your_operator_id\",\r\n  \"table_id\": \"URL_ADDRESSocs.dingtalk.com/i/nodes/AbCdEfGh\",\r\n  \"sheet_id\": \"your_sheet_id\",\r\n  \"sheet_name\": \"Sales Data\",\r\n  \"start_col\": \"B\",\r\n  \"col_count\": 2\r\n}\r\n```\r\n**Returns**:\r\n- JSON data of the operation result\r\n\r\n## Contact Us\r\nIf you have any questions or suggestions about this, please contact us through the following methods:\r\n- https://github.com/witmeng/dify_plugin\r\n- Email：myspsp@gmail.com",
        "label": {
          "en_US": "Dingtalk Spreadsheet",
          "ja_JP": "钉钉电子表格",
          "pt_BR": "Dingtalk Spreadsheet",
          "zh_Hans": "钉钉电子表格"
        },
        "latest_package_identifier": "witmeng/dingtalk_spreadsheet:0.0.2@f4aebd9e84bc75725a7ae2dbe1d67ff958c1e6455a0e6f916b6bf32535173746",
        "latest_version": "0.0.2",
        "model": {},
        "name": "dingtalk_spreadsheet",
        "org": "witmeng",
        "plugin_id": "witmeng/dingtalk_spreadsheet",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/dingtalk_spreadsheet.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "utilities"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Get your Client ID and Client Secret from DingTalk",
                "zh_Hans": "从钉钉开放平台获取您应用的 Client ID 和 Client Secret"
              },
              "label": {
                "en_US": "Client ID"
              },
              "name": "app_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your DingTalk Client id",
                "zh_Hans": "请输入你的钉钉 Client ID"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": "https://open-dev.dingtalk.com/fe/app"
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Client Secret"
              },
              "name": "app_secret",
              "options": null,
              "placeholder": {
                "en_US": "Please input your DingTalk Client secret",
                "zh_Hans": "请输入你的钉钉 Client secret"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            }
          ],
          "identity": {
            "author": "Huthu-Meng",
            "description": {
              "en_US": "DingTalk Spreadsheet, requires the following permissions: dingtalk-document, user/get. qyapi_get_member_by_mobile",
              "zh_Hans": "釘釘电子表格，需要开通以下权限: 钉钉表格权限，个人信息, 根据手机号获取成员基本信息权限；登录钉钉开发者后台 > 企业内部开发 > 找到需添加权限的应用 > 权限管理 > 通讯录管理页面，勾选企业员工手机号信息和邮箱等个人信息，单击申请权限。"
            },
            "icon": "ding.png",
            "label": {
              "en_US": "Dingtalk Spreadsheet",
              "zh_Hans": "钉钉电子表格"
            },
            "name": "dingtalk_spreadsheet",
            "tags": [
              "utilities",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Create Sheet",
                  "zh_Hans": "创建工作表"
                },
                "llm": "A tool for creating Sheet. (创建工作表)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Wit Meng",
                "label": {
                  "en_US": "Create Sheet",
                  "zh_Hans": "创建工作表Sheet"
                },
                "name": "create_sheet"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The title of the sheet",
                    "zh_Hans": "工作表的标题"
                  },
                  "label": {
                    "en_US": "sheet Title",
                    "zh_Hans": "工作表的标题"
                  },
                  "llm_description": "工作表的标题",
                  "max": null,
                  "min": null,
                  "name": "title",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "the unionId of Operator",
                    "zh_Hans": "操作人的unionId"
                  },
                  "label": {
                    "en_US": "the unionId",
                    "zh_Hans": "操作人的unionId"
                  },
                  "llm_description": "操作人的unionId",
                  "max": null,
                  "min": null,
                  "name": "operator_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the table, supports table URL input, e.g., https://alidocs.dingtalk.com/i/nodes/XXXXSlNkL2dUTCJcPRgentXXX",
                    "zh_Hans": "表格的ID，支持表格 URL 输入，如：https://alidocs.dingtalk.com/i/nodes/XXXXSlNkL2dUTCJcPRgentXXX"
                  },
                  "label": {
                    "en_US": "Table ID",
                    "zh_Hans": "表格的链接"
                  },
                  "llm_description": "表格的ID，支持表格 URL 输入，如：https://alidocs.dingtalk.com/i/nodes/XXXXSlNkL2dUTCJcPRgentXXX",
                  "max": null,
                  "min": null,
                  "name": "table_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get Sheet information",
                  "zh_Hans": "读取工作表信息"
                },
                "llm": "A tool for Get Sheet information. (读取工作表信息)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Wit Meng",
                "label": {
                  "en_US": "Get Sheet information",
                  "zh_Hans": "读取工作表信息"
                },
                "name": "read_sheet"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "the unionId of Operator",
                    "zh_Hans": "操作人的unionId"
                  },
                  "label": {
                    "en_US": "the unionId",
                    "zh_Hans": "操作人的unionId"
                  },
                  "llm_description": "操作人的unionId",
                  "max": null,
                  "min": null,
                  "name": "operator_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the table, supports table URL input, e.g., https://alidocs.dingtalk.com/i/nodes/XXXXSlNkL2dUTCJcPRgentXXX",
                    "zh_Hans": "表格的ID，支持表格 URL 输入，如：https://alidocs.dingtalk.com/i/nodes/XXXXSlNkL2dUTCJcPRgentXXX"
                  },
                  "label": {
                    "en_US": "Table ID",
                    "zh_Hans": "表格的链接"
                  },
                  "llm_description": "表格的ID，支持表格 URL 输入，如：https://alidocs.dingtalk.com/i/nodes/XXXXSlNkL2dUTCJcPRgentXXX",
                  "max": null,
                  "min": null,
                  "name": "table_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet ID, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表 ID，与 sheet_name 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_id",
                    "zh_Hans": "工作表 ID"
                  },
                  "llm_description": "工作表 ID，与 sheet_name 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet name, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表名称，与 sheet_id 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_name",
                    "zh_Hans": "工作表名称"
                  },
                  "llm_description": "工作表名称，与 sheet_id 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "List Spreadsheet Sheets",
                  "zh_Hans": "列出电子表格所有工作表"
                },
                "llm": "A tool for listing all sheets in a spreadsheet. (列出电子表格所有工作表)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Wit Meng",
                "label": {
                  "en_US": "List Spreadsheet Sheets",
                  "zh_Hans": "列出电子表格所有工作表"
                },
                "name": "read_table"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "the unionId of Operator",
                    "zh_Hans": "操作人的unionId"
                  },
                  "label": {
                    "en_US": "the unionId",
                    "zh_Hans": "操作人的unionId"
                  },
                  "llm_description": "操作人的unionId",
                  "max": null,
                  "min": null,
                  "name": "operator_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Spreadsheet ID or URL, e.g., XXXXSlNkL2dUTCJcPRgentXXX or https://alidocs.dingtalk.com/i/nodes/XXXXSlNkL2dUTCJcPRgentXXX",
                    "zh_Hans": "电子表格的ID或者URL，如：XXXXSlNkL2dUTCJcPRgentXXX或者https://alidocs.dingtalk.com/i/nodes/XXXXSlNkL2dUTCJcPRgentXXX"
                  },
                  "label": {
                    "en_US": "Spreadsheet ID or URL",
                    "zh_Hans": "表格的ID或者URL"
                  },
                  "llm_description": "电子表格的ID或者URL，如：XXXXSlNkL2dUTCJcPRgentXXX或者https://alidocs.dingtalk.com/i/nodes/XXXXSlNkL2dUTCJcPRgentXXX",
                  "max": null,
                  "min": null,
                  "name": "table_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Insert Data Before the Row",
                  "zh_Hans": "指定行向上新增多行数据"
                },
                "llm": "A tool for Insert Data Before the Row（multiple rows） (指定行向上新增多行数据)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Wit Meng",
                "label": {
                  "en_US": "Insert Data Before the Row",
                  "zh_Hans": "指定行向上新增多行数据"
                },
                "name": "insert_data_befor_row"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "the unionId of Operator",
                    "zh_Hans": "操作人的unionId"
                  },
                  "label": {
                    "en_US": "the unionId",
                    "zh_Hans": "操作人的unionId"
                  },
                  "llm_description": "操作人的unionId",
                  "max": null,
                  "min": null,
                  "name": "operator_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Spreadsheet ID or URL, e.g., XXXXSlNkL2dUTCJcPRgentXXX or https://alidocs.dingtalk.com/i/nodes/XXXXSlNkL2dUTCJcPRgentXXX",
                    "zh_Hans": "电子表格的ID或者URL，如：XXXXSlNkL2dUTCJcPRgentXXX或者https://alidocs.dingtalk.com/i/nodes/XXXXSlNkL2dUTCJcPRgentXXX"
                  },
                  "label": {
                    "en_US": "Spreadsheet ID or URL",
                    "zh_Hans": "表格的ID或者URL"
                  },
                  "llm_description": "电子表格的ID或者URL，如：XXXXSlNkL2dUTCJcPRgentXXX或者https://alidocs.dingtalk.com/i/nodes/XXXXSlNkL2dUTCJcPRgentXXX",
                  "max": null,
                  "min": null,
                  "name": "table_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet ID, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表 ID，与 sheet_name 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_id",
                    "zh_Hans": "工作表 ID"
                  },
                  "llm_description": "工作表 ID，与 sheet_name 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet name, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表名称，与 sheet_id 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_name",
                    "zh_Hans": "工作表名称"
                  },
                  "llm_description": "工作表名称，与 sheet_id 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "the Row number",
                    "zh_Hans": "指定的行号"
                  },
                  "label": {
                    "en_US": "the Row number",
                    "zh_Hans": "指定的行号"
                  },
                  "llm_description": "指定具体的行号",
                  "max": null,
                  "min": null,
                  "name": "start_row",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "the Count of Rows, 0 means automatic calculation",
                    "zh_Hans": "增加行数,0表示根据数据自动计算"
                  },
                  "label": {
                    "en_US": "the Count of Rows",
                    "zh_Hans": "增加行数"
                  },
                  "llm_description": "增加行数",
                  "max": null,
                  "min": null,
                  "name": "row_count",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "the Column code",
                    "zh_Hans": "数据指定列号（A-ZZ）"
                  },
                  "label": {
                    "en_US": "the Column code",
                    "zh_Hans": "数据指定列号（A-ZZ）"
                  },
                  "llm_description": "从指定的列开始更新数据",
                  "max": null,
                  "min": null,
                  "name": "start_col",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Content of the new rows, array of objects in string format, each array represents a row of table data, format like: [ [ \"ID\",\"Name\",\"Age\" ],[ 1,\"Zhang San\",10 ],[ 2,\"Li Si\",11 ] ].\n",
                    "zh_Hans": "新增行的表格内容，数组对象字符串，每个数组一行表格数据，格式,如：[[\"编号\",\"姓名\",\"年龄\"],[1,\"张三\",10],[2,\"李四\",11]]。"
                  },
                  "label": {
                    "en_US": "values",
                    "zh_Hans": "插入表格的内容"
                  },
                  "llm_description": "新增行的表格内容，数组对象字符串，每个数组一行表格数据，格式,如：[[\"编号\",\"姓名\",\"年龄\"],[1,\"张三\",10],[2,\"李四\",11]]。",
                  "max": null,
                  "min": null,
                  "name": "values",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Insert Data Before the Column",
                  "zh_Hans": "指定列向前新增多列数据"
                },
                "llm": "A tool for Insert Data Before the Column（multiple columns） (指定列向前新增多列数据)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Wit Meng",
                "label": {
                  "en_US": "Insert Data Before the Column",
                  "zh_Hans": "指定列向前新增多列数据"
                },
                "name": "insert_data_befor_col"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "the unionId of Operator",
                    "zh_Hans": "操作人的unionId"
                  },
                  "label": {
                    "en_US": "the unionId",
                    "zh_Hans": "操作人的unionId"
                  },
                  "llm_description": "操作人的unionId",
                  "max": null,
                  "min": null,
                  "name": "operator_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Spreadsheet ID or URL, e.g., XXXXSlNkL2dUTCJcPRgentXXX or https://alidocs.dingtalk.com/i/nodes/XXXXSlNkL2dUTCJcPRgentXXX",
                    "zh_Hans": "电子表格的ID或者URL，如：XXXXSlNkL2dUTCJcPRgentXXX或者https://alidocs.dingtalk.com/i/nodes/XXXXSlNkL2dUTCJcPRgentXXX"
                  },
                  "label": {
                    "en_US": "Spreadsheet ID or URL",
                    "zh_Hans": "表格的ID或者URL"
                  },
                  "llm_description": "电子表格的ID或者URL，如：XXXXSlNkL2dUTCJcPRgentXXX或者https://alidocs.dingtalk.com/i/nodes/XXXXSlNkL2dUTCJcPRgentXXX",
                  "max": null,
                  "min": null,
                  "name": "table_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet ID, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表 ID，与 sheet_name 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_id",
                    "zh_Hans": "工作表 ID"
                  },
                  "llm_description": "工作表 ID，与 sheet_name 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet name, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表名称，与 sheet_id 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_name",
                    "zh_Hans": "工作表名称"
                  },
                  "llm_description": "工作表名称，与 sheet_id 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "the Column code, e.g., A, B, AA, AB, ZZ",
                    "zh_Hans": "指定的列号,例如： A, B, AA, AB, ZZ"
                  },
                  "label": {
                    "en_US": "the Column code",
                    "zh_Hans": "指定的列号"
                  },
                  "llm_description": "指定具体的行号",
                  "max": null,
                  "min": null,
                  "name": "start_col",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "the Count of Columns, 0 means automatic calculation",
                    "zh_Hans": "增加列数, 0表示根据数据自动计算"
                  },
                  "label": {
                    "en_US": "the Count of Columns",
                    "zh_Hans": "增加列数"
                  },
                  "llm_description": "增加列数",
                  "max": null,
                  "min": null,
                  "name": "col_count",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "the row number",
                    "zh_Hans": "数据插入行号（>0）"
                  },
                  "label": {
                    "en_US": "the row number",
                    "zh_Hans": "数据插入行号（>0）"
                  },
                  "llm_description": "从指定的行始更新数据",
                  "max": null,
                  "min": null,
                  "name": "start_row",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Content of the new rows, array of objects in string format, each array represents a row of table data, format like: [ [ \"ID\",\"Name\",\"Age\" ],[ 1,\"Zhang San\",10 ],[ 2,\"Li Si\",11 ] ].\n",
                    "zh_Hans": "新增行的表格内容，数组对象字符串，每个数组一行表格数据，格式,如：[[\"编号\",\"姓名\",\"年龄\"],[1,\"张三\",10],[2,\"李四\",11]]。"
                  },
                  "label": {
                    "en_US": "values",
                    "zh_Hans": "插入表格的内容"
                  },
                  "llm_description": "新增行的表格内容，数组对象字符串，每个数组一行表格数据，格式,如：[[\"编号\",\"姓名\",\"年龄\"],[1,\"张三\",10],[2,\"李四\",11]]。",
                  "max": null,
                  "min": null,
                  "name": "values",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Del column",
                  "zh_Hans": "删除列"
                },
                "llm": "A tool for Del column. (删除列)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Wit Meng",
                "label": {
                  "en_US": "Del column",
                  "zh_Hans": "删除列"
                },
                "name": "del_col"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "the unionId of Operator",
                    "zh_Hans": "操作人的unionId"
                  },
                  "label": {
                    "en_US": "the unionId",
                    "zh_Hans": "操作人的unionId"
                  },
                  "llm_description": "操作人的unionId",
                  "max": null,
                  "min": null,
                  "name": "operator_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the table, supports table URL input, e.g., https://alidocs.dingtalk.com/i/nodes/XXXXSlNkL2dUTCJcPRgentXXX",
                    "zh_Hans": "表格的ID，支持表格 URL 输入，如：https://alidocs.dingtalk.com/i/nodes/XXXXSlNkL2dUTCJcPRgentXXX"
                  },
                  "label": {
                    "en_US": "Table ID",
                    "zh_Hans": "表格的链接"
                  },
                  "llm_description": "表格的ID，支持表格 URL 输入，如：https://alidocs.dingtalk.com/i/nodes/XXXXSlNkL2dUTCJcPRgentXXX",
                  "max": null,
                  "min": null,
                  "name": "table_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet ID, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表 ID，与 sheet_name 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_id",
                    "zh_Hans": "工作表 ID"
                  },
                  "llm_description": "工作表 ID，与 sheet_name 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet name, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表名称，与 sheet_id 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_name",
                    "zh_Hans": "工作表名称"
                  },
                  "llm_description": "工作表名称，与 sheet_id 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "the Column code, e.g., A, B, AA, AB, ZZ",
                    "zh_Hans": "指定的起始列号,例如： A, B, AA, AB, ZZ"
                  },
                  "label": {
                    "en_US": "the Column code",
                    "zh_Hans": "起始列号"
                  },
                  "llm_description": "起始列号",
                  "max": null,
                  "min": null,
                  "name": "start_col",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "the Count of Columns for delete, 0 means not delete",
                    "zh_Hans": "删除列数, 0表示不删除"
                  },
                  "label": {
                    "en_US": "Counts of Columns for delete",
                    "zh_Hans": "删除列数"
                  },
                  "llm_description": "删除列数",
                  "max": null,
                  "min": null,
                  "name": "col_count",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Del row",
                  "zh_Hans": "删除行"
                },
                "llm": "A tool for Del row. (删除行)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Wit Meng",
                "label": {
                  "en_US": "Del row",
                  "zh_Hans": "删除行"
                },
                "name": "del_row"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "the unionId of Operator",
                    "zh_Hans": "操作人的unionId"
                  },
                  "label": {
                    "en_US": "the unionId",
                    "zh_Hans": "操作人的unionId"
                  },
                  "llm_description": "操作人的unionId",
                  "max": null,
                  "min": null,
                  "name": "operator_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the table, supports table URL input, e.g., https://alidocs.dingtalk.com/i/nodes/XXXXSlNkL2dUTCJcPRgentXXX",
                    "zh_Hans": "表格的ID，支持表格 URL 输入，如：https://alidocs.dingtalk.com/i/nodes/XXXXSlNkL2dUTCJcPRgentXXX"
                  },
                  "label": {
                    "en_US": "Table ID",
                    "zh_Hans": "表格的链接"
                  },
                  "llm_description": "表格的ID，支持表格 URL 输入，如：https://alidocs.dingtalk.com/i/nodes/XXXXSlNkL2dUTCJcPRgentXXX",
                  "max": null,
                  "min": null,
                  "name": "table_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet ID, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表 ID，与 sheet_name 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_id",
                    "zh_Hans": "工作表 ID"
                  },
                  "llm_description": "工作表 ID，与 sheet_name 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet name, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表名称，与 sheet_id 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_name",
                    "zh_Hans": "工作表名称"
                  },
                  "llm_description": "工作表名称，与 sheet_id 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "the row index, e.g., 1, 2, 3",
                    "zh_Hans": "指定起始行号，例如： 1, 2, 3"
                  },
                  "label": {
                    "en_US": "the row index",
                    "zh_Hans": "行号"
                  },
                  "llm_description": "指定行起始行号，例如： 1, 2, 3",
                  "max": null,
                  "min": null,
                  "name": "start_row",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "the Count of rows for delete, 0 means not delete",
                    "zh_Hans": "删除行数, 0表示不删除"
                  },
                  "label": {
                    "en_US": "Counts of rows for delete",
                    "zh_Hans": "删除行数"
                  },
                  "llm_description": "删除行数",
                  "max": null,
                  "min": null,
                  "name": "row_count",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get Cells content",
                  "zh_Hans": "读取单元格信息"
                },
                "llm": "A tool for Get the cells content. (读取单元格信息)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Wit Meng",
                "label": {
                  "en_US": "Get Cells content",
                  "zh_Hans": "读取单元格信息"
                },
                "name": "read_area"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "the unionId of Operator",
                    "zh_Hans": "操作人的unionId"
                  },
                  "label": {
                    "en_US": "the unionId",
                    "zh_Hans": "操作人的unionId"
                  },
                  "llm_description": "操作人的unionId",
                  "max": null,
                  "min": null,
                  "name": "operator_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the table, supports table URL input, e.g., https://alidocs.dingtalk.com/i/nodes/XXXXSlNkL2dUTCJcPRgentXXX",
                    "zh_Hans": "表格的ID，支持表格 URL 输入，如：https://alidocs.dingtalk.com/i/nodes/XXXXSlNkL2dUTCJcPRgentXXX"
                  },
                  "label": {
                    "en_US": "Table ID",
                    "zh_Hans": "表格的链接"
                  },
                  "llm_description": "表格的ID，支持表格 URL 输入，如：https://alidocs.dingtalk.com/i/nodes/XXXXSlNkL2dUTCJcPRgentXXX",
                  "max": null,
                  "min": null,
                  "name": "table_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet ID, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表 ID，与 sheet_name 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_id",
                    "zh_Hans": "工作表 ID"
                  },
                  "llm_description": "工作表 ID，与 sheet_name 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet name, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表名称，与 sheet_id 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_name",
                    "zh_Hans": "工作表名称"
                  },
                  "llm_description": "工作表名称，与 sheet_id 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The area of the table, e.g., A1:B2",
                    "zh_Hans": "表格的区域，如：A1:B2"
                  },
                  "label": {
                    "en_US": "area",
                    "zh_Hans": "表格的区域"
                  },
                  "llm_description": "表格的区域，如：A1:B2",
                  "max": null,
                  "min": null,
                  "name": "area",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Update Cells content",
                  "zh_Hans": "更新单元格信息"
                },
                "llm": "A tool for update the cells content. (读取单元格信息)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Wit Meng",
                "label": {
                  "en_US": "update Cells content",
                  "zh_Hans": "更新单元格信息"
                },
                "name": "update_area"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "the unionId of Operator",
                    "zh_Hans": "操作人的unionId"
                  },
                  "label": {
                    "en_US": "the unionId",
                    "zh_Hans": "操作人的unionId"
                  },
                  "llm_description": "操作人的unionId",
                  "max": null,
                  "min": null,
                  "name": "operator_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the table, supports table URL input, e.g., https://alidocs.dingtalk.com/i/nodes/XXXXSlNkL2dUTCJcPRgentXXX",
                    "zh_Hans": "表格的ID，支持表格 URL 输入，如：https://alidocs.dingtalk.com/i/nodes/XXXXSlNkL2dUTCJcPRgentXXX"
                  },
                  "label": {
                    "en_US": "Table ID",
                    "zh_Hans": "表格的链接"
                  },
                  "llm_description": "表格的ID，支持表格 URL 输入，如：https://alidocs.dingtalk.com/i/nodes/XXXXSlNkL2dUTCJcPRgentXXX",
                  "max": null,
                  "min": null,
                  "name": "table_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet ID, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表 ID，与 sheet_name 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_id",
                    "zh_Hans": "工作表 ID"
                  },
                  "llm_description": "工作表 ID，与 sheet_name 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet name, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表名称，与 sheet_id 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_name",
                    "zh_Hans": "工作表名称"
                  },
                  "llm_description": "工作表名称，与 sheet_id 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The area of the table, e.g., A1:B2",
                    "zh_Hans": "表格的区域，如：A1:B2"
                  },
                  "label": {
                    "en_US": "area",
                    "zh_Hans": "表格的区域"
                  },
                  "llm_description": "表格的区域，如：A1:B2",
                  "max": null,
                  "min": null,
                  "name": "area",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Content of the new rows, array of objects in string format, each array represents a row of table data, format like: [ [ \"ID\",\"Name\",\"Age\" ],[ 1,\"Zhang San\",10 ],[ 2,\"Li Si\",11 ] ].\n",
                    "zh_Hans": "新增行的表格内容，数组对象字符串，每个数组一行表格数据，格式,如：[[\"编号\",\"姓名\",\"年龄\"],[1,\"张三\",10],[2,\"李四\",11]]。"
                  },
                  "label": {
                    "en_US": "values",
                    "zh_Hans": "插入表格的内容"
                  },
                  "llm_description": "新增行的表格内容，数组对象字符串，每个数组一行表格数据，格式,如：[[\"编号\",\"姓名\",\"年龄\"],[1,\"张三\",10],[2,\"李四\",11]]。",
                  "max": null,
                  "min": null,
                  "name": "values",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Clear Cells content",
                  "zh_Hans": "删除单元格信息"
                },
                "llm": "A tool for Clear the cells content. (读取单元格信息)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Wit Meng",
                "label": {
                  "en_US": "Clear Cells content",
                  "zh_Hans": "清除单元格信息"
                },
                "name": "clear_area"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "the unionId of Operator",
                    "zh_Hans": "操作人的unionId"
                  },
                  "label": {
                    "en_US": "the unionId",
                    "zh_Hans": "操作人的unionId"
                  },
                  "llm_description": "操作人的unionId",
                  "max": null,
                  "min": null,
                  "name": "operator_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the table, supports table URL input, e.g., https://alidocs.dingtalk.com/i/nodes/XXXXSlNkL2dUTCJcPRgentXXX",
                    "zh_Hans": "表格的ID，支持表格 URL 输入，如：https://alidocs.dingtalk.com/i/nodes/XXXXSlNkL2dUTCJcPRgentXXX"
                  },
                  "label": {
                    "en_US": "Table ID",
                    "zh_Hans": "表格的链接"
                  },
                  "llm_description": "表格的ID，支持表格 URL 输入，如：https://alidocs.dingtalk.com/i/nodes/XXXXSlNkL2dUTCJcPRgentXXX",
                  "max": null,
                  "min": null,
                  "name": "table_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet ID, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表 ID，与 sheet_name 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_id",
                    "zh_Hans": "工作表 ID"
                  },
                  "llm_description": "工作表 ID，与 sheet_name 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sheet name, either sheet_id or sheet_name must be filled.",
                    "zh_Hans": "工作表名称，与 sheet_id 二者其一必填。"
                  },
                  "label": {
                    "en_US": "sheet_name",
                    "zh_Hans": "工作表名称"
                  },
                  "llm_description": "工作表名称，与 sheet_id 二者其一必填。",
                  "max": null,
                  "min": null,
                  "name": "sheet_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The area of the table, e.g., A1:B2",
                    "zh_Hans": "表格的区域，如：A1:B2"
                  },
                  "label": {
                    "en_US": "area",
                    "zh_Hans": "表格的区域"
                  },
                  "llm_description": "表格的区域，如：A1:B2",
                  "max": null,
                  "min": null,
                  "name": "area",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get the UNION ID of Operator, by user id or mobile, need permission： qyapi_get_member_by_mobile, qyapi_get_member",
                  "zh_Hans": "获取操作人UNION ID，通过钉钉ID或手机号获取，需要开权限：qyapi_get_member_by_mobile， qyapi_get_member"
                },
                "llm": "A tool for getting the unionId of the operator. (获取操作人的unionId)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Wit Meng",
                "label": {
                  "en_US": "Get Operator UNION ID",
                  "zh_Hans": "获取操作人的UNION ID"
                },
                "name": "get_operator_id"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The user id of the operator",
                    "zh_Hans": "操作人的钉钉ID userId （钉钉ID和手机号二选一）"
                  },
                  "label": {
                    "en_US": "user id",
                    "zh_Hans": "钉钉userId"
                  },
                  "llm_description": "操作人的钉钉ID",
                  "max": null,
                  "min": null,
                  "name": "user_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The mobile of user, such as +86 13800138000",
                    "zh_Hans": "操作人的手机号 例如：+86 13800138000 （钉钉ID和手机号二选一）"
                  },
                  "label": {
                    "en_US": "mobile",
                    "zh_Hans": "钉钉手机号"
                  },
                  "llm_description": "操作人的手机号",
                  "max": null,
                  "min": null,
                  "name": "mobile",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-10T14:00:13Z",
        "version_updated_at": "2025-04-10T14:00:13Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Kafka management service, send Topic messages",
          "ja_JP": "Kafka management service, send Topic messages",
          "pt_BR": "Kafka management service, send Topic messages",
          "zh_Hans": "Kafka 管理服务, 发送Topic消息"
        },
        "category": "tool",
        "created_at": "2025-03-31T08:03:26Z",
        "endpoint": {},
        "icon": "lework/packages/kafka/_assets/icon.svg",
        "index_id": "lework___kafka",
        "install_count": 181,
        "introduction": "## Kafka plugin\n\n**Author:** lework\n**Version:** 0.0.1\n**Type:** tool\n**REPO:** [dify-plugin-kafka](https://github.com/lework/dify-plugin-kafka)\n\n### Description\n\nThe Kafka plugin is used to send messages to Kafka topics, supports maintaining long connections to Kafka instances, and automatically reconnects when the connection is lost. Supports connecting to multiple different Kafka instances at the same time, including Kafka services that require SASL authentication.\n\n### Features\n\n- Send messages to the specified Kafka topic\n- Support for partition routing by specifying message key\n- Maintain Kafka Producer long connection\n- Automatically retry when connection fails\n- Support SASL/SSL secure connection\n- **Support connecting to multiple different Kafka clusters**\n- **Support dynamically specifying SASL authentication information**\n\n### Configuration parameters\n\n#### Connection credentials\n\n- **Bootstrap Servers** (required): Kafka server address, such as `broker1:9092,broker2:9092`\n- **Security Protocol** (optional): Security protocol, optional values: PLAINTEXT, SSL, SASL_PLAINTEXT, SASL_SSL\n- **SASL Mechanism** (optional): SASL authentication mechanism, optional values: PLAIN, SCRAM-SHA-256, SCRAM-SHA-512\n- **SASL Username** (optional): SASL username\n- **SASL Password** (optional): SASL password\n\n#### Tool parameters\n\n- **Topic** (required): Kafka topic name to send messages\n\n- **Message** (required): Message content to send\n\n- **Key** (optional): Message key, used for partition routing\n\n- **Bootstrap Servers** (optional): Specific Kafka server address, overwriting the configuration in the credentials\n\n- **Security Protocol** (optional): Specific security protocol, overwriting the configuration in the credentials\n\n- **SASL Mechanism** (optional): Specific SASL mechanism, overwriting the configuration in the credentials\n\n- **SASL Username** (optional): Specific SASL username, used with SASL Password\n\n- **SASL Password** (optional): Specific SASL password, used with SASL Username\n\n### Secure connection configuration\n\n#### Basic security configuration\n\nFor Kafka services that require secure connections, you can set the following parameters:\n\n```\nSecurity Protocol: SASL_SSL\nSASL Mechanism: PLAIN (or SCRAM-SHA-256, SCRAM-SHA-512)\nSASL Username: your_username\nSASL Password: your_password\n```\n\n#### Important Notes\n\n1. When the SASL username and password are configured, the plug-in automatically checks the security protocol settings. If it is not set to a protocol starting with SASL\\_, it will automatically adjust to SASL_SSL.\n2. If the SASL username and password are configured but the SASL mechanism is not specified, the PLAIN mechanism will be used by default.\n3. When customizing the server address, the original security configuration (including SASL authentication information) will be retained by default.\n4. Both the server address and SASL authentication information can be overwritten in the tool parameters.\n\n#### Example configuration\n\nConfluent Cloud cluster connection example:\n\n```\nBootstrap Servers: pkc-xxxxx.region.aws.confluent.cloud:9092\nSecurity Protocol: SASL_SSL\nSASL Mechanism: PLAIN\nSASL Username: your_api_key\nSASL Password: your_api_secret\n```\n\nSelf-hosted Kafka cluster SCRAM authentication example:\n\n```\nBootstrap Servers: kafka1:9093,kafka2:9093\nSecurity Protocol: SASL_SSL\nSASL Mechanism: SCRAM-SHA-256\nSASL Username: your_username\nSASL Password: your_password\n```\n\n### Connect to multiple Kafka instances\n\nThis plugin supports connecting to multiple different Kafka instances in the Dify application. There are two ways to achieve this:\n\n#### Method 1: Specify custom connection parameters in tool parameters\n\nWhen calling the tool, you can specify specific Kafka connection information through parameters, which will override the configuration in the plugin credentials. For example:\n\n```\nSend the message \"Hello, Kafka!\" to the Kafka topic \"test-topic\" using the server \"dev-kafka:9092\"\n```\n\nUsing this method, you can send messages to different Kafka clusters in the same process without creating a separate plugin configuration for each cluster.\n\n##### Custom SASL authentication information\n\nYou can also specify specific SASL authentication information when calling:\n\n```\nSend the message \"Hello, Secure Kafka!\" to the Kafka topic \"secure-topic\", using the server \"secure-kafka:9093\", the security protocol \"SASL_SSL\", the SASL mechanism \"PLAIN\", the SASL username \"admin\", and the SASL password \"admin-secret\"\n```\n\n**Note**: If you specify both the SASL username and password, you must ensure that the security protocol settings are compatible (starting with SASL\\_), otherwise the plugin will automatically adjust the security protocol to SASL_SSL.\n\n##### Partially overwrite the configuration\n\nYou can overwrite only some of the connection information, leaving other parameters unchanged:\n\n```\nSend message \"Hello, Kafka!\" to Kafka topic \"test-topic\", using server \"new-kafka:9092\" // Overwrite only the server address\n```\n\n```\nSend message \"Hello, Kafka!\" to Kafka topic \"test-topic\", SASL username \"new-user\", SASL password \"new-password\" // Overwrite only the authentication information\n```\n\n#### Method 2: Configure multiple plugins for different environments\n\nAnother method is to create multiple Kafka plugin configurations for different environments, each with different credentials. For example, you can create three different plugin instances:\n\n1. Kafka-Dev: Configured to connect to the development environment (bootstrap.servers: dev-kafka:9092)\n\n2. Kafka-Test: Configured to connect to the test environment (bootstrap.servers: test-kafka:9092)\n\n3. Kafka-Prod: Configured to connect to the production environment, using SASL authentication (bootstrap.servers: prod-kafka:9092)\n\n### Example Usage\n\nIn the Dify application, you can call the tool in the following format:\n\n```\nSend the message \"Hello, Kafka!\" to the Kafka topic \"test-topic\"\n```\n\nUse a custom server:\n\n```\nSend the message \"Hello, Kafka!\" to the Kafka topic \"test-topic\", using the server \"custom-kafka:9092\"\n```\n\nUse custom SASL authentication:\n\n```\nSend the message \"Hello, Kafka!\" to the Kafka topic \"test-topic\", using the server \"custom-kafka:9092\"\n```\n\nUse custom SASL authentication:\n\n```\nSend the message \"Hello, Kafka!\" to the Kafka topic \"test-topic\", using the server \"custom-kafka:9092\" Topic \"secure-topic\" sends message \"Hello, Secure Kafka!\", using server \"secure-kafka:9093\", security protocol \"SASL_SSL\", SASL mechanism \"PLAIN\", SASL username \"admin\", SASL password \"admin-secret\"\n```\n\nComplete example:\n\n```\nSend message \"{\"user_id\": 123, \"action\": \"login\"}\" to Kafka topic \"user-events\", using key \"user123\", using server \"prod-kafka:9092,prod-kafka2:9092\"\n```\n\n### Development and debugging\n\n```bash\n# Install dependencies\npip install -r requirements.txt\n\n# Run debug\npython -m main\n\n# Package plugin\ndify plugin package ./kafka\n```\n",
        "label": {
          "en_US": "Kafka",
          "ja_JP": "Kafka",
          "pt_BR": "Kafka",
          "zh_Hans": "Kafka"
        },
        "latest_package_identifier": "lework/kafka:0.0.1@2778f9c8a388dd19520c8074f88a311e2e8613e421e39c70dfc70b973aedc29d",
        "latest_version": "0.0.1",
        "model": {},
        "name": "kafka",
        "org": "lework",
        "plugin_id": "lework/kafka",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/kafka.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "model": {
              "enabled": true,
              "llm": false,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Comma-separated list of Kafka brokers",
                "pt_BR": "Comma-separated list of Kafka brokers",
                "zh_Hans": "逗号分隔的Kafka代理服务器列表"
              },
              "label": {
                "en_US": "Bootstrap Servers",
                "pt_BR": "Bootstrap Servers",
                "zh_Hans": "引导服务器"
              },
              "name": "bootstrap.servers",
              "options": null,
              "placeholder": {
                "en_US": "broker1:9092,broker2:9092",
                "pt_BR": "broker1:9092,broker2:9092",
                "zh_Hans": "broker1:9092,broker2:9092"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://docs.confluent.io/kafka-clients/python/current/overview.html"
            },
            {
              "default": null,
              "help": {
                "en_US": "Protocol used to communicate with brokers",
                "pt_BR": "Protocol used to communicate with brokers",
                "zh_Hans": "与代理通信使用的协议"
              },
              "label": {
                "en_US": "Security Protocol",
                "pt_BR": "Security Protocol",
                "zh_Hans": "安全协议"
              },
              "name": "security.protocol",
              "options": [
                {
                  "label": {
                    "en_US": "PLAINTEXT",
                    "pt_BR": "PLAINTEXT",
                    "zh_Hans": "PLAINTEXT"
                  },
                  "value": "PLAINTEXT"
                },
                {
                  "label": {
                    "en_US": "SASL_PLAINTEXT",
                    "pt_BR": "SASL_PLAINTEXT",
                    "zh_Hans": "SASL_PLAINTEXT"
                  },
                  "value": "SASL_PLAINTEXT"
                },
                {
                  "label": {
                    "en_US": "SASL_SSL",
                    "pt_BR": "SASL_SSL",
                    "zh_Hans": "SASL_SSL"
                  },
                  "value": "SASL_SSL"
                }
              ],
              "placeholder": {
                "en_US": "PLAINTEXT",
                "pt_BR": "PLAINTEXT",
                "zh_Hans": "PLAINTEXT"
              },
              "required": false,
              "scope": null,
              "type": "select",
              "url": null
            },
            {
              "default": "PLAIN",
              "help": {
                "en_US": "SASL mechanism to use for authentication",
                "pt_BR": "SASL mechanism to use for authentication",
                "zh_Hans": "用于身份验证的SASL机制"
              },
              "label": {
                "en_US": "SASL Mechanism",
                "pt_BR": "SASL Mechanism",
                "zh_Hans": "SASL机制"
              },
              "name": "sasl.mechanism",
              "options": [
                {
                  "label": {
                    "en_US": "PLAIN",
                    "pt_BR": "PLAIN",
                    "zh_Hans": "PLAIN"
                  },
                  "value": "PLAIN"
                },
                {
                  "label": {
                    "en_US": "SCRAM-SHA-256",
                    "pt_BR": "SCRAM-SHA-256",
                    "zh_Hans": "SCRAM-SHA-256"
                  },
                  "value": "SCRAM-SHA-256"
                },
                {
                  "label": {
                    "en_US": "SCRAM-SHA-512",
                    "pt_BR": "SCRAM-SHA-512",
                    "zh_Hans": "SCRAM-SHA-512"
                  },
                  "value": "SCRAM-SHA-512"
                }
              ],
              "placeholder": null,
              "required": false,
              "scope": null,
              "type": "select",
              "url": null
            },
            {
              "default": null,
              "help": {
                "en_US": "SASL username for PLAIN and SCRAM authentication",
                "pt_BR": "SASL username for PLAIN and SCRAM authentication",
                "zh_Hans": "PLAIN和SCRAM认证的SASL用户名"
              },
              "label": {
                "en_US": "SASL Username",
                "pt_BR": "SASL Username",
                "zh_Hans": "SASL用户名"
              },
              "name": "sasl.username",
              "options": null,
              "placeholder": null,
              "required": false,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "help": {
                "en_US": "SASL password for PLAIN and SCRAM authentication",
                "pt_BR": "SASL password for PLAIN and SCRAM authentication",
                "zh_Hans": "PLAIN和SCRAM认证的SASL密码"
              },
              "label": {
                "en_US": "SASL Password",
                "pt_BR": "SASL Password",
                "zh_Hans": "SASL密码"
              },
              "name": "sasl.password",
              "options": null,
              "placeholder": null,
              "required": false,
              "scope": null,
              "type": "secret-input",
              "url": null
            }
          ],
          "identity": {
            "author": "lework",
            "description": {
              "en_US": "Send messages to Kafka topics",
              "pt_BR": "Send messages to Kafka topics",
              "zh_Hans": "向Kafka主题发送消息"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Kafka Producer",
              "pt_BR": "Kafka Producer",
              "zh_Hans": "Kafka生产者"
            },
            "name": "kafka",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Send message to Kafka topic",
                  "pt_BR": "Send message to Kafka topic",
                  "zh_Hans": "发送消息到Kafka主题"
                },
                "llm": "Send message to Kafka topic"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "lework",
                "label": {
                  "en_US": "kafka",
                  "pt_BR": "kafka",
                  "zh_Hans": "Kafka消息发送"
                },
                "name": "kafka"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Kafka topic name",
                    "pt_BR": "Kafka topic name",
                    "zh_Hans": "Kafka主题名称"
                  },
                  "label": {
                    "en_US": "Topic",
                    "pt_BR": "Topic",
                    "zh_Hans": "主题"
                  },
                  "llm_description": "Kafka topic name to send message to",
                  "max": null,
                  "min": null,
                  "name": "topic",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Message content to send",
                    "pt_BR": "Message content to send",
                    "zh_Hans": "要发送的消息内容"
                  },
                  "label": {
                    "en_US": "Message",
                    "pt_BR": "Message",
                    "zh_Hans": "消息内容"
                  },
                  "llm_description": "Message content to send to Kafka topic",
                  "max": null,
                  "min": null,
                  "name": "message",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional message key",
                    "pt_BR": "Optional message key",
                    "zh_Hans": "可选的消息键"
                  },
                  "label": {
                    "en_US": "Message Key",
                    "pt_BR": "Message Key",
                    "zh_Hans": "消息键"
                  },
                  "llm_description": "Optional message key for partitioning",
                  "max": null,
                  "min": null,
                  "name": "key",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Specific Kafka bootstrap servers, override credential setting",
                    "pt_BR": "Specific Kafka bootstrap servers, override credential setting",
                    "zh_Hans": "特定的Kafka服务器地址，覆盖凭证设置"
                  },
                  "label": {
                    "en_US": "Bootstrap Servers",
                    "pt_BR": "Bootstrap Servers",
                    "zh_Hans": "Kafka服务器"
                  },
                  "llm_description": "Optional bootstrap servers to override credential setting",
                  "max": null,
                  "min": null,
                  "name": "bootstrap_servers",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Security protocol to use (PLAINTEXT, SSL, SASL_PLAINTEXT, SASL_SSL)",
                    "pt_BR": "Security protocol to use (PLAINTEXT, SSL, SASL_PLAINTEXT, SASL_SSL)",
                    "zh_Hans": "使用的安全协议 (PLAINTEXT, SSL, SASL_PLAINTEXT, SASL_SSL)"
                  },
                  "label": {
                    "en_US": "Security Protocol",
                    "pt_BR": "Security Protocol",
                    "zh_Hans": "安全协议"
                  },
                  "llm_description": "Optional security protocol to override credential setting",
                  "max": null,
                  "min": null,
                  "name": "security_protocol",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "SASL mechanism to use (PLAIN, SCRAM-SHA-256, SCRAM-SHA-512)",
                    "pt_BR": "SASL mechanism to use (PLAIN, SCRAM-SHA-256, SCRAM-SHA-512)",
                    "zh_Hans": "使用的SASL机制 (PLAIN, SCRAM-SHA-256, SCRAM-SHA-512)"
                  },
                  "label": {
                    "en_US": "SASL Mechanism",
                    "pt_BR": "SASL Mechanism",
                    "zh_Hans": "SASL机制"
                  },
                  "llm_description": "Optional SASL mechanism to override credential setting",
                  "max": null,
                  "min": null,
                  "name": "sasl_mechanism",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "SASL username for authentication",
                    "pt_BR": "SASL username for authentication",
                    "zh_Hans": "SASL身份验证的用户名"
                  },
                  "label": {
                    "en_US": "SASL Username",
                    "pt_BR": "SASL Username",
                    "zh_Hans": "SASL用户名"
                  },
                  "llm_description": "Optional SASL username to override credential setting",
                  "max": null,
                  "min": null,
                  "name": "sasl_username",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "SASL password for authentication",
                    "pt_BR": "SASL password for authentication",
                    "zh_Hans": "SASL身份验证的密码"
                  },
                  "label": {
                    "en_US": "SASL Password",
                    "pt_BR": "SASL Password",
                    "zh_Hans": "SASL密码"
                  },
                  "llm_description": "Optional SASL password to override credential setting",
                  "max": null,
                  "min": null,
                  "name": "sasl_password",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-31T08:03:31Z",
        "version_updated_at": "2025-03-31T08:03:31Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Lark message and group, requires the following permissions: im:message、im:message.group_msg.\n",
          "zh_Hans": "Lark 消息和群组，需要开通以下权限: im:message、im:message.group_msg。\n"
        },
        "category": "tool",
        "created_at": "2025-02-26T10:39:08Z",
        "endpoint": {},
        "icon": "langgenius/packages/lark_message_and_group/_assets/icon.png",
        "index_id": "langgenius___lark_message_and_group",
        "install_count": 180,
        "introduction": "",
        "label": {
          "en_US": "Lark Message And Group",
          "zh_Hans": "Lark 消息和群组"
        },
        "latest_package_identifier": "langgenius/lark_message_and_group:0.0.1@034d7c0aae85d5a739ea0a4f2602b48e78be415c2218ef2c68e30972dbad9cc2",
        "latest_version": "0.0.1",
        "model": {},
        "name": "lark_message_and_group",
        "org": "langgenius",
        "plugin_id": "langgenius/lark_message_and_group",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/lark_message_and_group.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "social"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "APP ID"
              },
              "name": "app_id",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Lark app id",
                "zh_Hans": "请输入你的 Lark app id"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": "https://open.larksuite.com/app"
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "APP Secret"
              },
              "name": "app_secret",
              "options": null,
              "placeholder": {
                "en_US": "Please input your app secret",
                "zh_Hans": "请输入你的 Lark app secret"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            }
          ],
          "identity": {
            "author": "langgenius",
            "description": {
              "en_US": "Lark message and group, requires the following permissions: im:message、im:message.group_msg.\n",
              "zh_Hans": "Lark 消息和群组，需要开通以下权限: im:message、im:message.group_msg。\n"
            },
            "icon": "icon.png",
            "label": {
              "en_US": "Lark Message And Group",
              "zh_Hans": "Lark 消息和群组"
            },
            "name": "lark_message_and_group",
            "tags": [
              "social",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Send bot message",
                  "zh_Hans": "发送 Lark 应用消息"
                },
                "llm": "A tool for sending Lark application messages."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Send Bot Message",
                  "zh_Hans": "发送 Lark 应用消息"
                },
                "name": "send_bot_message"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the message receiver, the ID type is consistent with the value of the query parameter receive_id_type.",
                    "zh_Hans": "消息接收者的 ID，ID 类型与查询参数 receive_id_type 的取值一致。"
                  },
                  "label": {
                    "en_US": "receive_id",
                    "zh_Hans": "消息接收者的 ID"
                  },
                  "llm_description": "消息接收者的 ID，ID 类型与查询参数 receive_id_type 的取值一致。",
                  "max": null,
                  "min": null,
                  "name": "receive_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The ID type of the message receiver, optional values are open_id, union_id, user_id, email, chat_id, with a default value of open_id.",
                    "zh_Hans": "消息接收者的 ID 类型，可选值有 open_id、union_id、user_id、email、chat_id，默认值为 open_id。"
                  },
                  "label": {
                    "en_US": "receive_id_type",
                    "zh_Hans": "消息接收者的 ID 类型"
                  },
                  "llm_description": "消息接收者的 ID 类型，可选值有 open_id、union_id、user_id、email、chat_id，默认值为 open_id。",
                  "max": null,
                  "min": null,
                  "name": "receive_id_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "open_id",
                        "zh_Hans": "open_id"
                      },
                      "value": "open_id"
                    },
                    {
                      "label": {
                        "en_US": "union_id",
                        "zh_Hans": "union_id"
                      },
                      "value": "union_id"
                    },
                    {
                      "label": {
                        "en_US": "user_id",
                        "zh_Hans": "user_id"
                      },
                      "value": "user_id"
                    },
                    {
                      "label": {
                        "en_US": "email",
                        "zh_Hans": "email"
                      },
                      "value": "email"
                    },
                    {
                      "label": {
                        "en_US": "chat_id",
                        "zh_Hans": "chat_id"
                      },
                      "value": "chat_id"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Message type. Optional values are text, post, image, file, audio, media, sticker, interactive, share_chat, share_user, system. For detailed introduction of different message types, refer to the message content(https://open.larkoffice.com/document/server-docs/im-v1/message-content-description/create_json).",
                    "zh_Hans": "消息类型。可选值有：text、post、image、file、audio、media、sticker、interactive、share_chat、share_user、system。不同消息类型的详细介绍，参见发送消息内容(https://open.larkoffice.com/document/server-docs/im-v1/message-content-description/create_json)。"
                  },
                  "label": {
                    "en_US": "msg_type",
                    "zh_Hans": "消息类型"
                  },
                  "llm_description": "消息类型。可选值有：text、post、image、file、audio、media、sticker、interactive、share_chat、share_user、system。不同消息类型的详细介绍，参见发送消息内容(https://open.larkoffice.com/document/server-docs/im-v1/message-content-description/create_json)。",
                  "max": null,
                  "min": null,
                  "name": "msg_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "text",
                        "zh_Hans": "文本"
                      },
                      "value": "text"
                    },
                    {
                      "label": {
                        "en_US": "interactive",
                        "zh_Hans": "卡片"
                      },
                      "value": "interactive"
                    },
                    {
                      "label": {
                        "en_US": "post",
                        "zh_Hans": "富文本"
                      },
                      "value": "post"
                    },
                    {
                      "label": {
                        "en_US": "image",
                        "zh_Hans": "图片"
                      },
                      "value": "image"
                    },
                    {
                      "label": {
                        "en_US": "file",
                        "zh_Hans": "文件"
                      },
                      "value": "file"
                    },
                    {
                      "label": {
                        "en_US": "audio",
                        "zh_Hans": "语音"
                      },
                      "value": "audio"
                    },
                    {
                      "label": {
                        "en_US": "media",
                        "zh_Hans": "视频"
                      },
                      "value": "media"
                    },
                    {
                      "label": {
                        "en_US": "sticker",
                        "zh_Hans": "表情包"
                      },
                      "value": "sticker"
                    },
                    {
                      "label": {
                        "en_US": "share_chat",
                        "zh_Hans": "分享群名片"
                      },
                      "value": "share_chat"
                    },
                    {
                      "label": {
                        "en_US": "share_user",
                        "zh_Hans": "分享个人名片"
                      },
                      "value": "share_user"
                    },
                    {
                      "label": {
                        "en_US": "system",
                        "zh_Hans": "系统消息"
                      },
                      "value": "system"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Message content, a JSON structure serialized string. The value of this parameter corresponds to msg_type. For example, if msg_type is text, this parameter needs to pass in text type content. To understand the format and usage limitations of different message types, refer to the message content(https://open.larksuite.com/document/server-docs/im-v1/message-content-description/create_json).",
                    "zh_Hans": "消息内容，JSON 结构序列化后的字符串。该参数的取值与 msg_type 对应，例如 msg_type 取值为 text，则该参数需要传入文本类型的内容。了解不同类型的消息内容格式、使用限制，可参见发送消息内容(https://open.larksuite.com/document/server-docs/im-v1/message-content-description/create_json)。"
                  },
                  "label": {
                    "en_US": "content",
                    "zh_Hans": "消息内容"
                  },
                  "llm_description": "消息内容，JSON 结构序列化后的字符串。该参数的取值与 msg_type 对应，例如 msg_type 取值为 text，则该参数需要传入文本类型的内容。了解不同类型的消息内容格式、使用限制，可参见发送消息内容(https://open.larksuite.com/document/server-docs/im-v1/message-content-description/create_json)。",
                  "max": null,
                  "min": null,
                  "name": "content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get Chat Messages",
                  "zh_Hans": "获取指定单聊、群聊的消息历史"
                },
                "llm": "A tool for getting chat messages from specific one-on-one chats or group chats.(获取指定单聊、群聊的消息历史)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Get Chat Messages",
                  "zh_Hans": "获取指定单聊、群聊的消息历史"
                },
                "name": "get_chat_messages"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the group chat or single chat. Refer to the group ID description for how to obtain it. https://open.larkoffice.com/document/server-docs/group/chat/chat-id-description",
                    "zh_Hans": "群聊或单聊的 ID，获取方式参见群 ID 说明。https://open.larkoffice.com/document/server-docs/group/chat/chat-id-description"
                  },
                  "label": {
                    "en_US": "Container Id",
                    "zh_Hans": "群聊或单聊的 ID"
                  },
                  "llm_description": "群聊或单聊的 ID，获取方式参见群 ID 说明。https://open.larkoffice.com/document/server-docs/group/chat/chat-id-description",
                  "max": null,
                  "min": null,
                  "name": "container_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The start time for querying historical messages, formatted as \"2006-01-02 15:04:05\".",
                    "zh_Hans": "待查询历史信息的起始时间，格式为 \"2006-01-02 15:04:05\"。"
                  },
                  "label": {
                    "en_US": "Start Time",
                    "zh_Hans": "起始时间"
                  },
                  "llm_description": "待查询历史信息的起始时间，格式为 \"2006-01-02 15:04:05\"。",
                  "max": null,
                  "min": null,
                  "name": "start_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The end time for querying historical messages, formatted as \"2006-01-02 15:04:05\".",
                    "zh_Hans": "待查询历史信息的结束时间，格式为 \"2006-01-02 15:04:05\"。"
                  },
                  "label": {
                    "en_US": "End Time",
                    "zh_Hans": "结束时间"
                  },
                  "llm_description": "待查询历史信息的结束时间，格式为 \"2006-01-02 15:04:05\"。",
                  "max": null,
                  "min": null,
                  "name": "end_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "ByCreateTimeAsc",
                  "form": "form",
                  "human_description": {
                    "en_US": "The message sorting method. Optional values are ByCreateTimeAsc: sorted in ascending order by message creation time; ByCreateTimeDesc: sorted in descending order by message creation time. The default value is ByCreateTimeAsc. Note: When using page_token for pagination requests, the sorting method (sort_type) is consistent with the first request and cannot be changed midway.\n",
                    "zh_Hans": "消息排序方式，可选值有 ByCreateTimeAsc：按消息创建时间升序排列；ByCreateTimeDesc：按消息创建时间降序排列。默认值为：ByCreateTimeAsc。注意：使用 page_token 分页请求时，排序方式（sort_type）均与第一次请求一致，不支持中途改换排序方式。\n"
                  },
                  "label": {
                    "en_US": "Sort Type",
                    "zh_Hans": "排序方式"
                  },
                  "llm_description": "消息排序方式，可选值有 ByCreateTimeAsc：按消息创建时间升序排列；ByCreateTimeDesc：按消息创建时间降序排列。默认值为：ByCreateTimeAsc。注意：使用 page_token 分页请求时，排序方式（sort_type）均与第一次请求一致，不支持中途改换排序方式。",
                  "max": null,
                  "min": null,
                  "name": "sort_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "ByCreateTimeAsc",
                        "zh_Hans": "ByCreateTimeAsc"
                      },
                      "value": "ByCreateTimeAsc"
                    },
                    {
                      "label": {
                        "en_US": "ByCreateTimeDesc",
                        "zh_Hans": "ByCreateTimeDesc"
                      },
                      "value": "ByCreateTimeDesc"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 20,
                  "form": "form",
                  "human_description": {
                    "en_US": "The page size, i.e., the number of data entries returned in a single request. The default value is 20, and the value range is [1,50].",
                    "zh_Hans": "分页大小，即单次请求所返回的数据条目数。默认值为 20，取值范围为 [1,50]。"
                  },
                  "label": {
                    "en_US": "Page Size",
                    "zh_Hans": "分页大小"
                  },
                  "llm_description": "分页大小，即单次请求所返回的数据条目数。默认值为 20，取值范围为 [1,50]。",
                  "max": null,
                  "min": null,
                  "name": "page_size",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The pagination token. Leave it blank for the first request, indicating to start traversing from the beginning; when the pagination query result has more items, a new page_token will be returned simultaneously, which can be used to obtain the query result in the next traversal.",
                    "zh_Hans": "分页标记，第一次请求不填，表示从头开始遍历；分页查询结果还有更多项时会同时返回新的 page_token，下次遍历可采用该 page_token 获取查询结果。"
                  },
                  "label": {
                    "en_US": "Page Token",
                    "zh_Hans": "分页标记"
                  },
                  "llm_description": "分页标记，第一次请求不填，表示从头开始遍历；分页查询结果还有更多项时会同时返回新的 page_token，下次遍历可采用该 page_token 获取查询结果。",
                  "max": null,
                  "min": null,
                  "name": "page_token",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Send webhook message",
                  "zh_Hans": "使用自定义机器人发送 Lark 消息"
                },
                "llm": "A tool for sending Lark messages using a custom robot."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Send Webhook Message",
                  "zh_Hans": "使用自定义机器人发送 Lark 消息"
                },
                "name": "send_webhook_message"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The address of the webhook, the format of the webhook address corresponding to the bot is as follows: https://open.larksuite.com/open-apis/bot/v2/hook/xxxxxxxxxxxxxxxxx. For details, please refer to: Lark Custom Bot Usage Guide(https://open.larkoffice.com/document/client-docs/bot-v3/add-custom-bot)\n",
                    "zh_Hans": "webhook 的地址，机器人对应的 webhook 地址格式如下: https://open.larksuite.com/open-apis/bot/v2/hook/xxxxxxxxxxxxxxxxx，详情可参考: Lark 自定义机器人使用指南(https://open.larksuite.com/document/client-docs/bot-v3/add-custom-bot)\n"
                  },
                  "label": {
                    "en_US": "webhook",
                    "zh_Hans": "webhook"
                  },
                  "llm_description": "webhook 的地址，机器人对应的 webhook 地址格式如下: https://open.larksuite.com/open-apis/bot/v2/hook/xxxxxxxxxxxxxxxxx，详情可参考: Lark 自定义机器人使用指南(https://open.larksuite.com/document/client-docs/bot-v3/add-custom-bot)\n",
                  "max": null,
                  "min": null,
                  "name": "webhook",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Message type. Optional values are text, image, interactive, share_chat. For detailed introduction of different message types, refer to the message content(https://open.larkoffice.com/document/server-docs/im-v1/message-content-description/create_json).",
                    "zh_Hans": "消息类型。可选值有：text、image、interactive、share_chat。不同消息类型的详细介绍，参见发送消息内容(https://open.larkoffice.com/document/server-docs/im-v1/message-content-description/create_json)。"
                  },
                  "label": {
                    "en_US": "msg_type",
                    "zh_Hans": "消息类型"
                  },
                  "llm_description": "消息类型。可选值有：text、image、interactive、share_chat。不同消息类型的详细介绍，参见发送消息内容(https://open.larkoffice.com/document/server-docs/im-v1/message-content-description/create_json)。",
                  "max": null,
                  "min": null,
                  "name": "msg_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "text",
                        "zh_Hans": "文本"
                      },
                      "value": "text"
                    },
                    {
                      "label": {
                        "en_US": "interactive",
                        "zh_Hans": "卡片"
                      },
                      "value": "interactive"
                    },
                    {
                      "label": {
                        "en_US": "image",
                        "zh_Hans": "图片"
                      },
                      "value": "image"
                    },
                    {
                      "label": {
                        "en_US": "share_chat",
                        "zh_Hans": "分享群名片"
                      },
                      "value": "share_chat"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Message content, a JSON structure serialized string. The value of this parameter corresponds to msg_type. For example, if msg_type is text, this parameter needs to pass in text type content. To understand the format and usage limitations of different message types, refer to the message content(https://open.larkoffice.com/document/server-docs/im-v1/message-content-description/create_json).",
                    "zh_Hans": "消息内容，JSON 结构序列化后的字符串。该参数的取值与 msg_type 对应，例如 msg_type 取值为 text，则该参数需要传入文本类型的内容。了解不同类型的消息内容格式、使用限制，可参见发送消息内容(https://open.larkoffice.com/document/server-docs/im-v1/message-content-description/create_json)。"
                  },
                  "label": {
                    "en_US": "content",
                    "zh_Hans": "消息内容"
                  },
                  "llm_description": "消息内容，JSON 结构序列化后的字符串。该参数的取值与 msg_type 对应，例如 msg_type 取值为 text，则该参数需要传入文本类型的内容。了解不同类型的消息内容格式、使用限制，可参见发送消息内容(https://open.larkoffice.com/document/server-docs/im-v1/message-content-description/create_json)。",
                  "max": null,
                  "min": null,
                  "name": "content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get Thread Messages",
                  "zh_Hans": "获取指定话题的消息历史"
                },
                "llm": "A tool for getting chat messages from specific threads.(获取指定话题的消息历史)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Get Thread Messages",
                  "zh_Hans": "获取指定话题的消息历史"
                },
                "name": "get_thread_messages"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the thread. Refer to the thread overview on how to obtain the thread_id. https://open.larksuite.com/document/uAjLw4CM/ukTMukTMukTM/reference/im-v1/message/thread-introduction",
                    "zh_Hans": "话题 ID，获取方式参见话题概述的如何获取 thread_id 章节。https://open.larksuite.com/document/uAjLw4CM/ukTMukTMukTM/reference/im-v1/message/thread-introduction"
                  },
                  "label": {
                    "en_US": "Thread Id",
                    "zh_Hans": "话题 ID"
                  },
                  "llm_description": "话题 ID，获取方式参见话题概述的如何获取 thread_id 章节。https://open.larksuite.com/document/uAjLw4CM/ukTMukTMukTM/reference/im-v1/message/thread-introduction",
                  "max": null,
                  "min": null,
                  "name": "container_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "ByCreateTimeAsc",
                  "form": "form",
                  "human_description": {
                    "en_US": "The message sorting method. Optional values are ByCreateTimeAsc: sorted in ascending order by message creation time; ByCreateTimeDesc: sorted in descending order by message creation time. The default value is ByCreateTimeAsc. Note: When using page_token for pagination requests, the sorting method (sort_type) is consistent with the first request and cannot be changed midway.\n",
                    "zh_Hans": "消息排序方式，可选值有 ByCreateTimeAsc：按消息创建时间升序排列；ByCreateTimeDesc：按消息创建时间降序排列。默认值为：ByCreateTimeAsc。注意：使用 page_token 分页请求时，排序方式（sort_type）均与第一次请求一致，不支持中途改换排序方式。\n"
                  },
                  "label": {
                    "en_US": "Sort Type",
                    "zh_Hans": "排序方式"
                  },
                  "llm_description": "消息排序方式，可选值有 ByCreateTimeAsc：按消息创建时间升序排列；ByCreateTimeDesc：按消息创建时间降序排列。默认值为：ByCreateTimeAsc。注意：使用 page_token 分页请求时，排序方式（sort_type）均与第一次请求一致，不支持中途改换排序方式。",
                  "max": null,
                  "min": null,
                  "name": "sort_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "ByCreateTimeAsc",
                        "zh_Hans": "ByCreateTimeAsc"
                      },
                      "value": "ByCreateTimeAsc"
                    },
                    {
                      "label": {
                        "en_US": "ByCreateTimeDesc",
                        "zh_Hans": "ByCreateTimeDesc"
                      },
                      "value": "ByCreateTimeDesc"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 20,
                  "form": "form",
                  "human_description": {
                    "en_US": "The page size, i.e., the number of data entries returned in a single request. The default value is 20, and the value range is [1,50].",
                    "zh_Hans": "分页大小，即单次请求所返回的数据条目数。默认值为 20，取值范围为 [1,50]。"
                  },
                  "label": {
                    "en_US": "Page Size",
                    "zh_Hans": "分页大小"
                  },
                  "llm_description": "分页大小，即单次请求所返回的数据条目数。默认值为 20，取值范围为 [1,50]。",
                  "max": null,
                  "min": null,
                  "name": "page_size",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The pagination token. Leave it blank for the first request, indicating to start traversing from the beginning; when the pagination query result has more items, a new page_token will be returned simultaneously, which can be used to obtain the query result in the next traversal.",
                    "zh_Hans": "分页标记，第一次请求不填，表示从头开始遍历；分页查询结果还有更多项时会同时返回新的 page_token，下次遍历可采用该 page_token 获取查询结果。"
                  },
                  "label": {
                    "en_US": "Page Token",
                    "zh_Hans": "分页标记"
                  },
                  "llm_description": "分页标记，第一次请求不填，表示从头开始遍历；分页查询结果还有更多项时会同时返回新的 page_token，下次遍历可采用该 page_token 获取查询结果。",
                  "max": null,
                  "min": null,
                  "name": "page_token",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-26T10:39:12Z",
        "version_updated_at": "2025-02-26T10:39:12Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Connect to external data source -  Cloudflare D1",
          "ja_JP": "Connect to external data source -  Cloudflare D1",
          "pt_BR": "Connect to external data source -  Cloudflare D1",
          "zh_Hans": "Connect to external data source -  Cloudflare D1"
        },
        "category": "tool",
        "created_at": "2025-03-12T07:37:24Z",
        "endpoint": {},
        "icon": "alterxyz/packages/data_connector_cloudflare_d1/_assets/icon.svg",
        "index_id": "alterxyz___data_connector_cloudflare_d1",
        "install_count": 179,
        "introduction": "# Cloudflare D1 Data Connector for Dify\n\nA Dify plugin that allows you to connect to Cloudflare D1 databases, execute SQL queries, and integrate database operations into your AI applications.\n\n## Overview\n\nCloudflare D1 is a serverless SQL database with SQLite semantics, offering:\n\n- Built-in disaster recovery\n- Worker and HTTP API access\n- Horizontal scaling across multiple smaller databases\n- Time Travel for point-in-time recovery\n\nThis connector enables seamless integration with Dify's AI workflow, allowing your AI agents to directly query and retrieve data from your D1 databases.\n\n## Features\n\n- **SQL Query Execution**: Execute SQL queries against Cloudflare D1 databases\n- **Token Verification**: Verify Cloudflare API token validity\n- **Parameterized Queries**: Support for secure parameterized SQL queries\n- **Error Handling**: Comprehensive error reporting and handling\n\n## Setup Requirements\n\n### Prerequisites\n\n- A Cloudflare account\n- At least one D1 database created\n- API token with D1 access permissions\n\n### Required Credentials\n\n1. **Cloudflare API Token**:\n\n    - Create at: <https://developers.cloudflare.com/fundamentals/api/get-started/create-token/>\n    - Required permissions: D1 read/write access\n\n2. **Cloudflare Account ID**:\n    - Find at: <https://developers.cloudflare.com/fundamentals/setup/find-account-and-zone-ids/>\n\n### Database Information\n\nFor each query, you'll need:\n\n- **Database ID**: The unique identifier of your D1 database\n- **SQL Query**: The query to execute\n- **Parameters** (optional): Values for parameterized queries\n\n## Response Format\n\nThe connector has two types of responses:\n\n1. **Success Response**: Returns a JSON object with:\n\n    - `success`: Boolean value true\n    - `metadata`: Complete Cloudflare D1 execution result that may containing:\n        - Query results\n        - Execution metadata\n        - Status information\n\n2. **Error Response**:\n    - Raises an exception start with error type\n    - Includes `metadata` with error information\n    - Stops execution and triggers Dify's error handling\n\nExample Success Response:\n\n```json\n{\n    \"success\": true,\n    \"metadata\": {\n        \"result\": [\n            {\n                \"results\": [\n                    {\n                        \"1\": 1\n                    }\n                ],\n                \"success\": true,\n                \"meta\": {\n                    \"served_by\": \"v3-prod\",\n                    \"served_by_region\": \"APAC\",\n                    \"served_by_primary\": true,\n                    \"timings\": {\n                        \"sql_duration_ms\": 0.2211\n                    },\n                    \"duration\": 0.2211,\n                    \"changes\": 0,\n                    \"last_row_id\": 0,\n                    \"changed_db\": false,\n                    \"size_after\": 28672,\n                    \"rows_read\": 0,\n                    \"rows_written\": 0\n                }\n            }\n        ],\n        \"errors\": [],\n        \"messages\": [],\n        \"success\": true\n    }\n}\n```\n\n```plaintext\nTrue\n```\n\n## Error Handling\n\nThe connector provides detailed error information when queries fail:\n\n- **API Errors**: Returns specific Cloudflare API error codes and messages\n- **HTTP Errors**: Returns status codes and error details\n- **Connection Errors**: Provides relevant connection error information\n\nSince it might fail, it is recommended to enable Dify's retry and error handling.\n\n## Best Practices\n\n1. **Use Parameterized Queries**: Always use parameter placeholders (`?`) for dynamic values\n2. **Verify Tokens**: Test API token validity with the verification tool before executing queries\n3. **Handle Errors**: Always implement proper error handling in your applications\n\n## Limitations\n\n- Follows Cloudflare D1 service limits (see: <https://developers.cloudflare.com/d1/platform/limits/>)\n- Connection timeouts may occur for very complex queries\n- Excutes only one query at a time\n\n## Additional Resources\n\n- [Cloudflare D1 Documentation](https://developers.cloudflare.com/d1/)\n- [Cloudflare API Documentation](https://developers.cloudflare.com/api/)\n- [SQLite Documentation](https://www.sqlite.org/docs.html)\n",
        "label": {
          "en_US": "Cloudflare D1 Operator",
          "ja_JP": "Cloudflare D1 オペレーター",
          "pt_BR": "Operador Cloudflare D1",
          "zh_Hans": "Cloudflare D1 操控台"
        },
        "latest_package_identifier": "alterxyz/data_connector_cloudflare_d1:0.0.3@fddacd966e3954fa05d2283d2d3ffa7b69c0c3301b2b5b453d5c19ff16c01784",
        "latest_version": "0.0.3",
        "model": {},
        "name": "data_connector_cloudflare_d1",
        "org": "alterxyz",
        "plugin_id": "alterxyz/data_connector_cloudflare_d1",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/data_connector_cloudflare_d1.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": true,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "utilities"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Cloudflare Token",
                "pt_BR": "Cloudflare Token",
                "zh_Hans": "Cloudflare Token"
              },
              "name": "cloudflare_api_token",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Cloudflare Token",
                "pt_BR": "Por favor, insira seu Token do Cloudflare",
                "zh_Hans": "请输入您的 Cloudflare Token"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://developers.cloudflare.com/fundamentals/api/get-started/create-token/"
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Cloudflare Account ID",
                "pt_BR": "Cloudflare Account ID",
                "zh_Hans": "Cloudflare Account ID"
              },
              "name": "cloudflare_account_id",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Cloudflare Account ID",
                "pt_BR": "Por favor, insira seu ID de conta do Cloudflare",
                "zh_Hans": "请输入您的 Cloudflare Account ID"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://developers.cloudflare.com/fundamentals/setup/find-account-and-zone-ids/"
            }
          ],
          "identity": {
            "author": "alterxyz",
            "description": {
              "en_US": "Connect to external data source -  Cloudflare D1",
              "pt_BR": "Connect to external data source -  Cloudflare D1",
              "zh_Hans": "Connect to external data source -  Cloudflare D1"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Cloudflare D1",
              "pt_BR": "Cloudflare D1",
              "zh_Hans": "Cloudflare D1"
            },
            "name": "data_connector_cloudflare_d1",
            "tags": [
              "utilities",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool to verify the validity and status of Cloudflare API tokens",
                  "pt_BR": "Uma ferramenta para verificar a validade e o status dos tokens da API Cloudflare",
                  "zh_Hans": "用于验证 Cloudflare API 令牌有效性和状态的工具"
                },
                "llm": "This tool verifies the validity and active status of a Cloudflare API token. It can use either the default token from credentials or an alternative token provided as a parameter. The tool returns a JSON response with verification results including success status, messages, and token details."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "alterxyz",
                "label": {
                  "en_US": "Cloudflare Token Verification",
                  "pt_BR": "Verificação de Token Cloudflare",
                  "zh_Hans": "Cloudflare 令牌验证"
                },
                "name": "cloudflare_verify"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "An alternative Cloudflare API token to verify instead of using the default one",
                    "pt_BR": "Um token alternativo da API Cloudflare para verificar em vez de usar o padrão",
                    "zh_Hans": "用于验证的替代 Cloudflare API 令牌，不使用默认令牌"
                  },
                  "label": {
                    "en_US": "Alternative API Token",
                    "pt_BR": "Token de API Alternativo",
                    "zh_Hans": "替代 API 令牌"
                  },
                  "llm_description": "An optional alternative Cloudflare API token to verify. If provided, this token will be used for verification instead of the default token from credentials.",
                  "max": null,
                  "min": null,
                  "name": "a_cloudflare_api_token",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Executes SQL statements on Cloudflare D1 and returns the full result set. Connects to the external data source - Cloudflare D1.",
                  "pt_BR": "Executa instruções SQL no Cloudflare D1 e retorna o conjunto de resultados completo. Conecta-se à fonte de dados externa - Cloudflare D1.",
                  "zh_Hans": "在 Cloudflare D1 上执行 SQL 语句并返回完整结果集。连接到外部数据源 - Cloudflare D1。"
                },
                "llm": "Execute SQL statements on Cloudflare D1 and retrieve the complete result set. Important:Process only one SQL statement per tool call."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "alterxyz",
                "label": {
                  "en_US": "Cloudflare D1 Query Executor",
                  "pt_BR": "Ferramenta de Execução Cloudflare D1",
                  "zh_Hans": "Cloudflare D1 指令执行"
                },
                "name": "query"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Cloudflare D1 database ID.",
                    "pt_BR": "ID do banco de dados Cloudflare D1.",
                    "zh_Hans": "Cloudflare D1 数据库 ID。"
                  },
                  "label": {
                    "en_US": "Database ID",
                    "pt_BR": "ID do banco de dados",
                    "zh_Hans": "数据库 ID"
                  },
                  "llm_description": "Specify the Cloudflare D1 database ID. Important:You MUST obtain this ID from the user if not already available.",
                  "max": null,
                  "min": null,
                  "name": "database_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "SQL statement to execute on Cloudflare D1.",
                    "pt_BR": "Instrução SQL para executar no Cloudflare D1.",
                    "zh_Hans": "在 Cloudflare D1 上执行的 SQL 语句。"
                  },
                  "label": {
                    "en_US": "Statement",
                    "pt_BR": "Instrução SQL",
                    "zh_Hans": "SQL 语句"
                  },
                  "llm_description": "Provide a complete and valid SQL statement for Cloudflare D1 execution. Important:Ensure it is parameter-free (no placeholders like `?`, `:param`, etc.).",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Executes parameterized SQL queries on Cloudflare D1 and returns the full result set. Connects to external data source - Cloudflare D1 platform.",
                  "pt_BR": "Executa consultas SQL parametrizadas no Cloudflare D1 e retorna o conjunto de resultados completo. Conecta-se à fonte de dados externa - plataforma Cloudflare D1.",
                  "zh_Hans": "在 Cloudflare D1 上执行带参数的 SQL 查询并返回完整结果集。连接到外部数据源 - Cloudflare D1 平台。"
                },
                "llm": "Execute parameterized SQL queries on Cloudflare D1 and retrieve the complete result set."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "alterxyz",
                "label": {
                  "en_US": "Cloudflare D1 Advanced Query Executor",
                  "pt_BR": "Executor de Consulta Avançada Cloudflare D1",
                  "zh_Hans": "Cloudflare D1 指令执行 拓展版"
                },
                "name": "query_advanced"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Cloudflare D1 database ID.",
                    "pt_BR": "ID do banco de dados Cloudflare D1.",
                    "zh_Hans": "Cloudflare D1 数据库 ID。"
                  },
                  "label": {
                    "en_US": "Database ID",
                    "pt_BR": "ID do banco de dados",
                    "zh_Hans": "数据库 ID"
                  },
                  "llm_description": "Specify the Cloudflare D1 database ID to query.",
                  "max": null,
                  "min": null,
                  "name": "database_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "SQL query to execute on Cloudflare D1. Use `?` as placeholders for parameters. **Primarily supports standard SQL syntax, with some SQLite-specific variations and extensions. Based on SQLite.**",
                    "pt_BR": "Consulta SQL para executar no Cloudflare D1. Use `?` como marcadores de posição para parâmetros. **Suporta principalmente a sintaxe SQL padrão, com algumas variações e extensões específicas do SQLite. Baseado em SQLite.**",
                    "zh_Hans": "在 Cloudflare D1 上执行的 SQL 查询。使用 `?` 作为参数占位符。**主要支持标准 SQL 语法，但存在一些 SQLite 特有的差异和扩展。基于 SQLite。**"
                  },
                  "label": {
                    "en_US": "Query string",
                    "pt_BR": "String de consulta",
                    "zh_Hans": "执行语句"
                  },
                  "llm_description": "Provide the SQL query to execute on Cloudflare D1. Use `?` as parameter placeholders.",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Parameters for the SQL query.  Must be a JSON array string, e.g., `[\"value1\", \"value2\"]`.",
                    "pt_BR": "Parâmetros para a consulta SQL. Deve ser uma string array JSON, por exemplo - `[\"valor1\", \"valor2\"]`.",
                    "zh_Hans": "SQL 查询的参数。必须是 JSON 数组字符串，例如：`[\"value1\", \"value2\"]`。"
                  },
                  "label": {
                    "en_US": "Query parameters (JSON array string)",
                    "pt_BR": "Parâmetros de consulta (string array JSON)",
                    "zh_Hans": "查询参数 (JSON 数组字符串)"
                  },
                  "llm_description": "Provide query parameters as a JSON array string. **Important:** Ensure the parameter order matches the `?` placeholders in your query. Example - `[\"firstParam\", \"secondParam\"]`.",
                  "max": null,
                  "min": null,
                  "name": "params",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Optional Cloudflare account ID for D1 access.",
                    "pt_BR": "ID da conta Cloudflare opcional para acesso ao D1.",
                    "zh_Hans": "可选的 Cloudflare 账户 ID，用于 D1 访问。"
                  },
                  "label": {
                    "en_US": "Account ID (Optional)",
                    "pt_BR": "ID da conta (Opcional)",
                    "zh_Hans": "账户 ID (可选)"
                  },
                  "llm_description": "Optional Cloudflare account ID. **Note:**  This and `api_token` are primarily for Dify variable support and should be configured by the user in their Dify settings.  If asked to provide these, use default empty string or question the user as incorrect values will prevent execution.",
                  "max": null,
                  "min": null,
                  "name": "account_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Optional Cloudflare API token for D1 access.",
                    "pt_BR": "Token de API Cloudflare opcional para acesso ao D1.",
                    "zh_Hans": "可选的 Cloudflare API 令牌，用于 D1 访问。"
                  },
                  "label": {
                    "en_US": "API Token (Optional)",
                    "pt_BR": "Token de API (Opcional)",
                    "zh_Hans": "API 令牌 (可选)"
                  },
                  "llm_description": "Optional Cloudflare API Token. **Note:** This and `account_id` are primarily for Dify variable support and should be configured by the user in their Dify settings. If asked to provide these, use default empty string or question the user as incorrect values will prevent execution.",
                  "max": null,
                  "min": null,
                  "name": "api_token",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-12T07:37:35Z",
        "version_updated_at": "2025-03-12T07:37:35Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Interact with Dropbox files and folders. Allows listing, searching, uploading, downloading, and managing files.",
          "ja_JP": "Dropbox のファイルとフォルダを操作します。ファイルの一覧表示、検索、アップロード、ダウンロード、管理が可能です。",
          "pt_BR": "Interaja com arquivos e pastas do Dropbox. Permite listar, pesquisar, fazer upload, download e gerenciar arquivos.",
          "zh_Hans": "与 Dropbox 文件和文件夹交互。允许列出、搜索、上传、下载和管理文件。"
        },
        "category": "tool",
        "created_at": "2025-04-08T03:22:21Z",
        "endpoint": {},
        "icon": "langgenius/packages/dropbox/_assets/icon.svg",
        "index_id": "langgenius___dropbox",
        "install_count": 161,
        "introduction": "# Dropbox Plugin for Dify\n\n**Author:** lcandy  \n**Version:** 0.0.1  \n**Type:** Tool  \n\n## Description\n\nThe Dropbox plugin enables Dify applications to interact with Dropbox files and folders. With this plugin, you can build AI applications that can list, search, upload, download, and manage files in Dropbox.\n\n## Features\n\n- **List Files and Folders**: View the contents of any folder in your Dropbox\n- **Search Files**: Find files and folders matching your search criteria\n- **Upload Files**: Create new files in your Dropbox\n- **Download Files**: Retrieve file content from your Dropbox\n- **Create Folders**: Organize your Dropbox by creating new folders\n- **Delete Files/Folders**: Remove files or folders from your Dropbox\n\n## Setup\n\n1. Install the plugin in your Dify workspace\n2. Create a Dropbox app in the [Dropbox App Console](https://www.dropbox.com/developers/apps)\n3. Generate an access token for your Dropbox app\n4. Configure the plugin with your access token\n\n## Authentication\n\nThis plugin uses OAuth 2.0 for authentication. You'll need to provide an access token with the appropriate permissions for the operations you want to perform.\n\n## Usage Examples\n\n### List files in your Dropbox root folder\n```\nList all files in my Dropbox\n```\n\n### Search for specific files\n```\nFind all PDF files in my Dropbox\n```\n\n### Upload a new file\n```\nUpload a file named \"meeting-notes.txt\" to my Dropbox with the content \"Meeting scheduled for next Tuesday\"\n```\n\n### Download file content\n```\nDownload the file \"/Documents/important.txt\" from my Dropbox\n```\n\n## Requirements\n\n- A Dropbox account\n- Access token with appropriate permissions\n- Dify platform\n\n\n\n",
        "label": {
          "en_US": "Dropbox",
          "ja_JP": "Dropbox",
          "pt_BR": "Dropbox",
          "zh_Hans": "Dropbox"
        },
        "latest_package_identifier": "langgenius/dropbox:0.0.1@97824c380e70f5dce0e8c8c4d814311e85a0854661caa294f0ebc201fc500df7",
        "latest_version": "0.0.1",
        "model": {},
        "name": "dropbox",
        "org": "langgenius",
        "plugin_id": "langgenius/dropbox",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/dropbox.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Get your access token from Dropbox App Console",
                "ja_JP": "Dropbox アプリコンソールからアクセストークンを取得してください",
                "pt_BR": "Obtenha seu token de acesso no Console de Aplicativos do Dropbox",
                "zh_Hans": "从 Dropbox 应用控制台获取您的访问令牌"
              },
              "label": {
                "en_US": "Access Token",
                "ja_JP": "アクセストークン",
                "pt_BR": "Token de Acesso",
                "zh_Hans": "访问令牌"
              },
              "name": "access_token",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Dropbox access token",
                "ja_JP": "Dropbox アクセストークンを入力してください",
                "pt_BR": "Por favor, insira seu token de acesso do Dropbox",
                "zh_Hans": "请输入您的 Dropbox 访问令牌"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://www.dropbox.com/developers/apps"
            }
          ],
          "identity": {
            "author": "lcandy",
            "description": {
              "en_US": "Interact with Dropbox files and folders",
              "ja_JP": "Dropbox のファイルとフォルダを操作します",
              "pt_BR": "Interaja com arquivos e pastas do Dropbox",
              "zh_Hans": "与 Dropbox 文件和文件夹交互"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Dropbox",
              "ja_JP": "Dropbox",
              "pt_BR": "Dropbox",
              "zh_Hans": "Dropbox"
            },
            "name": "dropbox",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "List files and folders in a Dropbox folder",
                  "ja_JP": "Dropbox フォルダ内のファイルとフォルダを一覧表示します",
                  "pt_BR": "Listar arquivos e pastas em uma pasta do Dropbox",
                  "zh_Hans": "列出 Dropbox 文件夹中的文件和文件夹"
                },
                "llm": "Lists all files and folders within a specified Dropbox folder path. If no path is provided, lists contents of the root folder. Returns details including file names, paths, types (file/folder), sizes, and modification dates."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "lcandy",
                "label": {
                  "en_US": "List Files",
                  "ja_JP": "ファイル一覧",
                  "pt_BR": "Listar Arquivos",
                  "zh_Hans": "列出文件"
                },
                "name": "list_files"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The path of the folder to list (leave empty for root)",
                    "ja_JP": "一覧表示するフォルダのパス（ルートの場合は空のままにします）",
                    "pt_BR": "O caminho da pasta para listar (deixe vazio para a raiz)",
                    "zh_Hans": "要列出内容的文件夹路径（留空表示根目录）"
                  },
                  "label": {
                    "en_US": "Folder Path",
                    "ja_JP": "フォルダパス",
                    "pt_BR": "Caminho da Pasta",
                    "zh_Hans": "文件夹路径"
                  },
                  "llm_description": "Path to the Dropbox folder whose contents you want to list. Leave empty to list the root folder. Use format like '/Documents' or '/Photos/Vacation'. Paths are case-sensitive.",
                  "max": null,
                  "min": null,
                  "name": "folder_path",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Search for files and folders in Dropbox",
                  "ja_JP": "Dropbox 内のファイルとフォルダを検索します",
                  "pt_BR": "Procurar arquivos e pastas no Dropbox",
                  "zh_Hans": "在 Dropbox 中搜索文件和文件夹"
                },
                "llm": "Searches for files and folders in Dropbox that match the specified query. Returns detailed information about each matching item including path, type, size, and modification date."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "lcandy",
                "label": {
                  "en_US": "Search Files",
                  "ja_JP": "ファイル検索",
                  "pt_BR": "Pesquisar Arquivos",
                  "zh_Hans": "搜索文件"
                },
                "name": "search_files"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Enter keywords to search for files and folders",
                    "ja_JP": "ファイルとフォルダを検索するためのキーワードを入力してください",
                    "pt_BR": "Digite palavras-chave para pesquisar arquivos e pastas",
                    "zh_Hans": "输入关键词搜索文件和文件夹"
                  },
                  "label": {
                    "en_US": "Search Query",
                    "ja_JP": "検索クエリ",
                    "pt_BR": "Termo de Pesquisa",
                    "zh_Hans": "搜索关键词"
                  },
                  "llm_description": "The search query to find files and folders in Dropbox. Can be a filename, part of a filename, or content within files.",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 10,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Maximum number of results to return (default is 10)",
                    "ja_JP": "返す結果の最大数（デフォルトは10）",
                    "pt_BR": "Número máximo de resultados a retornar (padrão é 10)",
                    "zh_Hans": "返回的最大结果数（默认为10）"
                  },
                  "label": {
                    "en_US": "Maximum Results",
                    "ja_JP": "最大結果数",
                    "pt_BR": "Resultados Máximos",
                    "zh_Hans": "最大结果数"
                  },
                  "llm_description": "The maximum number of search results to return. Default is 10 if not specified.",
                  "max": null,
                  "min": null,
                  "name": "max_results",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Upload a file to Dropbox",
                  "ja_JP": "Dropbox にファイルをアップロードします",
                  "pt_BR": "Enviar um arquivo para o Dropbox",
                  "zh_Hans": "将文件上传到 Dropbox"
                },
                "llm": "Uploads a file to Dropbox at the specified path. Can upload text content directly or binary content as base64-encoded string. Returns information about the uploaded file including path, size, and modification date."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "lcandy",
                "label": {
                  "en_US": "Upload File",
                  "ja_JP": "ファイルアップロード",
                  "pt_BR": "Enviar Arquivo",
                  "zh_Hans": "上传文件"
                },
                "name": "upload_file"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The path where the file will be saved in Dropbox",
                    "ja_JP": "Dropbox に保存されるファイルのパス",
                    "pt_BR": "O caminho onde o arquivo será salvo no Dropbox",
                    "zh_Hans": "文件在 Dropbox 中的保存路径"
                  },
                  "label": {
                    "en_US": "File Path",
                    "ja_JP": "ファイルパス",
                    "pt_BR": "Caminho do Arquivo",
                    "zh_Hans": "文件路径"
                  },
                  "llm_description": "The destination path in Dropbox where the file will be saved. Should include filename with extension, like '/Documents/report.txt' or '/Photos/image.jpg'. Paths are case-sensitive and must start with a forward slash.",
                  "max": null,
                  "min": null,
                  "name": "file_path",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The text content to save (for text files)",
                    "ja_JP": "保存するテキスト内容（テキストファイル用）",
                    "pt_BR": "O conteúdo de texto a ser salvo (para arquivos de texto)",
                    "zh_Hans": "要保存的文本内容（用于文本文件）"
                  },
                  "label": {
                    "en_US": "File Content",
                    "ja_JP": "ファイル内容",
                    "pt_BR": "Conteúdo do Arquivo",
                    "zh_Hans": "文件内容"
                  },
                  "llm_description": "The text content to be stored in the file. Use this for text files. Either file_content or file_content_base64 must be provided.",
                  "max": null,
                  "min": null,
                  "name": "file_content",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The base64-encoded content (for binary files)",
                    "ja_JP": "Base64 エンコードされた内容（バイナリファイル用）",
                    "pt_BR": "O conteúdo codificado em base64 (para arquivos binários)",
                    "zh_Hans": "Base64 编码的内容（用于二进制文件）"
                  },
                  "label": {
                    "en_US": "File Content (Base64)",
                    "ja_JP": "ファイル内容（Base64）",
                    "pt_BR": "Conteúdo do Arquivo (Base64)",
                    "zh_Hans": "文件内容（Base64）"
                  },
                  "llm_description": "Base64-encoded content for the file. Use this for binary files like images or documents. Either file_content or file_content_base64 must be provided.",
                  "max": null,
                  "min": null,
                  "name": "file_content_base64",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Whether to overwrite the file if it already exists",
                    "ja_JP": "ファイルが既に存在する場合に上書きするかどうか",
                    "pt_BR": "Se deve sobrescrever o arquivo se ele já existir",
                    "zh_Hans": "如果文件已存在，是否覆盖"
                  },
                  "label": {
                    "en_US": "Overwrite",
                    "ja_JP": "上書き",
                    "pt_BR": "Sobrescrever",
                    "zh_Hans": "覆盖"
                  },
                  "llm_description": "Set to true to overwrite the file if it already exists. Set to false to avoid overwriting existing files. Default is false.",
                  "max": null,
                  "min": null,
                  "name": "overwrite",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Download a file from Dropbox",
                  "ja_JP": "Dropbox からファイルをダウンロードします",
                  "pt_BR": "Baixar um arquivo do Dropbox",
                  "zh_Hans": "从 Dropbox 下载文件"
                },
                "llm": "Downloads a file from Dropbox at the specified path. Returns file metadata and optionally the file content (as base64 for binary files or text for text files)."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "lcandy",
                "label": {
                  "en_US": "Download File",
                  "ja_JP": "ファイルダウンロード",
                  "pt_BR": "Baixar Arquivo",
                  "zh_Hans": "下载文件"
                },
                "name": "download_file"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The path of the file to download from Dropbox",
                    "ja_JP": "Dropbox からダウンロードするファイルのパス",
                    "pt_BR": "O caminho do arquivo para baixar do Dropbox",
                    "zh_Hans": "要从 Dropbox 下载的文件路径"
                  },
                  "label": {
                    "en_US": "File Path",
                    "ja_JP": "ファイルパス",
                    "pt_BR": "Caminho do Arquivo",
                    "zh_Hans": "文件路径"
                  },
                  "llm_description": "The path of the file to download from Dropbox. Should include the complete path with filename and extension, like '/Documents/report.txt'. Paths are case-sensitive and must start with a forward slash.",
                  "max": null,
                  "min": null,
                  "name": "file_path",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Whether to include the file content in the response",
                    "ja_JP": "レスポンスにファイルの内容を含めるかどうか",
                    "pt_BR": "Se deve incluir o conteúdo do arquivo na resposta",
                    "zh_Hans": "是否在响应中包含文件内容"
                  },
                  "label": {
                    "en_US": "Include Content",
                    "ja_JP": "内容を含める",
                    "pt_BR": "Incluir Conteúdo",
                    "zh_Hans": "包含内容"
                  },
                  "llm_description": "Set to true to include the file content in the response. For small text files, the content will be provided as text. For binary files, the content will be provided as base64-encoded string. Default is false.",
                  "max": null,
                  "min": null,
                  "name": "include_content",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Create a new folder in Dropbox",
                  "ja_JP": "Dropbox に新しいフォルダを作成します",
                  "pt_BR": "Criar uma nova pasta no Dropbox",
                  "zh_Hans": "在 Dropbox 中创建新文件夹"
                },
                "llm": "Creates a new folder at the specified path in Dropbox. Returns information about the created folder including path and ID."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "lcandy",
                "label": {
                  "en_US": "Create Folder",
                  "ja_JP": "フォルダ作成",
                  "pt_BR": "Criar Pasta",
                  "zh_Hans": "创建文件夹"
                },
                "name": "create_folder"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The path where the folder will be created in Dropbox",
                    "ja_JP": "Dropbox でフォルダを作成するパス",
                    "pt_BR": "O caminho onde a pasta será criada no Dropbox",
                    "zh_Hans": "文件夹在 Dropbox 中的创建路径"
                  },
                  "label": {
                    "en_US": "Folder Path",
                    "ja_JP": "フォルダパス",
                    "pt_BR": "Caminho da Pasta",
                    "zh_Hans": "文件夹路径"
                  },
                  "llm_description": "The path where the folder will be created in Dropbox. Should be specified as a complete path, like '/Documents/Projects' or '/Photos/Vacation2023'. Paths are case-sensitive and must start with a forward slash.",
                  "max": null,
                  "min": null,
                  "name": "folder_path",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Delete a file or folder from Dropbox",
                  "ja_JP": "Dropbox からファイルやフォルダを削除します",
                  "pt_BR": "Excluir um arquivo ou pasta do Dropbox",
                  "zh_Hans": "从 Dropbox 删除文件或文件夹"
                },
                "llm": "Permanently deletes a file or folder from Dropbox at the specified path. Returns confirmation information about the deleted item."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "lcandy",
                "label": {
                  "en_US": "Delete File/Folder",
                  "ja_JP": "ファイル/フォルダ削除",
                  "pt_BR": "Excluir Arquivo/Pasta",
                  "zh_Hans": "删除文件/文件夹"
                },
                "name": "delete_file"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The path of the file or folder to delete from Dropbox",
                    "ja_JP": "Dropbox から削除するファイルやフォルダのパス",
                    "pt_BR": "O caminho do arquivo ou pasta para excluir do Dropbox",
                    "zh_Hans": "要从 Dropbox 删除的文件或文件夹的路径"
                  },
                  "label": {
                    "en_US": "File/Folder Path",
                    "ja_JP": "ファイル/フォルダパス",
                    "pt_BR": "Caminho do Arquivo/Pasta",
                    "zh_Hans": "文件/文件夹路径"
                  },
                  "llm_description": "The path of the file or folder to delete from Dropbox. Should be specified as a complete path, like '/Documents/report.txt' or '/Photos/Vacation2023'. Paths are case-sensitive and must start with a forward slash. WARNING - This is a permanent deletion.",
                  "max": null,
                  "min": null,
                  "name": "file_path",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-08T03:22:27Z",
        "version_updated_at": "2025-04-08T03:22:27Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "OneBot v11 protocol tool, provides a set of actions for OneBot v11 protocol",
          "zh_Hans": "OneBot v11 协议工具，提供 OneBot v11 协议的一组动作 API"
        },
        "category": "tool",
        "created_at": "2024-12-03T08:45:53Z",
        "endpoint": {},
        "icon": "langgenius/packages/onebot/_assets/icon.ico",
        "index_id": "langgenius___onebot",
        "install_count": 158,
        "introduction": "# OneBot v11 Protocol Tool\n\n## Overview\n\nThis is a tool built for interacting with the OneBot v11 protocol. It enables developers to create and manage bots that communicate with various messaging platforms. Functionalities include sending and receiving messages, handling events, managing group and user information, and more. It provides a framework for building versatile and automated chat applications. The tool offers extensive API access for interacting with the protocol.\n\n## Configuration\n\n### 1. Apply the Access Token and HTTP URL from the [github link](https://11.onebot.dev/).\n\n### 2. Get OneBot v11 Protocol tools from Plugin Marketplace\n   The OneBot v11 Protocol tools could be found at the Plugin Marketplace, please install it first.\n\n### 3. Fill in the configuration in Dify\n\nOn the Dify navigation page, click `Tools > OneBot v11 Protocol Tools > To Authorize` and fill in the Access Token and HTTP URL.\n\n   ![](./_assets/onebot_1.PNG)\n\n### 4. Use the tool\n\nYou can use the OneBot v11 Protocol tool in the following application types:\n\n   ![](./_assets/onebot_2.PNG)\n\n#### Chatflow / Workflow applications\n\n    Both Chatflow and Workflow applications support the OneBot v11 Protocol tool node.\n   \n#### Agent applications\n\n    Add the OneBot v11 Protocol tool in the Agent application, then enter the private message or public message to call this tool.",
        "label": {
          "en_US": "OneBot v11 Protocol Tool",
          "zh_Hans": "OneBot v11 协议工具"
        },
        "latest_package_identifier": "langgenius/onebot:0.0.2@cbec773269a10877bd8b160ac3cdf9445343afb38d2805215bb25f9bc20193d2",
        "latest_version": "0.0.2",
        "model": {},
        "name": "onebot",
        "org": "langgenius",
        "plugin_id": "langgenius/onebot",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/onebot.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "Access Token",
                "zh_Hans": "访问令牌"
              },
              "name": "access_token",
              "options": null,
              "placeholder": null,
              "required": false,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "HTTP URL",
                "zh_Hans": "HTTP URL"
              },
              "name": "ob11_http_url",
              "options": null,
              "placeholder": null,
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            }
          ],
          "identity": {
            "author": "rockchinq",
            "description": {
              "en_US": "OneBot v11 protocol tool, provides a set of actions for OneBot v11 protocol",
              "zh_Hans": "OneBot v11 协议工具，提供 OneBot v11 协议的一组动作 API"
            },
            "icon": "icon.ico",
            "label": {
              "en_US": "OneBot v11 Protocol Tool",
              "zh_Hans": "OneBot v11 协议工具"
            },
            "name": "onebot",
            "tags": []
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Send a message to a group",
                  "zh_Hans": "发送消息到群聊"
                },
                "llm": "A tool for sending a message segment to a group"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "RockChinQ",
                "label": {
                  "en_US": "Send Group Message",
                  "zh_Hans": "发送群消息"
                },
                "name": "send_group_msg"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The group ID of the target group",
                    "zh_Hans": "目标群的群 ID"
                  },
                  "label": {
                    "en_US": "Target Group ID",
                    "zh_Hans": "目标群 ID"
                  },
                  "llm_description": "The group ID of the target group",
                  "max": null,
                  "min": null,
                  "name": "group_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The message to send",
                    "zh_Hans": "要发送的消息。支持 CQ码（需要同时设置 auto_escape 为 true）"
                  },
                  "label": {
                    "en_US": "Message",
                    "zh_Hans": "消息"
                  },
                  "llm_description": "The message to send",
                  "max": null,
                  "min": null,
                  "name": "message",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "If true, the message will be treated as a CQ code for parsing, otherwise it will be treated as plain text for direct sending. Since Dify currently does not support passing Object-format message chains, developers can send complex message components through CQ codes.",
                    "zh_Hans": "若为 true 则会把 message 视为 CQ 码解析，否则视为 纯文本 直接发送。由于 Dify 目前不支持传入 Object格式 的消息，故开发者可以通过 CQ 码来发送复杂消息组件。"
                  },
                  "label": {
                    "en_US": "Auto Escape",
                    "zh_Hans": "自动转义"
                  },
                  "llm_description": "If true, the message will be treated as a CQ code for parsing, otherwise it will be treated as plain text for direct sending.",
                  "max": null,
                  "min": null,
                  "name": "auto_escape",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Send a private message to a user",
                  "zh_Hans": "发送私聊消息给用户"
                },
                "llm": "A tool for sending a message segment to a user in private chat"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "RockChinQ",
                "label": {
                  "en_US": "Send Private Message",
                  "zh_Hans": "发送私聊消息"
                },
                "name": "send_private_msg"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The user ID of the target user",
                    "zh_Hans": "目标用户的用户 ID"
                  },
                  "label": {
                    "en_US": "Target User ID",
                    "zh_Hans": "目标用户 ID"
                  },
                  "llm_description": "The user ID of the target user",
                  "max": null,
                  "min": null,
                  "name": "user_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The message to send",
                    "zh_Hans": "要发送的消息。支持 CQ码（需要同时设置 auto_escape 为 true）"
                  },
                  "label": {
                    "en_US": "Message",
                    "zh_Hans": "消息"
                  },
                  "llm_description": "The message to send",
                  "max": null,
                  "min": null,
                  "name": "message",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "If true, the message will be treated as a CQ code for parsing, otherwise it will be treated as plain text for direct sending. Since Dify currently does not support passing Object-format message chains, developers can send complex message components through CQ codes.",
                    "zh_Hans": "若为 true 则会把 message 视为 CQ 码解析，否则视为 纯文本 直接发送。由于 Dify 目前不支持传入 Object格式 的消息，故开发者可以通过 CQ 码来发送复杂消息组件。"
                  },
                  "label": {
                    "en_US": "Auto Escape",
                    "zh_Hans": "自动转义"
                  },
                  "llm_description": "If true, the message will be treated as a CQ code for parsing, otherwise it will be treated as plain text for direct sending.",
                  "max": null,
                  "min": null,
                  "name": "auto_escape",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-17T07:14:19Z",
        "version_updated_at": "2025-02-17T07:14:19Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "A tool for managing Yida forms. ",
          "ja_JP": "A tool for managing Yida forms. ",
          "pt_BR": "A tool for managing Yida forms. ",
          "zh_Hans": "一款用于管理宜搭表单的工具"
        },
        "category": "tool",
        "created_at": "2025-02-24T16:33:41Z",
        "endpoint": {},
        "icon": "zxr-alibaba/packages/dingtalk_yida/_assets/icon.svg",
        "index_id": "zxr-alibaba___dingtalk_yida",
        "install_count": 153,
        "introduction": "## dingtalk_yida\n\n**Author:** yida\n**Version:** 0.0.1\n**Type:** tool\n\n### Description\n\nThis plugin is provided by the official DingTalk Yida team and is based on the Yida OpenAPI. It offers features for adding, deleting, retrieving, and updating Yida form instance data. All data will only be used to call the Yida API, so you can use it with confidence. Official Yida OpenAPI documentation: https://open.dingtalk.com/document/orgapp/overview-yida\n\n### Configuration\n\n1. You need to obtain your AppKey and AppSecret from the DingTalk Developer Console. For more details, please refer to the [DingTalk Developer Platform Documentation](https://open.dingtalk.com/document/orgapp/obtain-the-access_token-of-an-internal-app).\n2. In the authorization settings interface, enter the AppKey and AppSecret and save them.\n![img.png](img.png)\n3. Now you can freely use the tool. You can refer to the [Yida Application Development](https://open.dingtalk.com/document/orgapp/overview-yida) for the input parameters and functions of each tool.\n",
        "label": {
          "en_US": "dingtalk_yida",
          "ja_JP": "dingtalk_yida",
          "pt_BR": "dingtalk_yida",
          "zh_Hans": "钉钉宜搭"
        },
        "latest_package_identifier": "zxr-alibaba/dingtalk_yida:0.0.1@7eb415756305b1468ddb35b0c1575e1b5a806c52229829888ee40feae4e3d994",
        "latest_version": "0.0.1",
        "model": {},
        "name": "dingtalk_yida",
        "org": "zxr-alibaba",
        "plugin_id": "zxr-alibaba/dingtalk_yida",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/dingtalk_yida.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": true,
              "rerank": true,
              "speech2text": true,
              "text_embedding": true,
              "tts": true
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "App Key",
                "zh_Hans": "AppKey"
              },
              "name": "app_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your App Key",
                "zh_Hans": "请输入您的AppKey"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": "https://open.dingtalk.com/document/orgapp/obtain-the-access_token-of-an-internal-app"
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "App Secret",
                "zh_Hans": "AppSecret"
              },
              "name": "app_secret",
              "options": null,
              "placeholder": {
                "en_US": "Please input your App Secret",
                "zh_Hans": "请输入您的AppSecret"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://open.dingtalk.com/document/orgapp/obtain-the-access_token-of-an-internal-app"
            }
          ],
          "identity": {
            "author": "YIDA",
            "description": {
              "en_US": "Tool for creating and submitting DingTalk form instances.",
              "zh_Hans": "用于创建和提交钉钉表单实例的工具。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "DingTalk Yida",
              "zh_Hans": "钉钉宜搭"
            },
            "name": "dingtalk_yida",
            "tags": [
              "social",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Batch delete multiple form instances from the Yida form.",
                  "zh_Hans": "从宜搭表单中批量删除多个表单实例"
                },
                "llm": "A tool for batch deleting multiple form instances from the Yida form."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "dingtalk_yida",
                "label": {
                  "en_US": "Batch Delete Form Instances",
                  "zh_Hans": "批量删除表单实例数据"
                },
                "name": "batch_delete_form_instances"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The UUID of the form from which to delete instances.",
                    "zh_Hans": "要删除实例的表单的UUID。"
                  },
                  "label": {
                    "en_US": "Form UUID",
                    "zh_Hans": "表单UUID"
                  },
                  "llm_description": "The unique identifier of the form, e.g., FORM-GX866MC1NC1VOFF6WVQW33FD16E23LXXXXXXXX.",
                  "max": null,
                  "min": null,
                  "name": "form_uuid",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The application code.",
                    "zh_Hans": "应用编码。"
                  },
                  "label": {
                    "en_US": "App Type",
                    "zh_Hans": "应用编码"
                  },
                  "llm_description": "The application code, e.g., APP_XCE0EVXS6DYGXXXXXXXX.",
                  "max": null,
                  "min": null,
                  "name": "app_type",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The system token required for authentication.",
                    "zh_Hans": "用于身份验证的应用密钥。"
                  },
                  "label": {
                    "en_US": "System Token",
                    "zh_Hans": "应用密钥"
                  },
                  "llm_description": "The system token required to authenticate the request, e.g., 09866181UTZVVD4R3DC955FNKIM52HXXXXXXXX.",
                  "max": null,
                  "min": null,
                  "name": "system_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the user performing the deletion.",
                    "zh_Hans": "执行删除操作的用户ID。"
                  },
                  "label": {
                    "en_US": "User ID",
                    "zh_Hans": "用户ID"
                  },
                  "llm_description": "The unique identifier of the user performing the deletion, e.g., 021664184515XXXXXXXX.",
                  "max": null,
                  "min": null,
                  "name": "user_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "A JSON string representing a list of form instance IDs to delete, e.g., '[\"FINST-J8766S91O2UYN87ZX3XOF1MY8MBA291XXXXXXXX\"]'.",
                    "zh_Hans": "表单实例ID列表的JSON字符串，例如 '[\"FINST-J8766S91O2UYN87ZX3XOF1MY8MBA291XXXXXXXX\"]'。"
                  },
                  "label": {
                    "en_US": "Form Instance ID List",
                    "zh_Hans": "表单实例ID列表"
                  },
                  "llm_description": "A JSON-formatted string containing a list of form instance IDs to delete, e.g., '[\"FINST-J8766S91O2UYN87ZX3XOF1MY8MBA291XXXXXXXX\"]'.",
                  "max": null,
                  "min": null,
                  "name": "form_instance_id_list",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Whether to execute the delete operation asynchronously on the Yida server. (Optional)",
                    "zh_Hans": "是否在宜搭服务器端异步执行删除操作。（可选）"
                  },
                  "label": {
                    "en_US": "Asynchronous Execution",
                    "zh_Hans": "是否异步执行该任务"
                  },
                  "llm_description": "Whether to execute the delete operation asynchronously on the Yida server, e.g., true. (Optional)",
                  "max": null,
                  "min": null,
                  "name": "asynchronous_execution",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Whether to execute form-bound validation rules, related business rules, and third-party service callbacks during the delete operation. (Optional)",
                    "zh_Hans": "是否在删除操作中执行表单绑定的校验规则、关联业务规则和第三方服务回调。（可选）"
                  },
                  "label": {
                    "en_US": "Execute Expression",
                    "zh_Hans": "是否触发表单绑定的校验规则、关联业务规则和三方回调"
                  },
                  "llm_description": "Whether to execute form-bound validation rules, related business rules, and third-party service callbacks during the delete operation, e.g., false. (Optional)",
                  "max": null,
                  "min": null,
                  "name": "execute_expression",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Retrieve multiple form instances from the Yida form based on a list of instance IDs.",
                  "zh_Hans": "根据实例ID列表从宜搭表单中批量检索表单实例"
                },
                "llm": "A tool for retrieving multiple form instances from the Yida form based on a list of instance IDs."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "dingtalk_yida",
                "label": {
                  "en_US": "Batch Get Form Instances",
                  "zh_Hans": "批量获取表单实例数据"
                },
                "name": "batch_get_form_instances"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The UUID of the form to retrieve instances from.",
                    "zh_Hans": "要从中检索实例的表单的UUID。"
                  },
                  "label": {
                    "en_US": "Form UUID",
                    "zh_Hans": "表单UUID"
                  },
                  "llm_description": "The unique identifier of the form, e.g., FORM-F5177FA821294F44988682E0D076XXXXXXXX.",
                  "max": null,
                  "min": null,
                  "name": "form_uuid",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Application code.",
                    "zh_Hans": "应用编码。"
                  },
                  "label": {
                    "en_US": "App Type",
                    "zh_Hans": "应用编码"
                  },
                  "llm_description": "Application code, e.g., APP_VZ4Q0ITP6MV1XXXXXXXX.",
                  "max": null,
                  "min": null,
                  "name": "app_type",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Application key required for authentication.",
                    "zh_Hans": "用于身份验证的应用密钥。"
                  },
                  "label": {
                    "en_US": "System Token",
                    "zh_Hans": "应用密钥"
                  },
                  "llm_description": "The system token required to authenticate the request, e.g., VTC664B19FTS3BQQ9VQHHDUUYUVXXXXXXXXXXXX.",
                  "max": null,
                  "min": null,
                  "name": "system_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "A list of form instance IDs to retrieve.",
                    "zh_Hans": "要检索的表单实例ID列表。"
                  },
                  "label": {
                    "en_US": "Form Instance ID List",
                    "zh_Hans": "表单实例ID列表"
                  },
                  "llm_description": "A list of form instance IDs, e.g., [\"FINST-56B66Q91BEUSFYD172R9N9ING9YA24XXXXXXXXX\",\"FINST-ERD665811PTSLIK97TNGI9137FZF3SZLXXXXXXXX\"].",
                  "max": null,
                  "min": null,
                  "name": "form_instance_id_list",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the user performing the retrieval.",
                    "zh_Hans": "执行检索的用户ID。"
                  },
                  "label": {
                    "en_US": "User ID",
                    "zh_Hans": "用户ID"
                  },
                  "llm_description": "The unique identifier of the user performing the retrieval, e.g., 021664184515XXXXXXXX.",
                  "max": null,
                  "min": null,
                  "name": "user_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Whether to include the form instance values in the response. (Optional)",
                    "zh_Hans": "是否需要宜搭表单组件格式的实例数据。（可选）"
                  },
                  "label": {
                    "en_US": "Need Form Instance Value",
                    "zh_Hans": "是否需要宜搭表单组件格式的实例数据"
                  },
                  "llm_description": "Whether to include the form instance values in the response, e.g., false. (Optional)",
                  "max": null,
                  "min": null,
                  "name": "need_form_instance_value",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Batch save multiple form instances in the Yida form.",
                  "zh_Hans": "在宜搭表单中批量新增多个表单实例"
                },
                "llm": "A tool for batch saving multiple form instances in the Yida form."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "dingtalk_yida",
                "label": {
                  "en_US": "Batch Save Form Instances",
                  "zh_Hans": "批量新增表单实例数据"
                },
                "name": "batch_save_form_instances"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The UUID of the form to save instances to.",
                    "zh_Hans": "要保存实例的表单的UUID。"
                  },
                  "label": {
                    "en_US": "Form UUID",
                    "zh_Hans": "表单UUID"
                  },
                  "llm_description": "The unique identifier of the form, e.g., FORM-F5177FA821294F44988682E0D076XXXXXXXX.",
                  "max": null,
                  "min": null,
                  "name": "form_uuid",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Application code.",
                    "zh_Hans": "应用编码。"
                  },
                  "label": {
                    "en_US": "App Type",
                    "zh_Hans": "应用编码"
                  },
                  "llm_description": "Application code, e.g., APP_VZ4Q0ITP6MV1XXXXXXXX.",
                  "max": null,
                  "min": null,
                  "name": "app_type",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Application key required for authentication.",
                    "zh_Hans": "用于身份验证的应用密钥。"
                  },
                  "label": {
                    "en_US": "System Token",
                    "zh_Hans": "应用密钥"
                  },
                  "llm_description": "The system token required to authenticate the request, e.g., VTC664B19FTS3BQQ9VQHHDUUYUVXXXXXXXXXXXX.",
                  "max": null,
                  "min": null,
                  "name": "system_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the user performing the save operation.",
                    "zh_Hans": "执行保存操作的用户ID。"
                  },
                  "label": {
                    "en_US": "User ID",
                    "zh_Hans": "用户ID"
                  },
                  "llm_description": "The unique identifier of the user performing the save operation, e.g., 021664184515XXXXXXXX.",
                  "max": null,
                  "min": null,
                  "name": "user_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "A JSON string representing a list of form data objects to save.",
                    "zh_Hans": "表单数据对象列表的JSON字符串。"
                  },
                  "label": {
                    "en_US": "Form Data JSON List",
                    "zh_Hans": "表单数据JSON列表"
                  },
                  "llm_description": "A JSON-formatted string containing a list of form data objects to save, e.g., '[\"{\\\\\"textField\\\\\":\\\\\"Sample Text1\\\\\"}\", \"{\\\\\"textField\\\\\":\\\\\"Sample Text2\\\\\"}\"]'.",
                  "max": null,
                  "min": null,
                  "name": "form_data_json_list",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Whether to skip executing form-bound validation rules, related business rules, and third-party service callbacks. (Optional)",
                    "zh_Hans": "是否跳过执行表单绑定的校验规则、关联业务规则和第三方服务回调。（可选）"
                  },
                  "label": {
                    "en_US": "No Execute Expression",
                    "zh_Hans": "是否不触发表单绑定的校验规则、业务规则和三方回调"
                  },
                  "llm_description": "Whether to skip executing form-bound validation rules, related business rules, and third-party service callbacks, e.g., true. (Optional)",
                  "max": null,
                  "min": null,
                  "name": "no_execute_expression",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Whether to execute the save operation asynchronously on the Yida server. (Optional)",
                    "zh_Hans": "是否在宜搭服务器端异步执行保存操作。（可选）"
                  },
                  "label": {
                    "en_US": "Asynchronous Execution",
                    "zh_Hans": "是否需要宜搭服务端异步执行该任务"
                  },
                  "llm_description": "Whether to execute the save operation asynchronously on the Yida server, e.g., true. (Optional)",
                  "max": null,
                  "min": null,
                  "name": "asynchronous_execution",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Whether to skip the erroneous form instances and continue saving the next ones if an exception occurs during batch save. (Optional)",
                    "zh_Hans": "批量保存过程中如果发生异常，是否跳过出错的表单实例并继续保存下一个表单实例。（可选）"
                  },
                  "label": {
                    "en_US": "Keep Running After Exception",
                    "zh_Hans": "发生异常时是否跳过并继续保存下一个表单实例数据"
                  },
                  "llm_description": "Whether to skip the erroneous form instances and continue saving the next ones if an exception occurs during batch save, e.g., true. (Optional)",
                  "max": null,
                  "min": null,
                  "name": "keep_running_after_exception",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Batch update multiple form instances in the Yida form.",
                  "zh_Hans": "在宜搭表单中批量更新多个表单实例"
                },
                "llm": "A tool for batch updating multiple form instances in the Yida form."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "dingtalk_yida",
                "label": {
                  "en_US": "Batch Update Form Instances",
                  "zh_Hans": "批量更新表单实例数据"
                },
                "name": "batch_update_form_instances"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The UUID of the form to update instances in.",
                    "zh_Hans": "要更新实例的表单的UUID。"
                  },
                  "label": {
                    "en_US": "Form UUID",
                    "zh_Hans": "表单UUID"
                  },
                  "llm_description": "The unique identifier of the form, e.g., FORM-GX866MC1NC1VOFF6WVQW33FD16E23LXXXXXXXX.",
                  "max": null,
                  "min": null,
                  "name": "form_uuid",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The application code.",
                    "zh_Hans": "应用编码。"
                  },
                  "label": {
                    "en_US": "App Type",
                    "zh_Hans": "应用编码"
                  },
                  "llm_description": "The application code, e.g., APP_XCE0EVXS6DYGXXXXXXXX.",
                  "max": null,
                  "min": null,
                  "name": "app_type",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The system token required for authentication.",
                    "zh_Hans": "用于身份验证的应用密钥。"
                  },
                  "label": {
                    "en_US": "System Token",
                    "zh_Hans": "应用密钥"
                  },
                  "llm_description": "The system token required to authenticate the request, e.g., 09866181UTZVVD4R3DC955FNKIM52HXXXXXXXX.",
                  "max": null,
                  "min": null,
                  "name": "system_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the user performing the update operation.",
                    "zh_Hans": "执行更新操作的用户ID。"
                  },
                  "label": {
                    "en_US": "User ID",
                    "zh_Hans": "用户ID"
                  },
                  "llm_description": "The unique identifier of the user performing the update operation, e.g., 021664184515XXXXXXXX.",
                  "max": null,
                  "min": null,
                  "name": "user_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "A JSON string representing a list of form instance IDs to update, e.g., '[\"FINST-J8766S91O2UYN87ZX3XOF1MY8MBA291XXXXXXXX\"]'.",
                    "zh_Hans": "表单实例ID列表的JSON字符串，例如 '[\"FINST-J8766S91O2UYN87ZX3XOF1MY8MBA291XXXXXXXX\"]'。"
                  },
                  "label": {
                    "en_US": "Form Instance ID List",
                    "zh_Hans": "表单实例ID列表"
                  },
                  "llm_description": "A JSON-formatted string containing a list of form instance IDs to update, e.g., '[\"FINST-J8766S91O2UYN87ZX3XOF1MY8MBA291XXXXXXXX\"]'.",
                  "max": null,
                  "min": null,
                  "name": "form_instance_id_list",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "A JSON string representing the updated form data for each instance, e.g., '[\"{\\\\\"field\\\\\":\\\\\"value1\\\\\"}\", \"{\\\\\"field\\\\\":\\\\\"value2\\\\\"}\"]'.",
                    "zh_Hans": "每个实例的更新表单数据的JSON字符串，例如 '[\"{\\\\\"textField_m6zxxxxx\\\\\":\\\\\"示例文本1\\\\\"}\", \"{\\\\\"textField_m6zxxxxx\\\\\":\\\\\"示例文本2\\\\\"}\"]'。"
                  },
                  "label": {
                    "en_US": "Update Form Data JSON",
                    "zh_Hans": "更新表单数据JSON"
                  },
                  "llm_description": "A JSON-formatted string containing the updated form data for each instance, e.g., '[\"{\\\\\"textField_m6zxxxxx\\\\\":\\\\\"Sample Text1\\\\\"}\", \"{\\\\\"textField_m6zxxxxx\\\\\":\\\\\"Sample Text2\\\\\"}\"]'.",
                  "max": null,
                  "min": null,
                  "name": "update_form_data_json",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Whether to skip executing form-bound validation rules, related business rules, and third-party service callbacks. (Optional)",
                    "zh_Hans": "是否跳过执行表单绑定的校验规则、关联业务规则和第三方服务回调。（可选）"
                  },
                  "label": {
                    "en_US": "No Execute Expression",
                    "zh_Hans": "是否不触发表单绑定的校验规则、业务规则和三方回调"
                  },
                  "llm_description": "Whether to skip executing form-bound validation rules, related business rules, and third-party service callbacks during the update operation, e.g., true. (Optional)",
                  "max": null,
                  "min": null,
                  "name": "no_execute_expression",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Whether to ignore empty values in the update data. (Optional)",
                    "zh_Hans": "是否在更新数据中忽略空值。（可选）"
                  },
                  "label": {
                    "en_US": "Ignore Empty",
                    "zh_Hans": "是否忽略空值"
                  },
                  "llm_description": "Whether to ignore empty values in the update data, e.g., false. (Optional)",
                  "max": null,
                  "min": null,
                  "name": "ignore_empty",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Whether to use the latest version of the form schema for the update. (Optional)",
                    "zh_Hans": "是否使用表单模式的最新版本进行更新。（可选）"
                  },
                  "label": {
                    "en_US": "Use Latest Form Schema Version",
                    "zh_Hans": "是否使用最新的表单模式版本"
                  },
                  "llm_description": "Whether to use the latest version of the form schema for the update, e.g., true. (Optional)",
                  "max": null,
                  "min": null,
                  "name": "use_latest_form_schema_version",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Whether to execute the update operation asynchronously on the Yida server. (Optional)",
                    "zh_Hans": "是否在宜搭服务器端异步执行更新操作。（可选）"
                  },
                  "label": {
                    "en_US": "Asynchronous Execution",
                    "zh_Hans": "是否需要宜搭服务端异步执行该任务"
                  },
                  "llm_description": "Whether to execute the update operation asynchronously on the Yida server, e.g., true. (Optional)",
                  "max": null,
                  "min": null,
                  "name": "asynchronous_execution",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Delete a specific form instance from the Yida form.",
                  "zh_Hans": "从宜搭表单中删除特定的表单实例"
                },
                "llm": "A tool for deleting a specific form instance from the Yida form."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "dingtalk_yida",
                "label": {
                  "en_US": "Delete Form Instance",
                  "zh_Hans": "删除表单实例数据"
                },
                "name": "delete_form_instance"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The application code.",
                    "zh_Hans": "应用编码。"
                  },
                  "label": {
                    "en_US": "App Type",
                    "zh_Hans": "应用编码"
                  },
                  "llm_description": "The application code, e.g., APP_VZ4Q0ITP6MVXXXXXXXX.",
                  "max": null,
                  "min": null,
                  "name": "app_type",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The system token required for authentication.",
                    "zh_Hans": "用于身份验证的应用密钥。"
                  },
                  "label": {
                    "en_US": "System Token",
                    "zh_Hans": "应用密钥"
                  },
                  "llm_description": "The system token required to authenticate the request, e.g., VTC664B19FTS3BQQ9VQHHDUUYUVJ3R2XXXXXXXX.",
                  "max": null,
                  "min": null,
                  "name": "system_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the user performing the deletion.",
                    "zh_Hans": "执行删除操作的用户ID。"
                  },
                  "label": {
                    "en_US": "User ID",
                    "zh_Hans": "用户ID"
                  },
                  "llm_description": "The unique identifier of the user performing the deletion, e.g., 021664184515XXXXXXXX.",
                  "max": null,
                  "min": null,
                  "name": "user_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the form instance to be deleted.",
                    "zh_Hans": "要删除的表单实例的ID。"
                  },
                  "label": {
                    "en_US": "Form Instance ID",
                    "zh_Hans": "表单实例ID"
                  },
                  "llm_description": "The unique identifier of the form instance to delete, e.g., FINST-12345.",
                  "max": null,
                  "min": null,
                  "name": "form_instance_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Retrieve the fields of a specific form from the Yida platform.",
                  "zh_Hans": "从宜搭平台检索特定表单的字段信息"
                },
                "llm": "A tool for retrieving the fields of a specific form from the Yida platform."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "dingtalk_yida",
                "label": {
                  "en_US": "Get Form Fields",
                  "zh_Hans": "获取指定表单元数据"
                },
                "name": "get_form_fields"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The application code.",
                    "zh_Hans": "应用编码。"
                  },
                  "label": {
                    "en_US": "App Type",
                    "zh_Hans": "应用编码"
                  },
                  "llm_description": "The application code, e.g., APP_PBKxxxxx.",
                  "max": null,
                  "min": null,
                  "name": "app_type",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The system token required for authentication.",
                    "zh_Hans": "用于身份验证的应用密钥。"
                  },
                  "label": {
                    "en_US": "System Token",
                    "zh_Hans": "应用密钥"
                  },
                  "llm_description": "The system token required to authenticate the request, e.g., FO8xxxxx.",
                  "max": null,
                  "min": null,
                  "name": "system_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The UUID of the form whose fields are to be retrieved.",
                    "zh_Hans": "要检索字段的表单的UUID。"
                  },
                  "label": {
                    "en_US": "Form UUID",
                    "zh_Hans": "表单UUID"
                  },
                  "llm_description": "The unique identifier of the form, e.g., FORM-J7xxxxx.",
                  "max": null,
                  "min": null,
                  "name": "form_uuid",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the user performing the retrieval.",
                    "zh_Hans": "执行检索操作的用户ID。"
                  },
                  "label": {
                    "en_US": "User ID",
                    "zh_Hans": "用户ID"
                  },
                  "llm_description": "The unique identifier of the user performing the retrieval, e.g., 5014xxxxx.",
                  "max": null,
                  "min": null,
                  "name": "user_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Retrieve an existing instance of data from the Yida form.",
                  "zh_Hans": "从宜搭表单中检索一条实例数据"
                },
                "llm": "A tool for retrieving an existing instance of data from the Yida form."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "dingtalk_yida",
                "label": {
                  "en_US": "Get Form Instance Data",
                  "zh_Hans": "获取表单实例数据"
                },
                "name": "get_form_instance"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the form instance to retrieve.",
                    "zh_Hans": "要检索的表单实例的ID。"
                  },
                  "label": {
                    "en_US": "Form Instance ID",
                    "zh_Hans": "表单实例ID"
                  },
                  "llm_description": "The unique identifier of the form instance to retrieve, e.g., INSTANCE-12345.",
                  "max": null,
                  "min": null,
                  "name": "form_instance_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Application code.",
                    "zh_Hans": "应用编码。"
                  },
                  "label": {
                    "en_US": "App Type",
                    "zh_Hans": "应用编码"
                  },
                  "llm_description": "Application code, e.g., APP_VZ4Q0ITP6MV1XXXXXXXX.",
                  "max": null,
                  "min": null,
                  "name": "app_type",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Application key.",
                    "zh_Hans": "应用密钥。"
                  },
                  "label": {
                    "en_US": "System Token",
                    "zh_Hans": "应用密钥"
                  },
                  "llm_description": "The system token required to authenticate the request, e.g., VTC664B19FTS3BQQ9VQHHDUUYUVJ3R2XXXXXXXX.",
                  "max": null,
                  "min": null,
                  "name": "system_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the user requesting the form instance.",
                    "zh_Hans": "请求表单实例的用户ID。"
                  },
                  "label": {
                    "en_US": "User ID",
                    "zh_Hans": "用户ID"
                  },
                  "llm_description": "The unique identifier of the user requesting the form instance, e.g., 021664184515XXXXXXXX.",
                  "max": null,
                  "min": null,
                  "name": "user_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Retrieve forms from the Yida platform based on various criteria.",
                  "zh_Hans": "根据各种条件从宜搭平台检索表单"
                },
                "llm": "A tool for retrieving forms from the Yida platform based on various criteria."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "dingtalk_yida",
                "label": {
                  "en_US": "Get Forms In APP",
                  "zh_Hans": "获取指定应用下表单列表"
                },
                "name": "get_forms"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The application code.",
                    "zh_Hans": "应用编码。"
                  },
                  "label": {
                    "en_US": "App Type",
                    "zh_Hans": "应用编码"
                  },
                  "llm_description": "The application code, e.g., APP_PBKTxxxxx.",
                  "max": null,
                  "min": null,
                  "name": "app_type",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The system token required for authentication.",
                    "zh_Hans": "用于身份验证的应用密钥。"
                  },
                  "label": {
                    "en_US": "System Token",
                    "zh_Hans": "应用密钥"
                  },
                  "llm_description": "The system token required to authenticate the request, e.g., FO86xxxxx.",
                  "max": null,
                  "min": null,
                  "name": "system_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the user performing the retrieval.",
                    "zh_Hans": "执行检索操作的用户ID。"
                  },
                  "label": {
                    "en_US": "User ID",
                    "zh_Hans": "用户ID"
                  },
                  "llm_description": "The unique identifier of the user performing the retrieval, e.g., 5014xxxxx.",
                  "max": null,
                  "min": null,
                  "name": "user_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The types of forms to retrieve. Options， receipt (普通单据表单), process (流程表单). (Optional)",
                    "zh_Hans": "要检索的表单类型。选项：receipt（普通单据表单）、process（流程表单）。（可选）"
                  },
                  "label": {
                    "en_US": "Form Types",
                    "zh_Hans": "表单类型"
                  },
                  "llm_description": "The types of forms to retrieve, e.g., receipt, process. (Optional)",
                  "max": null,
                  "min": null,
                  "name": "form_types",
                  "options": [
                    {
                      "label": {
                        "en_US": "Receipt",
                        "zh_Hans": "普通单据表单"
                      },
                      "value": "receipt"
                    },
                    {
                      "label": {
                        "en_US": "Process",
                        "zh_Hans": "流程表单"
                      },
                      "value": "process"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The number of results per page. (Optional)",
                    "zh_Hans": "每页的结果数量。（可选）"
                  },
                  "label": {
                    "en_US": "Page Size",
                    "zh_Hans": "每页数量"
                  },
                  "llm_description": "The number of forms to return per page. (Optional)",
                  "max": null,
                  "min": null,
                  "name": "page_size",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The page number for paginated results. (Optional)",
                    "zh_Hans": "分页结果的页码。（可选）"
                  },
                  "label": {
                    "en_US": "Page Number",
                    "zh_Hans": "页码"
                  },
                  "llm_description": "The page number to retrieve, starting from 1. (Optional)",
                  "max": null,
                  "min": null,
                  "name": "page_number",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Add a new instance of data in the Yida form.",
                  "zh_Hans": "在宜搭表单中新增一条实例数据"
                },
                "llm": "A tool for adding a new instance of data in the Yida form."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "dingtalk_yida",
                "label": {
                  "en_US": "Add Form Instance Data",
                  "zh_Hans": "添加表单实例数据"
                },
                "name": "save_form_instance"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Application code.",
                    "zh_Hans": "应用编码"
                  },
                  "label": {
                    "en_US": "App Type",
                    "zh_Hans": "应用编码"
                  },
                  "llm_description": "Application code, e.g., APP_VZ4Q0ITP6MVXXXXXXXX.",
                  "max": null,
                  "min": null,
                  "name": "app_type",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Application key.",
                    "zh_Hans": "应用密钥"
                  },
                  "label": {
                    "en_US": "System Token",
                    "zh_Hans": "应用密钥"
                  },
                  "llm_description": "The system token required to authenticate the request, e.g., VTC664B19FTS3BQQ9VQHHDUUYXXXXXXXXXXXXXX.",
                  "max": null,
                  "min": null,
                  "name": "system_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the user submitting the form.",
                    "zh_Hans": "提交表单的用户ID。"
                  },
                  "label": {
                    "en_US": "User ID",
                    "zh_Hans": "用户ID"
                  },
                  "llm_description": "The unique identifier of the user submitting the form instance, e.g., 021664184515XXXXXXXX.",
                  "max": null,
                  "min": null,
                  "name": "user_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The UUID of the form to be submitted.",
                    "zh_Hans": "要提交的表单的UUID。"
                  },
                  "label": {
                    "en_US": "Form UUID",
                    "zh_Hans": "表单UUID"
                  },
                  "llm_description": "The unique identifier of the form, e.g., FORM-F5177FA821294F44988682E0D076XXXXXXXX.",
                  "max": null,
                  "min": null,
                  "name": "form_uuid",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The JSON string containing form data.",
                    "zh_Hans": "包含表单数据的JSON字符串。"
                  },
                  "label": {
                    "en_US": "Form Data JSON",
                    "zh_Hans": "表单数据JSON"
                  },
                  "llm_description": "The JSON-formatted string with the form data.",
                  "max": null,
                  "min": null,
                  "name": "form_data_json",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Search for form instances in the Yida form based on various criteria.",
                  "zh_Hans": "根据各种条件在宜搭表单中搜索表单实例"
                },
                "llm": "A tool for searching form instances in the Yida form based on various criteria."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "dingtalk_yida",
                "label": {
                  "en_US": "Search Form Instances",
                  "zh_Hans": "搜索表单实例数据"
                },
                "name": "search_form_instances"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Application code.",
                    "zh_Hans": "应用编码"
                  },
                  "label": {
                    "en_US": "App Type",
                    "zh_Hans": "应用编码"
                  },
                  "llm_description": "Application code, e.g., APP_VZ4Q0ITP6MV1XXXXXXXX.",
                  "max": null,
                  "min": null,
                  "name": "app_type",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The UUID of the form to search instances for.",
                    "zh_Hans": "要搜索实例的表单的UUID"
                  },
                  "label": {
                    "en_US": "Form UUID",
                    "zh_Hans": "表单UUID"
                  },
                  "llm_description": "The unique identifier of the form, e.g., FORM-F5177FA821294F44988682E0D076XXXXXXXX.",
                  "max": null,
                  "min": null,
                  "name": "form_uuid",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Application key required for authentication.",
                    "zh_Hans": "用于身份验证的应用密钥"
                  },
                  "label": {
                    "en_US": "System Token",
                    "zh_Hans": "应用密钥"
                  },
                  "llm_description": "The system token required to authenticate the request, e.g., VTC664B19FTS3BQQ9VQHHDUUYUXXXXXXXXXXXXX.",
                  "max": null,
                  "min": null,
                  "name": "system_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the user performing the search.",
                    "zh_Hans": "执行搜索的用户ID"
                  },
                  "label": {
                    "en_US": "User ID",
                    "zh_Hans": "用户ID"
                  },
                  "llm_description": "The unique identifier of the user performing the search, e.g., 021664184515XXXXXXXX.",
                  "max": null,
                  "min": null,
                  "name": "user_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The page number for paginated results. (Optional)",
                    "zh_Hans": "分页结果的页码（可选）"
                  },
                  "label": {
                    "en_US": "Page Number",
                    "zh_Hans": "页码"
                  },
                  "llm_description": "The page number to retrieve, starting from 1. (Optional)",
                  "max": null,
                  "min": null,
                  "name": "page_number",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The number of results per page. (Optional)",
                    "zh_Hans": "每页的结果数量（可选）"
                  },
                  "label": {
                    "en_US": "Page Size",
                    "zh_Hans": "每页数量"
                  },
                  "llm_description": "The number of form instances to return per page. (Optional)",
                  "max": null,
                  "min": null,
                  "name": "page_size",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The upper bound for the modification date in GMT. (Optional)",
                    "zh_Hans": "修改日期的上限（GMT）（可选）"
                  },
                  "label": {
                    "en_US": "Modified To Time GMT",
                    "zh_Hans": "修改结束时间GMT"
                  },
                  "llm_description": "The end date for filtering by modification time, in GMT, e.g., \"2025-02-13\". (Optional)",
                  "max": null,
                  "min": null,
                  "name": "modified_to_time_gmt",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The lower bound for the modification date in GMT. (Optional)",
                    "zh_Hans": "修改日期的下限（GMT）（可选）"
                  },
                  "label": {
                    "en_US": "Modified From Time GMT",
                    "zh_Hans": "修改开始时间GMT"
                  },
                  "llm_description": "The start date for filtering by modification time, in GMT, e.g., \"2021-05-01\". (Optional)",
                  "max": null,
                  "min": null,
                  "name": "modified_from_time_gmt",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "A JSON string specifying fields to search by. (Optional)",
                    "zh_Hans": "指定搜索字段的JSON字符串（可选）"
                  },
                  "label": {
                    "en_US": "Search Field JSON",
                    "zh_Hans": "搜索字段JSON"
                  },
                  "llm_description": "A JSON-formatted string containing fields and values to filter the search,. (Optional)",
                  "max": null,
                  "min": null,
                  "name": "search_field_json",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the originator of the form instances. (Optional)",
                    "zh_Hans": "表单实例发起人的ID（可选）"
                  },
                  "label": {
                    "en_US": "Originator ID",
                    "zh_Hans": "发起人ID"
                  },
                  "llm_description": "The unique identifier of the originator, e.g., \"02166418451524409518\". (Optional)",
                  "max": null,
                  "min": null,
                  "name": "originator_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The upper bound for the creation date in GMT. (Optional)",
                    "zh_Hans": "创建日期的上限（GMT）（可选）"
                  },
                  "label": {
                    "en_US": "Creation To Time GMT",
                    "zh_Hans": "创建结束时间GMT"
                  },
                  "llm_description": "The end date for filtering by creation time, in GMT, e.g., \"2025-02-13\". (Optional)",
                  "max": null,
                  "min": null,
                  "name": "create_to_time_gmt",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The lower bound for the creation date in GMT. (Optional)",
                    "zh_Hans": "创建日期的下限（GMT）（可选）"
                  },
                  "label": {
                    "en_US": "Creation From Time GMT",
                    "zh_Hans": "创建开始时间GMT"
                  },
                  "llm_description": "The start date for filtering by creation time, in GMT, e.g., \"2021-05-01\". (Optional)",
                  "max": null,
                  "min": null,
                  "name": "create_from_time_gmt",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Update an existing instance of data in the Yida form.",
                  "zh_Hans": "在宜搭表单中更新一条实例数据"
                },
                "llm": "A tool for updating an existing instance of data in the Yida form."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "dingtalk_yida",
                "label": {
                  "en_US": "Update Form Instance Data",
                  "zh_Hans": "更新表单实例数据"
                },
                "name": "update_form_instance"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Application code.",
                    "zh_Hans": "应用编码"
                  },
                  "label": {
                    "en_US": "App Type",
                    "zh_Hans": "应用编码"
                  },
                  "llm_description": "Application code, e.g., APP_VZ4Q0ITP6MVXXXXXXXX.",
                  "max": null,
                  "min": null,
                  "name": "app_type",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Application key.",
                    "zh_Hans": "应用密钥"
                  },
                  "label": {
                    "en_US": "System Token",
                    "zh_Hans": "应用密钥"
                  },
                  "llm_description": "The system token required to authenticate the request, e.g., VTC664B19FTS3BQQ9VQHHDUXXXXXXXXXXXXXXXX.",
                  "max": null,
                  "min": null,
                  "name": "system_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the user updating the form.",
                    "zh_Hans": "更新表单的用户ID。"
                  },
                  "label": {
                    "en_US": "User ID",
                    "zh_Hans": "用户ID"
                  },
                  "llm_description": "The unique identifier of the user updating the form instance, e.g., 021664184515XXXXXXXX.",
                  "max": null,
                  "min": null,
                  "name": "user_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the form instance to update.",
                    "zh_Hans": "要更新的表单实例的ID。"
                  },
                  "label": {
                    "en_US": "Form Instance ID",
                    "zh_Hans": "表单实例ID"
                  },
                  "llm_description": "The unique identifier of the form instance to update, e.g., INSTANCE-12345.",
                  "max": null,
                  "min": null,
                  "name": "form_instance_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Whether to use the latest version of the form.",
                    "zh_Hans": "是否使用表单的最新版本。"
                  },
                  "label": {
                    "en_US": "Use Latest Version",
                    "zh_Hans": "使用最新版本"
                  },
                  "llm_description": "Whether to use the latest version of the form when updating, e.g., true.",
                  "max": null,
                  "min": null,
                  "name": "use_latest_version",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The JSON string containing updated form data.",
                    "zh_Hans": "包含更新后表单数据的JSON字符串。"
                  },
                  "label": {
                    "en_US": "Update Form Data JSON",
                    "zh_Hans": "更新表单数据JSON"
                  },
                  "llm_description": "The JSON-formatted string with the updated form data.",
                  "max": null,
                  "min": null,
                  "name": "update_form_data_json",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-24T16:33:47Z",
        "version_updated_at": "2025-02-24T16:33:47Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "PANW AI Runtime Security API",
          "ja_JP": "PANW AI Runtime Security API",
          "pt_BR": "PANW AI Runtime Security API",
          "zh_Hans": "PANW AI Runtime Security API"
        },
        "category": "tool",
        "created_at": "2025-03-07T12:56:55Z",
        "endpoint": {},
        "icon": "zm1990s/packages/ai_security_api/_assets/icon.svg",
        "index_id": "zm1990s___ai_security_api",
        "install_count": 151,
        "introduction": "## PANW AI Security\n\n**Author:** Matt Zhang\n\n**Version:** 0.0.3\n\n**Type:** tool\n\n**中文文档|Chinese Doc**: [https://github.com/zm1990s/PANW-AIRS-for-Dify/blob/main/README-CN.md](https://github.com/zm1990s/PANW-AIRS-for-Dify/blob/main/README-CN.md)\n\n\n### Overview\n\nThis plugin is a PANW AI Runtime Security API security tool designed for the Dify platform, aiming to enhance the security of AI model and interactions. By integrating Palo Alto Networks' advanced cloud threat detection services, it provides users with comprehensive security protection.\n\n### Prerequisites\n\nAuthorized users should refer to the [AI Runtime Security: API Intercept Overview](https://docs.paloaltonetworks.com/ai-runtime-security/activation-and-onboarding/ai-runtime-security-api-intercept-overview) to complete the configuration of AI Runtime Security.\n\nIf you have not yet been authorized, please [contact our Palo Alto Networks account manager](https://www.paloaltonetworks.com/about-us/locations).\n\n### Main Features\n\n- **Prompt Detection**: Scans user inputs in Dify applications to prevent prompt injection, large model DoS attacks, and unsafe URLs, ensuring the secure operation of AI models.\n- **Model and Data Protection**: Scans the outputs of large models to prevent accidental leakage of sensitive data such as PII; prevents large models from returning malicious URLs or malicious content.\n- **Flexible Integration**: Seamlessly integrates into Dify's existing architecture without requiring customized modifications to the model, supporting various integration methods such as workflows and Agents.\n\n### Basic Usage Example\n\n#### Installation and Authorization\n\nInstall the plugin via **Marketplace/Github/Local Plugin**, and after installation, click \"Authorize\" to fill in the authentication information.\n\n![img1](_assets/img1-en.png)\n\n#### Calling in Chatflow\n\nYou can call the plugin in Chatflow to retrieve input and output content separately. It is also necessary to use \"conditional branches\" for judgment. If the detection result includes \"allow\", the workflow continues; otherwise, static content is returned, the and workflow is stopped.\n\n![img2](_assets/img2-en.png)\n\nThe following is an example of calling the input side tool:\n\n![img3](_assets/img3-en.png)\n\nThe specific parameters are described as follows:\n\n- **Check Options?** The PANW AIRS Prompt/Response identifier is used to distinguish whether the content to be checked belongs to input or output. Supported values are: `Input Check`,`Output Check`,`Code Input Check` and `Code Output Check`\n- **App Name (Optional)**: The name of the Chatflow/Agent, used for logging purposes.\n- **User Name (Optional)**: The user identifier for the current application, used for logging purposes.\n- **Model Name (Optional)**: The name of the model used by the current application, used for logging purposes.\n- **PANW AIRS Profile Name Override (Optional)**: If you want to use a different Profile for this application, you can adjust it through this parameter. The default will use the globally configured Profile Name.\n\nThe input judgment component is configured as follows:\n\n![img4](_assets/img4-en.png)\n\nThe following is an example of calling the output side tool:\n\n![img5](_assets/img5-en.png)\n\nThe output judgment component is configured as follows:\n\n![img6](_assets/img6-en.png)\n\n#### Calling in Agent\n\n![img7](_assets/img7-en.png)\n\nPrompt examples:\n\n> You are a personal information inquiry chatbot.\n>\n> \n>\n> You need to chat with users. Before chatting, you should call the `palo_alto_networks_ai_security_api` tool to check the user's input. If the detection result includes \"block\", reply to the user with \"Input is prohibited\", otherwise answer the question normally.\n>\n> \n>\n> If the user is asking about information related to Matt, you need to query the knowledge base for relevant content.\n>\n> \n>\n> Before answering the question, you should call the `palo_alto_networks_ai_security_api` tool to check the output. If the detection result includes \"block\", reply to the user with \"Output is prohibited\", otherwise answer the question normally.\n\n### Simple Demo\n\n![img8](_assets/img8-en.png)\n\n## PANW AI Security Tools for Dify\n\n**作者：** Matt Zhang\n\n**版本：** 0.0.3\n\n**类型：** tool\n\n### 概述\n\n该插件是一款适用于 Dify 平台的 PANW AI Runtime Security API 安全工具，旨在增强 AI 模型和数据交互中的安全性，通过集成 Palo Alto Networks 先进的云威胁检测服务，为用户提供全方位的安全防护。\n\n### 前提条件\n\n已获得授权的用户，请参照[此文档](https://docs.paloaltonetworks.com/ai-runtime-security/activation-and-onboarding/ai-runtime-security-api-intercept-overview)完成 AI Runtime Security 的配置。\n\n如还未获得授权，请[联系 Palo Alto Networks 客户经理](https://www.paloaltonetworks.cn/contact)。\n\n### 主要功能\n\n- **提示词检测**：扫描 Dify 应用的用户输入，防止提示词注入、大模型 DoS 攻击、不安全的 URL 等安全问题，确保 AI 模型的安全运行。\n- **模型与数据保护**：扫描大模型的输出，防止大模型意外泄露 PII 等敏感数据；防止大模型返回恶意 URL、恶意内容等安全风险。\n- **灵活集成**：无缝集成到 Dify 的现有架构中，无需对模型进行定制化修改，支持工作流、Agent 等多种对接方式。\n\n### 基本使用示例\n\n#### 安装及授权\n\n通过 **Marketplace/Github/本地插件**等方式安装插件，安装完毕后点击“去授权”，确保认证成功。\n\n![img1](_assets/img1.png)\n\n#### 在 Chatflow 中调用\n\n可以在 Chatflow 中分别调用插件对输入和输出内容进行检索，同时需要搭配“条件分支”来进行判断，如果检测结果中包含 \"allow\" 则继续进行工作流，否则返回静态内容，停止工作流。\n\n![img2](_assets/img2.png)\n\n输入侧工具调用示例如下：\n\n<img src=\"_assets/img3.png\" alt=\"img3\" style=\"zoom:50%;\" />\n\n具体参数说明如下：\n\n- 进行输入检查还是输出检查？：PANW AIRS Prompt/Response 标识符，用于区分待检测内容属于输入还是输出\n- 应用名称（可选）：该 Chatflow/Agent 的名称，用于日志记录\n- 用户名称（可选）：当前应用的用户标识，用于日志记录\n- 模型名称（可选）：当前应用所使用的模型名称，用于日志记录\n- 指定新的 PANW AIRS Profile Name（可选）：如果想针对该应用使用不同的 Profile，可以通过此参数来调整。默认将会使用全局配置的 Profile Name\n\n输入判断组件配置如下：\n\n<img src=\"_assets/img4.png\" alt=\"img4\" style=\"zoom:50%;\" />\n\n输出侧工具调用示例如下：\n\n\n<img src=\"_assets/img5.png\" alt=\"img5\" style=\"zoom:50%;\" />\n\n\n输出判断组件配置如下：\n\n\n<img src=\"_assets/img6.png\" alt=\"img6\" style=\"zoom:50%;\" />\n\n#### 在 Agent 中调用\n\n<img src=\"_assets/img7.png\" alt=\"img7\" style=\"zoom:50%;\" />\n\n提示词示例：\n\n> 你是一个个人信息查询对话机器人。\n>\n> 你需要和用户聊天，在聊天前需要先调用 palo_alto_networks_ai_security_api 对用户的输入进行检查，如果检测结果中包含 block，则回复用户“输入已被禁止”，否则请正常回答问题。\n>\n>  \n>\n> 如果用户在询问 Matt 相关的信息，需要查询知识库获取相关的内容。\n>\n>  \n>\n> 在回答问题前，需要先将你想回答的内容调用 palo_alto_networks_ai_security_api 对输出进行检查，如果检测结果中包含 block，则回复用户“输出已被禁止”，否则请正常回答问题。\n\n### 功能演示\n\n<img src=\"_assets/img8.png\" alt=\"img8\" style=\"zoom:50%;\" />\n\n## Changelog\n### v0.0.3\n- 新增恶意代码检测功能，与 API 功能对齐\n\n### v0.0.2\n- 新增 Profile Name Override 功能，满足不同应用使用不同的安全策略配置需求（注意：全局依然只能共享使用一个 Key）\n\n### v0.0.1\n- 初始版本，实现基本的全局凭据配置，输入检查及输出检查\n- 支持下列内容的识别：\n  - 提示词注入\n  - 恶意 URL\n  - 敏感数据检测（支持后台此定义策略）\n  - SQL 安全\n  - Toxic Content",
        "label": {
          "en_US": "Palo Alto Networks",
          "ja_JP": "Palo Alto Networks",
          "pt_BR": "Palo Alto Networks",
          "zh_Hans": "Palo Alto Networks"
        },
        "latest_package_identifier": "zm1990s/ai_security_api:0.0.3@d77f1140fd55c02c9e0467bcbd0527eff470980bed7383891700ff97962ec638",
        "latest_version": "0.0.3",
        "model": {},
        "name": "ai_security_api",
        "org": "zm1990s",
        "plugin_id": "zm1990s/ai_security_api",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/palo_alto_networks_ai_security_api.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 10485760,
          "permission": {}
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Get your AIRS API key from SCM",
                "ja_JP": "SCMからAIRS APIキーを取得する",
                "pt_BR": "Obtenha sua chave de API AIRS do SCM",
                "zh_Hans": "从 SCM 获取您的 AIRS API key"
              },
              "label": {
                "en_US": "PANW AIRS API key",
                "ja_JP": "PANW AIRS API key",
                "pt_BR": "PANW AIRS API key",
                "zh_Hans": "PANW AIRS API key"
              },
              "name": "airs_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your AIRS API key",
                "ja_JP": "AIRS APIキーを入力してください",
                "pt_BR": "Por favor, insira sua chave de API AIRS",
                "zh_Hans": "请输入你的 AIRS API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://docs.paloaltonetworks.com/ai-runtime-security/activation-and-onboarding/ai-runtime-security-api-intercept-overview/airs-apirs-manage-api-keys-profile-apps"
            },
            {
              "default": null,
              "help": {
                "en_US": "Get your AIRS Profile Name from SCM",
                "ja_JP": "SCMからAIRSプロファイル名を取得する",
                "pt_BR": "Obtenha o nome do seu perfil AIRS do SCM",
                "zh_Hans": "从 SCM 获取您的 AIRS Profile Name"
              },
              "label": {
                "en_US": "PANW AIRS Profile Name",
                "ja_JP": "PANW AIRS Profile Name",
                "pt_BR": "PANW AIRS Profile Name",
                "zh_Hans": "PANW AIRS Profile Name"
              },
              "name": "airs_ai_profile_name",
              "options": null,
              "placeholder": {
                "en_US": "Please input your AIRS Profile Name",
                "ja_JP": "AIRSプロファイル名を入力してください",
                "pt_BR": "Por favor, insira o nome do seu perfil AIRS",
                "zh_Hans": "请输入你的 AIRS Profile Name"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": "https://docs.paloaltonetworks.com/ai-runtime-security/activation-and-onboarding/ai-runtime-security-api-intercept-overview/airs-apirs-manage-api-keys-profile-apps"
            }
          ],
          "identity": {
            "author": "zm1990s",
            "description": {
              "en_US": "PANW AI Runtime Security API",
              "ja_JP": "PANW AI Runtime Security API",
              "pt_BR": "PANW AI Runtime Security API",
              "zh_Hans": "PANW AI Runtime Security API"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Palo Alto Networks",
              "ja_JP": "Palo Alto Networks",
              "pt_BR": "Palo Alto Networks",
              "zh_Hans": "Palo Alto Networks"
            },
            "name": "palo_alto_networks_ai_security_api",
            "tags": [
              "utilities"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Check the User Input and LLM Output through Palo Alto Networks‘ AI Runtime Security API.",
                  "ja_JP": "Palo Alto Networks の AI ランタイム セキュリティ API を使用して、ユーザー入力と大規模モデル出力を検査します",
                  "pt_BR": "Inspecione a entrada do usuário e a saída do modelo grande com a API de segurança de tempo de execução de IA da Palo Alto Networks.",
                  "zh_Hans": "通过 Palo Alto Networks 的 AI Runtime Security API 对用户输入和大模型输出进行检查"
                },
                "llm": "PANW AI Runtime Security API"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "zm1990s",
                "label": {
                  "en_US": "PANW AI Security",
                  "ja_JP": "PANW AI Security",
                  "pt_BR": "PANW AI Security",
                  "zh_Hans": "PANW AI Security"
                },
                "name": "palo_alto_networks_ai_security_api"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Query string",
                    "ja_JP": "クエリコンテンツ",
                    "pt_BR": "Cadeia de consulta",
                    "zh_Hans": "查询内容"
                  },
                  "label": {
                    "en_US": "Query string",
                    "ja_JP": "クエリコンテンツ",
                    "pt_BR": "Cadeia de consulta",
                    "zh_Hans": "查询内容"
                  },
                  "llm_description": "Check Against PANW AI Runtime Security API",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "input",
                  "form": "form",
                  "human_description": {
                    "en_US": "Check Options?",
                    "ja_JP": "オプションを確認する?",
                    "pt_BR": "Opções de verificação?",
                    "zh_Hans": "检查类型？"
                  },
                  "label": {
                    "en_US": "Check Options?",
                    "ja_JP": "オプションを確認する?",
                    "pt_BR": "Opções de verificação?",
                    "zh_Hans": "检查类型？"
                  },
                  "llm_description": "Whether the query is user input, or LLM output, is it Code input ir Code output",
                  "max": null,
                  "min": null,
                  "name": "inputoroutput",
                  "options": [
                    {
                      "label": {
                        "en_US": "Input Check",
                        "ja_JP": "入力チェック",
                        "pt_BR": "Verifique a entrada",
                        "zh_Hans": "输入检查"
                      },
                      "value": "input"
                    },
                    {
                      "label": {
                        "en_US": "Output Check",
                        "ja_JP": "出力チェック",
                        "pt_BR": "Verifique a saída",
                        "zh_Hans": "输出检查"
                      },
                      "value": "output"
                    },
                    {
                      "label": {
                        "en_US": "Code Input Check",
                        "ja_JP": "コード入力チェック",
                        "pt_BR": "Verificação de entrada de código",
                        "zh_Hans": "代码输入检查"
                      },
                      "value": "codeinput"
                    },
                    {
                      "label": {
                        "en_US": "Code Output Check",
                        "ja_JP": "コード出力チェック",
                        "pt_BR": "Verificador de saída de código",
                        "zh_Hans": "代码输出检查"
                      },
                      "value": "codeoutput"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "dify_app",
                  "form": "form",
                  "human_description": {
                    "en_US": "Specify the Dify App Name",
                    "ja_JP": "Dify アプリ名",
                    "pt_BR": "Nome da aplicação Dify",
                    "zh_Hans": "Dify 应用名称"
                  },
                  "label": {
                    "en_US": "App Name",
                    "ja_JP": "アプリケーション名",
                    "pt_BR": "Nome do aplicativo",
                    "zh_Hans": "应用名称"
                  },
                  "llm_description": "Dify App Name",
                  "max": null,
                  "min": null,
                  "name": "appname",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "dify_user",
                  "form": "form",
                  "human_description": {
                    "en_US": "Specify the Dify User Name",
                    "ja_JP": "Dify ユーザー名",
                    "pt_BR": "Nome de utilizador Dify",
                    "zh_Hans": "Dify 用户名称"
                  },
                  "label": {
                    "en_US": "User Name",
                    "ja_JP": "ユーザー名",
                    "pt_BR": "Nome de usuário",
                    "zh_Hans": "用户名称"
                  },
                  "llm_description": "Dify User Name",
                  "max": null,
                  "min": null,
                  "name": "appuser",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "dify_default_llm",
                  "form": "form",
                  "human_description": {
                    "en_US": "Model Name",
                    "ja_JP": "モデル名",
                    "pt_BR": "Nome do modelo",
                    "zh_Hans": "模型名称"
                  },
                  "label": {
                    "en_US": "Model Name",
                    "ja_JP": "モデル名",
                    "pt_BR": "Nome do modelo",
                    "zh_Hans": "模型名称"
                  },
                  "llm_description": "Model Name",
                  "max": null,
                  "min": null,
                  "name": "modelname",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Specify a new PANW AIRS Profile Name instead of the global one",
                    "ja_JP": "グローバル名の代わりに新しいPANW AIRSプロファイル名を指定します",
                    "pt_BR": "Especifique um novo nome de perfil PANW AIRS",
                    "zh_Hans": "指定新的 PANW AIRS 配置文件名称"
                  },
                  "label": {
                    "en_US": "PANW AIRS Profile Name Override",
                    "ja_JP": "新しいPANW AIRSプロファイル名を指定します",
                    "pt_BR": "Especifique um novo nome de perfil PANW AIRS",
                    "zh_Hans": "指定新的 PANW AIRS Profile Name"
                  },
                  "llm_description": "PANW AIRS Profile Name Override",
                  "max": null,
                  "min": null,
                  "name": "profileoverride",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-13T16:25:08Z",
        "version_updated_at": "2025-04-13T16:25:08Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "A DIFY chat interface that can render HTML code generated by LLM",
          "zh_Hans": "一个DIFY的聊天界面，可以渲染LLM生成的HTML代码"
        },
        "category": "extension",
        "created_at": "2025-04-22T15:20:59Z",
        "endpoint": {
          "endpoints": [
            {
              "hidden": false,
              "method": "GET",
              "path": "/"
            },
            {
              "hidden": false,
              "method": "POST",
              "path": "/api/chat"
            },
            {
              "hidden": false,
              "method": "GET",
              "path": "/asset/<path:path>"
            }
          ],
          "settings": [
            {
              "default": "Candy",
              "help": null,
              "label": {
                "en_US": "Bot name",
                "zh_Hans": "机器人名称"
              },
              "name": "bot_name",
              "options": null,
              "placeholder": {
                "en_US": "Please input your bot name",
                "zh_Hans": "请输入你的机器人名称"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "App",
                "zh_Hans": "App"
              },
              "name": "app",
              "options": null,
              "placeholder": null,
              "required": true,
              "scope": "chat",
              "type": "app-selector",
              "url": null
            }
          ]
        },
        "icon": "svcvit/packages/artifacts/_assets/icon.svg",
        "index_id": "svcvit___artifacts",
        "install_count": 146,
        "introduction": "# Artifacts\n\n**Repository:** [dify-plugin-artifacts](https://github.com/svcvit/dify-plugin-artifacts)\n\n### Feature Description\n\nThis is a web-based chat interaction interface that can help you automatically render HTML code generated by LLM, as shown below:\n\n![](./_assets/001.jpg)\n\n\n### Usage Instructions\n\n1. Configure the chatflow process you need to run\n![](./_assets/002.jpg)\n\n2. Add an endpoint, select the flow created in the first step.\n![](./_assets/003.jpg)\n\n3. Open the first URL to use\n![](./_assets/004.jpg)\n\n\n\n### Changelog\n\n\n#### v0.0.1\n- Project initialization\n- Added HTML code rendering",
        "label": {
          "en_US": "Artifacts"
        },
        "latest_package_identifier": "svcvit/artifacts:0.0.1@fa76c661309713085345ba82e0cb649ee6e50490f9e2718021762539e36e55b5",
        "latest_version": "0.0.1",
        "model": {},
        "name": "artifacts",
        "org": "svcvit",
        "plugin_id": "svcvit/artifacts",
        "plugins": {
          "agent_strategies": null,
          "endpoints": [
            "provider/artifacts.yaml"
          ],
          "models": null,
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-22T15:21:16Z",
        "version_updated_at": "2025-04-22T15:21:16Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Tools that can be operated on Airtable",
          "ja_JP": "Airtableで操作できるツールです",
          "pt_BR": "Ferramentas que podem ser operadas no Airtable",
          "zh_Hans": "可以在Airtable上操作的工具"
        },
        "category": "tool",
        "created_at": "2025-03-17T12:01:49Z",
        "endpoint": {},
        "icon": "chenzeng/packages/airtable/_assets/icon.svg",
        "index_id": "chenzeng___airtable",
        "install_count": 143,
        "introduction": "# Airtable Plugin\n\nA plugin tool for operating Airtable, supporting record creation and other operations.\n\n## What's Airtable?\n\n[Airtable](https://airtable.com/) is a cloud-based project management tool that blends a traditional spreadsheet with the robust features of a database. It allows businesses to organize their workflow, data, and records in a flexible and visually appealing way without the need for any coding.\nRepository: [dify-airtable-plugin](https://github.com/tokyo2006/dify-airtable-plugin)\n\n## Features\n\n- Support creating records in Airtable\n- Support get all records from existing table\n- Simple and easy-to-use API interface\n\n## Prerequisites\n\n- Airtable account\n- Airtable API Token\n- Created Airtable Base and Table\n\n## Configuration Guide\n\n### Getting Required Information\n\n1. **Airtable Token**\n   - Visit [Airtable Token Creation Page](https://airtable.com/create/tokens)\n   - Create and save your API Token\n\n2. **Base ID and Table ID**\n   - Can be obtained from Airtable URL\n   - For detailed instructions, refer to: [Finding Airtable IDs](https://support.airtable.com/v1/docs/finding-airtable-ids#finding-base-table-and-view-ids-from-urls)\n\n### Setup Steps\n\n1. Configure Airtable Token\n   - Enter your Airtable Token in the plugin configuration\n   - Token will be securely stored and used for API authentication\n\n2. Using the Plugin\n   - Provide Base ID\n   - Provide Table ID\n   - Provide record data to create (in JSON format)\n\n## Usage Example\n\n### Create a record\n\n#### Start by creating your own table in Airtable, something like this\n\n![table](_assets/table.png)\n\nAdd fields according to your needs\n\nExample of creating a record:\n\n```json\n{\n  \"Spend\": 52,\n  \"Store\": \"Gas station\",\n  \"Item\": \"Gas\",\n  \"DateTime\": \"2025-03-15\",\n  \"Memo\": \"Filled up 52 yuan worth of gas at the gas station\"\n}\n```\n\n#### Record Retrieval\n\nBy providing `baseId` and `tableId` in the tool, you can retrieve records. By default, all records are fetched. The output is returned as text. Example output:\n\n```json\n[\n  {\n    \"id\": \"rec123\",\n    \"Spend\": 52,\n    \"Store\": \"Gas station\",\n    \"Item\": \"Gas\",\n    \"DateTime\": \"2025-03-15\",\n    \"Memo\": \"Filled up 52 yuan worth of gas at the gas station\"\n  },\n  {\n    \"id\": \"rec456\",\n    \"Spend\": 100,\n    \"Store\": \"Supermarket\",\n    \"Item\": \"Milk\",\n    \"DateTime\": \"2025-03-16\",\n    \"Memo\": \"Bought 100 yuan worth of milk at the supermarket\" \n  }\n]\n```\n\n#### Filtering Records\n\nUse formulas to filter records. For formula syntax, refer to: [Getting Started with Formulas](https://support.airtable.com/v1/docs/getting-started-with-formulas)\nExample: To query records with a price equal to or exceeding 20 yuan, use:\n![formulas](_assets/formulas.png)\n\nResult:\n\n```json\n[{\"id\": \"rect1Vk9iOAHPfEk7\", \"Store\": \"Starbucks\", \"Item\": \"Coffe\", \"Spend\": 20, \"DateTime\": \"2025-03-13T16:00:00.000Z\"}, {\"id\": \"recTQXBclb1Fdm4a2\", \"Item\": \"Electronic heater\", \"Spend\": 200, \"DateTime\": \"2025-03-15T16:00:00.000Z\"}, {\"id\": \"recJUGiFffO6934P9\", \"Store\": \"JD\", \"Item\": \"SSD\", \"Spend\": 200, \"DateTime\": \"2025-03-15T16:00:00.000Z\"}]\n```\n\n#### Sorting\n\nUse sort to order records. Supported sorting methods: ASC and DESC. Multiple fields can be sorted by separating them with commas. Prefix a field with `-` for descending order.\nExample: Sort by Spend (descending) and DateTime (ascending):\n![sort](_assets/sort.png)\n\nResult:\n\n```json\n[{\"id\": \"recTQXBclb1Fdm4a2\", \"Item\": \"Electronic heater\", \"Spend\": 200, \"DateTime\": \"2025-03-15T16:00:00.000Z\"}, {\"id\": \"recJUGiFffO6934P9\", \"Store\": \"JD\", \"Item\": \"SSD\", \"Spend\": 200, \"DateTime\": \"2025-03-15T16:00:00.000Z\"}, {\"id\": \"rect1Vk9iOAHPfEk7\", \"Store\": \"Starbucks\", \"Item\": \"Coffe\", \"Spend\": 20, \"DateTime\": \"2025-03-13T16:00:00.000Z\"}]\n```\n\n#### Returning Specific Fields\n\nUse fields to specify returned fields. Multiple fields are comma-separated.\nExample: Return Store, Item, Spend, and DateTime:\n\n![fields](_assets/fields.png)\n\nResult:\n\n```json\n[{\"id\": \"recTQXBclb1Fdm4a2\", \"Item\": \"Electronic heater\", \"Spend\": 200, \"DateTime\": \"2025-03-15T16:00:00.000Z\"}, {\"id\": \"recJUGiFffO6934P9\", \"Store\": \"JD\", \"Item\": \"SSD\", \"Spend\": 200, \"DateTime\": \"2025-03-15T16:00:00.000Z\"}, {\"id\": \"rect1Vk9iOAHPfEk7\", \"Store\": \"Starbucks\", \"Item\": \"Coffe\", \"Spend\": 20, \"DateTime\": \"2025-03-13T16:00:00.000Z\"}]\n```\n",
        "label": {
          "en_US": "Airtable",
          "ja_JP": "Airtable",
          "pt_BR": "Airtable",
          "zh_Hans": "Airtable"
        },
        "latest_package_identifier": "chenzeng/airtable:0.1.2@7b6dd50f278015ed3738dc48e712dd94a682a080a8992abb07cc36d1b6ee2473",
        "latest_version": "0.1.2",
        "model": {},
        "name": "airtable",
        "org": "chenzeng",
        "plugin_id": "chenzeng/airtable",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/airtable.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Get your Airtable from Airtable",
                "zh_Hans": "从 Airtable 获取您的 Airtable Token"
              },
              "label": {
                "en_US": "Airtable Token",
                "zh_Hans": "Airtable Token"
              },
              "name": "airtable_token",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Airtable Token",
                "zh_Hans": "请输入你的 Airtable Token"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://airtable.com/create/tokens"
            }
          ],
          "identity": {
            "author": "chenzeng",
            "description": {
              "en_US": "A tool that can operate on the created airtable",
              "pt_BR": "A tool that can operate on the created airtable",
              "zh_Hans": "可以对创建的airtable进行操作的工具"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "airtable",
              "pt_BR": "airtable",
              "zh_Hans": "airtable"
            },
            "name": "airtable",
            "tags": [
              "utilities",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Create a record in Airtable",
                  "pt_BR": "Criando um registro no Airtable",
                  "zh_Hans": "在Airtable中创建记录"
                },
                "llm": "Create a record in Airtable"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "chenzeng",
                "label": {
                  "en_US": "airtable_insert",
                  "pt_BR": "airtable",
                  "zh_Hans": "增加记录"
                },
                "name": "airtable_insert"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "you can find it here https://support.airtable.com/v1/docs/finding-airtable-ids#finding-base-table-and-view-ids-from-urls",
                    "pt_BR": "you can find it here https://support.airtable.com/v1/docs/finding-airtable-ids#finding-base-table-and-view-ids-from-urls",
                    "zh_Hans": "你可以在这里找到它 https://support.airtable.com/v1/docs/finding-airtable-ids#finding-base-table-and-view-ids-from-urls"
                  },
                  "label": {
                    "en_US": "Base ID",
                    "pt_BR": "Base ID",
                    "zh_Hans": "Base ID"
                  },
                  "llm_description": "workspace Base id",
                  "max": null,
                  "min": null,
                  "name": "baseId",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "you can find it here https://support.airtable.com/v1/docs/finding-airtable-ids#finding-base-table-and-view-ids-from-urls",
                    "pt_BR": "you can find it here https://support.airtable.com/v1/docs/finding-airtable-ids#finding-base-table-and-view-ids-from-urls",
                    "zh_Hans": "你可以在这里找到它 https://support.airtable.com/v1/docs/finding-airtable-ids#finding-base-table-and-view-ids-from-urls"
                  },
                  "label": {
                    "en_US": "Table ID",
                    "pt_BR": "Table ID",
                    "zh_Hans": "Table ID"
                  },
                  "llm_description": "workspace Table id",
                  "max": null,
                  "min": null,
                  "name": "tableId",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Records to be created",
                    "pt_BR": "Registros a serem criados",
                    "zh_Hans": "需要创建的记录"
                  },
                  "label": {
                    "en_US": "record",
                    "pt_BR": "registos",
                    "zh_Hans": "记录"
                  },
                  "llm_description": "Records to be created",
                  "max": null,
                  "min": null,
                  "name": "record",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get all records in table",
                  "pt_BR": "Obter todos os registros em uma tabela",
                  "zh_Hans": "在表中获取所有的记录"
                },
                "llm": "Get all records in table"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "chenzeng",
                "label": {
                  "en_US": "airtable_all",
                  "pt_BR": "airtable_all",
                  "zh_Hans": "获取所有记录"
                },
                "name": "airtable_all"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "you can find it here https://support.airtable.com/v1/docs/finding-airtable-ids#finding-base-table-and-view-ids-from-urls",
                    "pt_BR": "you can find it here https://support.airtable.com/v1/docs/finding-airtable-ids#finding-base-table-and-view-ids-from-urls",
                    "zh_Hans": "你可以在这里找到它 https://support.airtable.com/v1/docs/finding-airtable-ids#finding-base-table-and-view-ids-from-urls"
                  },
                  "label": {
                    "en_US": "Base ID",
                    "pt_BR": "Base ID",
                    "zh_Hans": "Base ID"
                  },
                  "llm_description": "workspace Base id",
                  "max": null,
                  "min": null,
                  "name": "baseId",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "you can find it here https://support.airtable.com/v1/docs/finding-airtable-ids#finding-base-table-and-view-ids-from-urls",
                    "pt_BR": "you can find it here https://support.airtable.com/v1/docs/finding-airtable-ids#finding-base-table-and-view-ids-from-urls",
                    "zh_Hans": "你可以在这里找到它 https://support.airtable.com/v1/docs/finding-airtable-ids#finding-base-table-and-view-ids-from-urls"
                  },
                  "label": {
                    "en_US": "Table ID",
                    "pt_BR": "Table ID",
                    "zh_Hans": "Table ID"
                  },
                  "llm_description": "workspace Table id",
                  "max": null,
                  "min": null,
                  "name": "tableId",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 100,
                  "form": "llm",
                  "human_description": {
                    "en_US": "How many records per page",
                    "pt_BR": "Quantos dados por página",
                    "zh_Hans": "每页多少条数据"
                  },
                  "label": {
                    "en_US": "Page Size",
                    "pt_BR": "Tamanho da página",
                    "zh_Hans": "每页大小"
                  },
                  "llm_description": "How many records per page",
                  "max": null,
                  "min": null,
                  "name": "pageSize",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 1000,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The maximum number of pieces of data returned per page",
                    "pt_BR": "Número máximo de dados retornados por página",
                    "zh_Hans": "每页最多返回多少条数据"
                  },
                  "label": {
                    "en_US": "Maximum number of records per page",
                    "pt_BR": "Número máximo de registros por página",
                    "zh_Hans": "每页最大记录数"
                  },
                  "llm_description": "The maximum number of pieces of data returned per page",
                  "max": null,
                  "min": null,
                  "name": "maxRecords",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Sort by field, can pass multiple fields, separated by comma",
                    "pt_BR": "Ordenar por campo, pode passar vários campos, separados por vírgula",
                    "zh_Hans": "按字段排序,可以传入多个字段，用逗号分隔"
                  },
                  "label": {
                    "en_US": "Sort",
                    "pt_BR": "Ordenação",
                    "zh_Hans": "排序"
                  },
                  "llm_description": "Sort by field",
                  "max": null,
                  "min": null,
                  "name": "sort",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Fields to return, can pass multiple fields, separated by comma",
                    "pt_BR": "Campos a retornar, pode passar vários campos, separados por vírgula",
                    "zh_Hans": "返回的字段,可以传入多个字段，用逗号分隔"
                  },
                  "label": {
                    "en_US": "Fields",
                    "pt_BR": "Campos",
                    "zh_Hans": "字段"
                  },
                  "llm_description": "Fields to return",
                  "max": null,
                  "min": null,
                  "name": "fields",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Filter by formula",
                    "pt_BR": "Filtrar por fórmula",
                    "zh_Hans": "按公式过滤"
                  },
                  "label": {
                    "en_US": "Filter By Formula",
                    "pt_BR": "Filtro por fórmula",
                    "zh_Hans": "过滤公式"
                  },
                  "llm_description": "Filter by formula",
                  "max": null,
                  "min": null,
                  "name": "filterByFormula",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-10T14:53:02Z",
        "version_updated_at": "2025-04-10T14:53:02Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "netmind.ai",
          "zh_Hans": "netmind.ai"
        },
        "category": "model",
        "created_at": "2025-03-17T11:49:43Z",
        "endpoint": {},
        "icon": "netmind/packages/netmind/_assets/netmind.svg",
        "index_id": "netmind___netmind",
        "install_count": 139,
        "introduction": "## Overview\n[Netmind](https://www.netmind.ai/) Build AI Faster, Smarter, and More Affordably  \nTrain, Fine-tune, Run Inference, and Scale with our Global GPU Network—Your all-in-one AI Engine.\n\n## Configure\nTo configure [netmind.ai](https://www.netmind.ai/), specify the Model (Type and Name), your API Key (from [netmind.ai](https://www.netmind.ai/)). Save your settings.\n\n![](./_assets/netmind.png)\n",
        "label": {
          "en_US": "Netmind",
          "zh_Hans": "Netmind"
        },
        "latest_package_identifier": "netmind/netmind:0.0.1@8bf0c9c18a7e853542757326b78d7330991f6e76cd6709b3cf7c5f53187aa463",
        "latest_version": "0.0.1",
        "model": {
          "background": null,
          "configurate_methods": [
            "customizable-model"
          ],
          "description": {
            "en_US": "netmind.ai",
            "zh_Hans": "netmind.ai"
          },
          "help": {
            "title": {
              "en_US": "Get your API key from netmind.ai",
              "zh_Hans": "从 netmind.ai 获取 API Key"
            },
            "url": {
              "en_US": "https://www.netmind.ai/"
            }
          },
          "icon_large": {
            "en_US": "netmind_larg.svg"
          },
          "icon_small": {
            "en_US": "netmind.svg"
          },
          "label": {
            "en_US": "Netmind"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "API Key"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your API Key",
                  "zh_Hans": "在此输入您的 API Key"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "api_key"
              },
              {
                "default": "chat",
                "label": {
                  "en_US": "Completion mode"
                },
                "max_length": 0,
                "options": [
                  {
                    "label": {
                      "en_US": "Completion",
                      "zh_Hans": "补全"
                    },
                    "show_on": [],
                    "value": "completion"
                  },
                  {
                    "label": {
                      "en_US": "Chat",
                      "zh_Hans": "对话"
                    },
                    "show_on": [],
                    "value": "chat"
                  }
                ],
                "placeholder": {
                  "en_US": "Select completion mode",
                  "zh_Hans": "选择对话类型"
                },
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "select",
                "variable": "mode"
              },
              {
                "default": "4096",
                "label": {
                  "en_US": "Model context size",
                  "zh_Hans": "模型上下文长度"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Model context size",
                  "zh_Hans": "在此输入您的模型上下文长度"
                },
                "required": true,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "text-input",
                "variable": "context_size"
              },
              {
                "default": "4096",
                "label": {
                  "en_US": "Model context size",
                  "zh_Hans": "模型上下文长度"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your Model context size",
                  "zh_Hans": "在此输入您的模型上下文长度"
                },
                "required": true,
                "show_on": [
                  {
                    "value": "text-embedding",
                    "variable": "__model_type"
                  }
                ],
                "type": "text-input",
                "variable": "context_size"
              },
              {
                "default": "4096",
                "label": {
                  "en_US": "Upper bound for max tokens",
                  "zh_Hans": "最大 token 上限"
                },
                "max_length": 0,
                "options": [],
                "placeholder": null,
                "required": false,
                "show_on": [
                  {
                    "value": "llm",
                    "variable": "__model_type"
                  }
                ],
                "type": "text-input",
                "variable": "max_tokens_to_sample"
              }
            ],
            "model": {
              "label": {
                "en_US": "Model Name",
                "zh_Hans": "模型名称"
              },
              "placeholder": {
                "en_US": "Enter full model name",
                "zh_Hans": "输入模型全称"
              }
            }
          },
          "models": [],
          "provider": "netmind",
          "provider_credential_schema": null,
          "supported_model_types": [
            "llm",
            "text-embedding"
          ]
        },
        "name": "netmind",
        "org": "netmind",
        "plugin_id": "netmind/netmind",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/netmind.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "https://www.netmind.ai/doc/Privacy_Policy.html",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-03-17T11:49:51Z",
        "version_updated_at": "2025-03-17T11:49:51Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Powered by scrapeless.com, this real-time API delivers structured Google Search results at $0.1 per 1,000 queries.",
          "pt_BR": "Desenvolvido por scrapeless.com, esta API em tempo real fornece resultados estruturados do Google Search por $0,1 a cada 1.000 consultas.",
          "zh_Hans": "由 scrapeless.com 提供支持，此实时 API 以每 1,000 次查询 $0.1 的价格提供结构化的 Google 搜索结果。"
        },
        "category": "tool",
        "created_at": "2025-02-26T10:44:00Z",
        "endpoint": {},
        "icon": "scrapelesshq/packages/deep_serpapi/_assets/icon.svg",
        "index_id": "scrapelesshq___deep_serpapi",
        "install_count": 135,
        "introduction": "## Deep SerpApi\n\n### Overview\n\nPowered by scrapeless.com, this real-time API delivers structured Google Search results at $0.1 per 1,000 queries.\n\n### Configuration\n\n#### 1. Apply for an API Key\n\n- Register scrapeless.com and provide corporate KYC certification to receive a free trial quota, and apply for an API Key\n- After building your first AI tool, please contact official customer service to receive free developer support program\n\n#### 2. Install Deep SerpApi\n\nInstall Deep SerpApi from Dify Marketplace.\n\n#### 3. Add Deep SerpApi to your workflow\n\nAdd Deep SerpApi to your workflow. Click \"To authorize\" and paste the API key.\n\n![](./_assets/scrapeless_1.png)\n\n4. Using Deep SerpApi\n\n![](./_assets/scrapeless_2.png)\n",
        "label": {
          "en_US": "Deep SerpApi",
          "pt_BR": "Deep SerpApi",
          "zh_Hans": "Deep SerpApi"
        },
        "latest_package_identifier": "scrapelesshq/deep_serpapi:0.0.1@4f4f2ff0cb5d3ae89b4248195b1a7f1941007db2e1a6012fe6fb59e4c5072da5",
        "latest_version": "0.0.1",
        "model": {},
        "name": "deep_serpapi",
        "org": "scrapelesshq",
        "plugin_id": "scrapelesshq/deep_serpapi",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/deep_serpapi.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "Scrapeless API key",
                "pt_BR": "Scrapeless API key",
                "zh_Hans": "Scrapeless API key"
              },
              "name": "scrapeless_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Scrapeless API key",
                "pt_BR": "Please input your Scrapeless API key",
                "zh_Hans": "请输入你的 Scrapeless API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://app.scrapeless.com/dashboard/settings/api-key"
            }
          ],
          "identity": {
            "author": "scrapelesshq",
            "description": {
              "en_US": "Powered by scrapeless.com, this real-time API delivers structured Google Search results at $0.1 per 1,000 queries.",
              "pt_BR": "Desenvolvido por scrapeless.com, esta API em tempo real fornece resultados estruturados do Google Search por $0,1 a cada 1.000 consultas.",
              "zh_Hans": "由 scrapeless.com 提供支持，此实时 API 以每 1,000 次查询 $0.1 的价格提供结构化的 Google 搜索结果。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Deep SerpApi",
              "pt_BR": "Deep SerpApi",
              "zh_Hans": "Deep SerpApi"
            },
            "name": "deep_serpapi",
            "tags": [
              "search"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Powered by scrapeless.com, this real-time API delivers structured Google Search results at $0.1 per 1,000 queries.",
                  "pt_BR": "Desenvolvido por scrapeless.com, esta API em tempo real fornece resultados estruturados do Google Search por $0,1 a cada 1.000 consultas.",
                  "zh_Hans": "由 scrapeless.com 提供支持，此实时 API 以每 1,000 次查询 $0.1 的价格提供结构化的 Google 搜索结果。"
                },
                "llm": "Powered by scrapeless.com, this real-time API delivers structured Google Search results at $0.1 per 1,000 queries."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "scrapelesshq",
                "label": {
                  "en_US": "Deep SerpApi",
                  "pt_BR": "Deep SerpApi",
                  "zh_Hans": "Deep SerpApi"
                },
                "name": "deep_serpapi"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Powered by scrapeless.com, this real-time API delivers structured Google Search results at $0.1 per 1,000 queries.",
                    "pt_BR": "Desenvolvido por scrapeless.com, esta API em tempo real fornece resultados estruturados do Google Search por $0,1 a cada 1.000 consultas.",
                    "zh_Hans": "由 scrapeless.com 提供支持，此实时 API 以每 1,000 次查询 $0.1 的价格提供结构化的 Google 搜索结果。"
                  },
                  "label": {
                    "en_US": "Query string",
                    "pt_BR": "Query string",
                    "zh_Hans": "查询语句"
                  },
                  "llm_description": "Powered by scrapeless.com, this real-time API delivers structured Google Search results at $0.1 per 1,000 queries.",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-26T10:44:08Z",
        "version_updated_at": "2025-02-26T10:44:08Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "A plugin that enables asynchronous review of workflow variables through GoToHuman tools and endpoints",
          "ja_JP": "GoToHuman ツールとエンドポイントを通じてワークフロー変数の非同期レビューを可能にするプラグイン",
          "pt_BR": "Um plugin que permite a revisão assíncrona de variáveis de fluxo de trabalho através de ferramentas e endpoints GoToHuman",
          "zh_Hans": "通过 GoToHuman 工具和端点实现工作流变量的异步审查的插件"
        },
        "category": "tool",
        "created_at": "2025-02-18T10:52:36Z",
        "endpoint": {
          "endpoints": [
            {
              "hidden": false,
              "method": "POST",
              "path": "/goto_human"
            }
          ],
          "settings": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "App ID",
                "ja_JP": "App ID",
                "pt_BR": "App ID",
                "zh_Hans": "App ID"
              },
              "name": "app_id",
              "options": null,
              "placeholder": {
                "en_US": "Please input your App ID",
                "ja_JP": "アプリIDを入力してください",
                "pt_BR": "Por favor, insira seu App ID",
                "zh_Hans": "请输入你的 App ID"
              },
              "required": true,
              "scope": null,
              "type": "app-selector",
              "url": null
            }
          ]
        },
        "icon": "yevanchen/packages/goto_human/_assets/icon.jpg",
        "index_id": "yevanchen___goto_human",
        "install_count": 135,
        "introduction": "## goto_human\n\n**Author:** evanchen\n**Version:** 0.0.1\n**Date:** 2025-01-02 21:34:38.230712 &#43;0800 CST m=&#43;58.651056043\n**Type:** tool\n\n### Description\n\n[User Guide](https://local-carp-52a.notion.site/gotohuman-1704490152f08087be79c90f1fdde2ed?pvs=4)\n\nA community implementation of human-in-the-loop functionality using [GoToHuman](https://www.gotohuman.com/), enabling asynchronous review capabilities. When AI workflows contain unstable outputs, the GoToHuman tool can create rich review interfaces for any output variables from Dify workflow nodes.\n\n\n![GoToHuman Flow](./_assets/image.png)\n\nKey features:\n- Create customizable review pages with various frontend components\n- Comprehensive review management backend\n- Automatic review task creation when workflow reaches designated nodes\n- Asynchronous human review process with edit, approve, and reject actions\n- Webhook callbacks to endpoints when review status changes\n- Ability to trigger reverse calls to other Dify apps from the endpoint\n\n\nFlow:\n1. Workflow reaches a GoToHuman node\n2. Variables are sent to GoToHuman to create a review task\n3. Human reviewers can asynchronously:\n   - View the data in a customized interface\n   - Edit values if needed\n   - Approve or reject the review\n4. On status update, GoToHuman sends a webhook to the endpoint\n5. Endpoint processes the review result and can trigger another Dify app workflow\n\n![GoToHuman Flow](./_assets/image%20copy.png)\n\n\n\n\n\nThis enables quality control and human oversight at any point in your AI workflows while maintaining asynchronous operation.\n\n\n",
        "label": {
          "en_US": "goto_human",
          "ja_JP": "goto_human",
          "pt_BR": "goto_human",
          "zh_Hans": "goto_human"
        },
        "latest_package_identifier": "yevanchen/goto_human:0.0.2@07af351139dd3439cdf207be665e9c19d0c4dfed656829e0f31755564620d484",
        "latest_version": "0.0.2",
        "model": {},
        "name": "goto_human",
        "org": "yevanchen",
        "plugin_id": "yevanchen/goto_human",
        "plugins": {
          "agent_strategies": null,
          "endpoints": [
            "group/goto_human.yaml"
          ],
          "models": null,
          "tools": [
            "provider/goto_human.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "API key",
                "pt_BR": "API key",
                "zh_Hans": "API key"
              },
              "name": "api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your GoToHuman API key",
                "pt_BR": "Please input your GoToHuman API key",
                "zh_Hans": "请输入你的 GoToHuman API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            }
          ],
          "identity": {
            "author": "evanchen",
            "description": {
              "en_US": "A plugin that can be placed anywhere in the workflow to trigger human review events. Variables that need human review can be constructed as a dictionary string, and custom form styles can be defined on the GoToHuman platform.",
              "pt_BR": "Um plugin que pode ser colocado em qualquer lugar no fluxo de trabalho para acionar eventos de revisão humana. As variáveis que precisam de revisão humana podem ser construídas como uma string de dicionário e estilos de formulário personalizados podem ser definidos na plataforma GoToHuman.",
              "zh_Hans": "一个可以放置在工作流任意位置的插件，用于触发人工审核事件。需要人工审核的变量可以以字典形式构造为字符串，并可在GoToHuman平台上自定义表单样式。"
            },
            "icon": "icon.jpg",
            "label": {
              "en_US": "goto_human",
              "pt_BR": "goto_human",
              "zh_Hans": "goto_human"
            },
            "name": "goto_human",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool that sends content to GoToHuman for human review",
                  "zh_Hans": "一个将内容发送到GoToHuman进行人工审核的工具"
                },
                "llm": "A tool for sending content to GoToHuman platform for human review"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "Evanchen",
                "label": {
                  "en_US": "GoToHuman Review Tool",
                  "zh_Hans": "GoToHuman人工审核工具"
                },
                "name": "goto_human"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the form in GoToHuman",
                    "zh_Hans": "GoToHuman中的表单ID"
                  },
                  "label": {
                    "en_US": "Form ID",
                    "zh_Hans": "表单ID"
                  },
                  "llm_description": "The unique identifier of the form in GoToHuman platform",
                  "max": null,
                  "min": null,
                  "name": "form_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Content that needs to be reviewed",
                    "zh_Hans": "需要进行审核的内容"
                  },
                  "label": {
                    "en_US": "Review Content",
                    "zh_Hans": "审核内容"
                  },
                  "llm_description": "The content that will be sent for human review",
                  "max": null,
                  "min": null,
                  "name": "content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-21T09:22:56Z",
        "version_updated_at": "2025-02-21T09:22:56Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "A collection of tools to interact with your Shopify Store.",
          "ja_JP": "Shopifyストアとのやり取りに使用するツールのコレクション.",
          "pt_BR": "Uma coleção de ferramentas para interagir com sua loja Shopify.",
          "zh_Hans": "用于和您的Shopify店铺数据交互的工具."
        },
        "category": "tool",
        "created_at": "2025-03-14T11:39:54Z",
        "endpoint": {},
        "icon": "chekun/packages/shopify/_assets/icon.svg",
        "index_id": "chekun___shopify",
        "install_count": 133,
        "introduction": "# Shopify\n\n[项目代码地址](https://github.com/chekun/dify-plugin-shopify)\n\n## 概述\n\n在Dify中可以帮你交互Shopify店铺数据的工具🔧\n\n## 已实现的工具\n  \n  - 查询产品店铺产品信息\n\n## 配置\n\n### 1. 获取店铺ID\n\n登录Shopify后台，网址中如下图所示的部分，即为店铺ID.\n\n![](https://github.com/chekun/dify-plugin-shopify/blob/main/_assets/screenshots/store_id.png?raw=true)\n\n### 2. 创建店铺APP并获取后台 API 访问令牌\n\n> 如果已经存在店铺APP，可以跳过，也可以创建一个新的。\n\n![](https://github.com/chekun/dify-plugin-shopify/blob/main/_assets/screenshots/app_1.png?raw=true)\n\n![](https://github.com/chekun/dify-plugin-shopify/blob/main/_assets/screenshots/app_2.png?raw=true)\n\n![](https://github.com/chekun/dify-plugin-shopify/blob/main/_assets/screenshots/app_3.png?raw=true)\n\n![](https://github.com/chekun/dify-plugin-shopify/blob/main/_assets/screenshots/app_4.png?raw=true)\n\n![](https://github.com/chekun/dify-plugin-shopify/blob/main/_assets/screenshots/app_5.png?raw=true)\n\n> 设置访问范围的时候，只需要选择必要的权限即可，比如目前仅需给出读取产品的权限。\n\n![](https://github.com/chekun/dify-plugin-shopify/blob/main/_assets/screenshots/app_6.png?raw=true)\n\n![](https://github.com/chekun/dify-plugin-shopify/blob/main/_assets/screenshots/app_7.png?raw=true)\n\n### 3. 将店铺ID和访问令牌填入Dify\n\n点击插件，点击工具 Shopify , 点击设置授权。\n\n![](https://github.com/chekun/dify-plugin-shopify/blob/main/_assets/screenshots/auth.png?raw=true)\n\n### 4. 使用工具\n\n按照自己的需求使用即可\n\n> 举个例子，可以让AI分析你的产品图标，产品标题和文案，产品价格 是否可以优化等。\n\n查询产品信息返回示例：\n\n```json\n{\n    \"text\": \"\",\n    \"files\": [],\n    \"json\": [\n        {\n            \"createdAt\": \"2023-07-01T05:54:08Z\",\n            \"description\": \"this is description\",\n            \"descriptionHtml\": \"<p>this is <strong>description</strong></p>\",\n            \"featuredMedia\": {\n                \"preview\": {\n                    \"image\": {\n                        \"url\": \"https://cdn.shopify.com/s/files/1/0784/6720/3389/products/Main_b13ad453-477c-4ed1-9b43-81f3345adfd6.jpg?v=1688190848\"\n                    }\n                }\n            },\n            \"handle\": \"the-collection-snowboard-liquid\",\n            \"media\": [\n                {\n                    \"mediaContentType\": \"IMAGE\",\n                    \"preview\": {\n                        \"image\": {\n                            \"url\": \"https://cdn.shopify.com/s/files/1/0784/6720/3389/products/Main_b13ad453-477c-4ed1-9b43-81f3345adfd6.jpg?v=1688190848\"\n                        }\n                    }\n                }\n            ],\n            \"onlineStoreUrl\": null,\n            \"priceRangeV2\": {\n                \"maxVariantPrice\": {\n                    \"amount\": \"749.95\",\n                    \"currencyCode\": \"CNY\"\n                },\n                \"minVariantPrice\": {\n                    \"amount\": \"749.95\",\n                    \"currencyCode\": \"CNY\"\n                }\n            },\n            \"status\": \"ACTIVE\",\n            \"title\": \"The Collection Snowboard: Liquid\",\n            \"updatedAt\": \"2025-03-17T08:31:13Z\",\n            \"variants\": [\n                {\n                    \"displayName\": \"The Collection Snowboard: Liquid - Default Title\",\n                    \"image\": null,\n                    \"price\": \"749.95\"\n                }\n            ]\n        }\n    ]\n}\n```\n\n可以使用转换节点来提取或整合下一流程节点需要的数据。\n\n如果您有额外的数据需求，可以在项目中发起[issue](https://github.com/chekun/dify-plugin-shopify)。",
        "label": {
          "en_US": "Shopify",
          "ja_JP": "Shopify",
          "pt_BR": "Shopify",
          "zh_Hans": "Shopify"
        },
        "latest_package_identifier": "chekun/shopify:0.0.2@c2b5f40d5757fdc64995b0eed1cf6cb2d23ec7a499675c6c12e8eceb87a5c7c2",
        "latest_version": "0.0.2",
        "model": {},
        "name": "shopify",
        "org": "chekun",
        "plugin_id": "chekun/shopify",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/shopify.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "utilities"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "The store ID is the part after store/ in the browser URL after entering the store backend",
                "zh_Hans": "进入店铺后台后浏览器网址中的store/后面的部分就是店铺ID"
              },
              "label": {
                "en_US": "Store ID",
                "zh_Hans": "店铺ID"
              },
              "name": "shopify_store_id",
              "options": null,
              "placeholder": {
                "en_US": "Please input your store ID",
                "zh_Hans": "请输入您店铺ID"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": "https://github.com/chekun/dify-plugin-shopify/blob/main/README.md"
            },
            {
              "default": null,
              "help": {
                "en_US": "Get the app API access token from the Shopify store backend",
                "zh_Hans": "从Shopify店铺后台获取应用API访问令牌"
              },
              "label": {
                "en_US": "APP API Password",
                "zh_Hans": "应用API访问令牌"
              },
              "name": "shopify_app_password",
              "options": null,
              "placeholder": {
                "en_US": "Please input your store app API password",
                "zh_Hans": "请输入您店铺应用API访问令牌"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://github.com/chekun/dify-plugin-shopify/blob/main/README.md"
            }
          ],
          "identity": {
            "author": "chekun",
            "description": {
              "en_US": "A collection of tools to interact with your Shopify Store.",
              "ja_JP": "Shopifyストアとのやり取りに使用するツールのコレクション.",
              "pt_BR": "Uma coleção de ferramentas para interagir com sua loja Shopify.",
              "zh_Hans": "用于和您的Shopify店铺数据交互的工具."
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Shopify",
              "pt_BR": "Shopify",
              "zh_Hans": "Shopify"
            },
            "name": "shopify",
            "tags": [
              "productivity",
              "utilities"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Get product information by product ID or product handle.",
                  "pt_BR": "Obtenha informações do produto por ID do produto ou handle do produto.",
                  "zh_Hans": "根据产品ID或产品handle获取产品信息."
                },
                "llm": "Get product information by product ID or product handle."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "chekun",
                "label": {
                  "en_US": "Get Product Information",
                  "ja_JP": "製品情報の取得",
                  "pt_BR": "Obter informações do produto",
                  "zh_Hans": "获取产品信息"
                },
                "name": "shopify_get_product"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Product ID or product handle",
                    "pt_BR": "ID do produto ou handle do produto",
                    "zh_Hans": "产品ID或产品handle"
                  },
                  "label": {
                    "en_US": "Identifier",
                    "pt_BR": "Identificador",
                    "zh_Hans": "标识符"
                  },
                  "llm_description": "Product ID or product handle",
                  "max": null,
                  "min": null,
                  "name": "identifier",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-17T12:07:57Z",
        "version_updated_at": "2025-03-17T12:07:57Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Lark Task, requires the following permissions: task:task:write、contact:user.id:readonly.\n",
          "zh_Hans": "Lark 任务，需要开通以下权限: task:task:write、contact:user.id:readonly。\n"
        },
        "category": "tool",
        "created_at": "2025-02-26T10:38:31Z",
        "endpoint": {},
        "icon": "langgenius/packages/lark_task/_assets/icon.png",
        "index_id": "langgenius___lark_task",
        "install_count": 131,
        "introduction": "",
        "label": {
          "en_US": "Lark Task",
          "zh_Hans": "Lark 任务"
        },
        "latest_package_identifier": "langgenius/lark_task:0.0.1@6359e6d1f136f4feace9459bd883ae50f8e7b29217ec5a4a664cf9ac9edd90ce",
        "latest_version": "0.0.1",
        "model": {},
        "name": "lark_task",
        "org": "langgenius",
        "plugin_id": "langgenius/lark_task",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/lark_task.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "social"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "APP ID"
              },
              "name": "app_id",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Lark app id",
                "zh_Hans": "请输入你的 Lark app id"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": "https://open.larksuite.com/app"
            },
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "APP Secret"
              },
              "name": "app_secret",
              "options": null,
              "placeholder": {
                "en_US": "Please input your app secret",
                "zh_Hans": "请输入你的 Lark app secret"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            }
          ],
          "identity": {
            "author": "langgenius",
            "description": {
              "en_US": "Lark Task, requires the following permissions: task:task:write、contact:user.id:readonly.\n",
              "zh_Hans": "Lark 任务，需要开通以下权限: task:task:write、contact:user.id:readonly。\n"
            },
            "icon": "icon.png",
            "label": {
              "en_US": "Lark Task",
              "zh_Hans": "Lark 任务"
            },
            "name": "lark_task",
            "tags": [
              "social",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Delete Lark Task",
                  "zh_Hans": "删除 Lark 任务"
                },
                "llm": "A tool for deleting tasks in Lark.(删除 Lark 任务)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Delete Lark Task",
                  "zh_Hans": "删除 Lark 任务"
                },
                "name": "delete_task"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The GUID of the task to be deleted, supports passing either the Task ID or the Task link URL. Example of Task ID: 8b5425ec-9f2a-43bd-a3ab-01912f50282b; Example of Task link URL: https://applink.larksuite.com/client/todo/detail?guid=1b066afa-96de-406c-90a3-dfd30159a571&suite_entity_num=t100805\n",
                    "zh_Hans": "要删除的任务的 GUID，支持传任务 ID 和任务链接 URL。任务 ID 示例：8b5425ec-9f2a-43bd-a3ab-01912f50282b；任务链接 URL 示例：https://applink.larksuite.com/client/todo/detail?guid=1b066afa-96de-406c-90a3-dfd30159a571&suite_entity_num=t100805"
                  },
                  "label": {
                    "en_US": "Task GUID",
                    "zh_Hans": "任务 GUID"
                  },
                  "llm_description": "要删除的任务的 GUID，支持传任务 ID 和任务链接 URL。任务 ID 示例：8b5425ec-9f2a-43bd-a3ab-01912f50282b；任务链接 URL 示例：https://applink.larksuite.com/client/todo/detail?guid=1b066afa-96de-406c-90a3-dfd30159a571&suite_entity_num=t100805",
                  "max": null,
                  "min": null,
                  "name": "task_guid",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Create Lark Task",
                  "zh_Hans": "创建 Lark 任务"
                },
                "llm": "A tool for creating tasks in Lark.(创建 Lark 任务)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Create Lark Task",
                  "zh_Hans": "创建 Lark 任务"
                },
                "name": "create_task"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The title of the task.",
                    "zh_Hans": "任务标题"
                  },
                  "label": {
                    "en_US": "Task Title",
                    "zh_Hans": "任务标题"
                  },
                  "llm_description": "任务标题",
                  "max": null,
                  "min": null,
                  "name": "summary",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The description or notes for the task.",
                    "zh_Hans": "任务备注"
                  },
                  "label": {
                    "en_US": "Task Description",
                    "zh_Hans": "任务备注"
                  },
                  "llm_description": "任务备注",
                  "max": null,
                  "min": null,
                  "name": "description",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The start time of the task, in the format: 2006-01-02 15:04:05\n",
                    "zh_Hans": "任务开始时间，格式为：2006-01-02 15:04:05"
                  },
                  "label": {
                    "en_US": "Start Time",
                    "zh_Hans": "任务开始时间"
                  },
                  "llm_description": "任务开始时间，格式为：2006-01-02 15:04:05",
                  "max": null,
                  "min": null,
                  "name": "start_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The end time of the task, in the format: 2006-01-02 15:04:05\n",
                    "zh_Hans": "任务结束时间，格式为：2006-01-02 15:04:05"
                  },
                  "label": {
                    "en_US": "End Time",
                    "zh_Hans": "任务结束时间"
                  },
                  "llm_description": "任务结束时间，格式为：2006-01-02 15:04:05",
                  "max": null,
                  "min": null,
                  "name": "end_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The completion time of the task, in the format: 2006-01-02 15:04:05. Leave empty to create an incomplete task; fill in a specific time to create a completed task.\n",
                    "zh_Hans": "任务完成时间，格式为：2006-01-02 15:04:05，不填写表示创建一个未完成任务；填写一个具体的时间表示创建一个已完成任务。"
                  },
                  "label": {
                    "en_US": "Completed Time",
                    "zh_Hans": "任务完成时间"
                  },
                  "llm_description": "任务完成时间，格式为：2006-01-02 15:04:05，不填写表示创建一个未完成任务；填写一个具体的时间表示创建一个已完成任务。",
                  "max": null,
                  "min": null,
                  "name": "completed_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Update Lark Task",
                  "zh_Hans": "更新 Lark 任务"
                },
                "llm": "A tool for updating tasks in Lark.(更新 Lark 任务)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Update Lark Task",
                  "zh_Hans": "更新 Lark 任务"
                },
                "name": "update_task"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The task ID, supports inputting either the Task ID or the Task link URL. Example of Task ID: 42cad8a0-f8c8-4344-9be2-d1d7e8e91b64; Example of Task link URL: https://applink.larksuite.com/client/todo/detail?guid=1b066afa-96de-406c-90a3-dfd30159a571&suite_entity_num=t100805\n",
                    "zh_Hans": "任务ID，支持传入任务 ID 和任务链接 URL。任务 ID 示例: 42cad8a0-f8c8-4344-9be2-d1d7e8e91b64；任务链接 URL 示例: https://applink.larksuite.com/client/todo/detail?guid=1b066afa-96de-406c-90a3-dfd30159a571&suite_entity_num=t100805\n"
                  },
                  "label": {
                    "en_US": "Task GUID",
                    "zh_Hans": "任务 GUID"
                  },
                  "llm_description": "任务ID，支持传入任务 ID 和任务链接 URL。任务 ID 示例: 42cad8a0-f8c8-4344-9be2-d1d7e8e91b64；任务链接 URL 示例: https://applink.larksuite.com/client/todo/detail?guid=1b066afa-96de-406c-90a3-dfd30159a571&suite_entity_num=t100805\n",
                  "max": null,
                  "min": null,
                  "name": "task_guid",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The title of the task.",
                    "zh_Hans": "任务标题"
                  },
                  "label": {
                    "en_US": "Task Title",
                    "zh_Hans": "任务标题"
                  },
                  "llm_description": "任务标题",
                  "max": null,
                  "min": null,
                  "name": "summary",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The description or notes for the task.",
                    "zh_Hans": "任务备注"
                  },
                  "label": {
                    "en_US": "Task Description",
                    "zh_Hans": "任务备注"
                  },
                  "llm_description": "任务备注",
                  "max": null,
                  "min": null,
                  "name": "description",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The start time of the task, in the format: 2006-01-02 15:04:05\n",
                    "zh_Hans": "任务开始时间，格式为：2006-01-02 15:04:05"
                  },
                  "label": {
                    "en_US": "Start Time",
                    "zh_Hans": "任务开始时间"
                  },
                  "llm_description": "任务开始时间，格式为：2006-01-02 15:04:05",
                  "max": null,
                  "min": null,
                  "name": "start_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The end time of the task, in the format: 2006-01-02 15:04:05\n",
                    "zh_Hans": "任务结束时间，格式为：2006-01-02 15:04:05"
                  },
                  "label": {
                    "en_US": "End Time",
                    "zh_Hans": "任务结束时间"
                  },
                  "llm_description": "任务结束时间，格式为：2006-01-02 15:04:05",
                  "max": null,
                  "min": null,
                  "name": "end_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The completion time of the task, in the format: 2006-01-02 15:04:05\n",
                    "zh_Hans": "任务完成时间，格式为：2006-01-02 15:04:05"
                  },
                  "label": {
                    "en_US": "Completed Time",
                    "zh_Hans": "任务完成时间"
                  },
                  "llm_description": "任务完成时间，格式为：2006-01-02 15:04:05",
                  "max": null,
                  "min": null,
                  "name": "completed_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Add Lark Members",
                  "zh_Hans": "添加 Lark 任务成员"
                },
                "llm": "A tool for adding members to a Lark task.(添加 Lark 任务成员)"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Add Lark Members",
                  "zh_Hans": "添加 Lark 任务成员"
                },
                "name": "add_members"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The GUID of the task to be added, supports passing either the Task ID or the Task link URL. Example of Task ID: 8b5425ec-9f2a-43bd-a3ab-01912f50282b; Example of Task link URL: https://applink.larksuite.com/client/todo/detail?guid=1b066afa-96de-406c-90a3-dfd30159a571&suite_entity_num=t100805\n",
                    "zh_Hans": "要添加的任务的 GUID，支持传任务 ID 和任务链接 URL。任务 ID 示例：8b5425ec-9f2a-43bd-a3ab-01912f50282b；任务链接 URL 示例：https://applink.larksuite.com/client/todo/detail?guid=1b066afa-96de-406c-90a3-dfd30159a571&suite_entity_num=t100805"
                  },
                  "label": {
                    "en_US": "Task GUID",
                    "zh_Hans": "任务 GUID"
                  },
                  "llm_description": "要添加的任务的 GUID，支持传任务 ID 和任务链接 URL。任务 ID 示例：8b5425ec-9f2a-43bd-a3ab-01912f50282b；任务链接 URL 示例：https://applink.larksuite.com/client/todo/detail?guid=1b066afa-96de-406c-90a3-dfd30159a571&suite_entity_num=t100805",
                  "max": null,
                  "min": null,
                  "name": "task_guid",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "A list of member emails or phone numbers, separated by commas.",
                    "zh_Hans": "任务成员邮箱或者手机号列表，使用逗号分隔。"
                  },
                  "label": {
                    "en_US": "Task Member Phone Or Email",
                    "zh_Hans": "任务成员的电话或邮箱"
                  },
                  "llm_description": "任务成员邮箱或者手机号列表，使用逗号分隔。",
                  "max": null,
                  "min": null,
                  "name": "member_phone_or_email",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "follower",
                  "form": "form",
                  "human_description": {
                    "en_US": "Member role, optional values are \"assignee\" (responsible person) and \"follower\" (observer), with a default value of \"assignee\".",
                    "zh_Hans": "成员的角色，可选值有 \"assignee\"（负责人）和 \"follower\"（关注人），默认值为 \"assignee\"。"
                  },
                  "label": {
                    "en_US": "member_role",
                    "zh_Hans": "成员的角色"
                  },
                  "llm_description": "成员的角色，可选值有 \"assignee\"（负责人）和 \"follower\"（关注人），默认值为 \"assignee\"。",
                  "max": null,
                  "min": null,
                  "name": "member_role",
                  "options": [
                    {
                      "label": {
                        "en_US": "assignee",
                        "zh_Hans": "负责人"
                      },
                      "value": "assignee"
                    },
                    {
                      "label": {
                        "en_US": "follower",
                        "zh_Hans": "关注人"
                      },
                      "value": "follower"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-02-26T10:38:36Z",
        "version_updated_at": "2025-02-26T10:38:36Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Search for high-quality photos on Unsplash and get random photos",
          "ja_JP": "Unsplashで高品質な写真を検索してランダムな写真を取得",
          "pt_BR": "Pesquise fotos de alta qualidade no Unsplash e obtenha fotos aleatórias",
          "zh_Hans": "在Unsplash上搜索高质量图片并获取随机图片"
        },
        "category": "tool",
        "created_at": "2025-04-09T09:03:35Z",
        "endpoint": {},
        "icon": "stvlynn/packages/unsplash/_assets/icon.svg",
        "index_id": "stvlynn___unsplash",
        "install_count": 130,
        "introduction": "# Unsplash Plugin\n\n**Author:** [Steven Lynn](https://github.com/stvlynn)\n**Version:** 0.0.1\n**Type:** extension\n\n## Description\n\nThis plugin provides integration with Unsplash API to search and retrieve high-quality photos. It includes two main tools:\n1. **Unsplash Search Tool**: Search for photos by keywords with optional filters\n2. **Unsplash Random Tool**: Get random photos with optional filters\n\n## Features\n\n- Search Unsplash photos by keywords\n- Get random photos from Unsplash\n- Filter results by orientation and color\n- Download photos directly in your workflow\n- Detailed photo metadata including dimensions, author info, and license\n\n## Installation\n\n1. Install the plugin from Dify Marketplace\n2. Navigate to **Plugins** section in your Dify workspace\n3. Find the \"Unsplash\" plugin and click \"Install\"\n4. Configure your Unsplash API credentials\n\n## Configuration\n\nYou need to provide your Unsplash API access key in the plugin credentials:\n1. Go to Plugin settings\n2. Add your Unsplash API access key\n3. Save the configuration\n\n## Usage\n\n### Search Tool Parameters\n\n![](./_assets/search_photos.png)\n\n- **query** (required): Search keywords\n- **per_page** (optional): Number of results per page (1-30, default 10)\n- **orientation** (optional): Filter by orientation (landscape, portrait, squarish)\n- **color** (optional): Filter by hex color code\n\n### Random Tool Parameters\n\n![](./_assets/random_photo.png)\n\n- **count** (optional): Number of random photos (1-30, default 1)\n- **query** (optional): Filter by keywords\n- **orientation** (optional): Filter by orientation\n- **color** (optional): Filter by color\n\n## License\n\n[MIT License](./LICENSE)\n\n## Feedback and Issues\n\nIf you encounter any problems or have suggestions for improvements:\n\n1. Please open an issue in the [plugin's GitHub repository](https://github.com/stvlynn/Unsplash-Dify-Plugin/issues)\n\n2. Provide details about your problem, including error messages and steps to reproduce\n\n3. **Do not** submit issues to the main [Dify](https://github.com/langgenius/dify) repository for plugin-specific problems\n\n\n\n",
        "label": {
          "en_US": "Unsplash",
          "ja_JP": "Unsplash",
          "pt_BR": "Unsplash",
          "zh_Hans": "Unsplash图片搜索"
        },
        "latest_package_identifier": "stvlynn/unsplash:0.0.1@6ffa915ed26ce525a028b27b2f2eb2f8c235585a756ed14fa3fee64b04b283b0",
        "latest_version": "0.0.1",
        "model": {},
        "name": "unsplash",
        "org": "stvlynn",
        "plugin_id": "stvlynn/unsplash",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/unsplash.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": false,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Get your Unsplash Access Key from Unsplash Developer Portal",
                "pt_BR": "Obtenha sua Chave de Acesso Unsplash no Portal do Desenvolvedor Unsplash",
                "zh_Hans": "从Unsplash开发者门户获取您的访问密钥"
              },
              "label": {
                "en_US": "Unsplash Access Key",
                "pt_BR": "Chave de Acesso Unsplash",
                "zh_Hans": "Unsplash访问密钥"
              },
              "name": "access_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Unsplash Access Key",
                "pt_BR": "Por favor, insira sua Chave de Acesso Unsplash",
                "zh_Hans": "请输入您的Unsplash访问密钥"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://unsplash.com/developers"
            }
          ],
          "identity": {
            "author": "stvlynn",
            "description": {
              "en_US": "Search for high-quality photos on Unsplash",
              "pt_BR": "Pesquise fotos de alta qualidade no Unsplash",
              "zh_Hans": "在Unsplash上搜索高质量图片"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Unsplash",
              "pt_BR": "Unsplash",
              "zh_Hans": "Unsplash图片搜索"
            },
            "name": "unsplash",
            "tags": [
              "image",
              "search"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Search for high-quality photos on Unsplash based on keywords",
                  "pt_BR": "Pesquise fotos de alta qualidade no Unsplash com base em palavras-chave",
                  "zh_Hans": "根据关键词在Unsplash上搜索高质量图片"
                },
                "llm": "A tool for searching high-quality photos on Unsplash. Input should be a search query or keywords."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "stvlynn",
                "label": {
                  "en_US": "Search Photos",
                  "pt_BR": "Pesquisar Fotos",
                  "zh_Hans": "搜索图片"
                },
                "name": "search"
              },
              "output_schema": {
                "properties": {
                  "photos": {
                    "items": {
                      "properties": {
                        "alt_description": {
                          "type": "string"
                        },
                        "description": {
                          "type": "string"
                        },
                        "id": {
                          "type": "string"
                        },
                        "links": {
                          "type": "object"
                        },
                        "urls": {
                          "type": "object"
                        },
                        "user": {
                          "type": "object"
                        }
                      },
                      "type": "object"
                    },
                    "type": "array"
                  }
                },
                "type": "object"
              },
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Keywords to search for photos",
                    "pt_BR": "Palavras-chave para pesquisar fotos",
                    "zh_Hans": "用于搜索图片的关键词"
                  },
                  "label": {
                    "en_US": "Search Query",
                    "pt_BR": "Consulta de Pesquisa",
                    "zh_Hans": "搜索关键词"
                  },
                  "llm_description": "The search query or keywords to find photos on Unsplash",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 10,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Number of photos to return (max 30)",
                    "pt_BR": "Número de fotos a retornar (máximo 30)",
                    "zh_Hans": "返回的图片数量（最多30张）"
                  },
                  "label": {
                    "en_US": "Results Per Page",
                    "pt_BR": "Resultados Por Página",
                    "zh_Hans": "每页结果数"
                  },
                  "llm_description": "Number of photos to return in the results (maximum 30)",
                  "max": null,
                  "min": null,
                  "name": "per_page",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Filter by photo orientation",
                    "pt_BR": "Filtrar por orientação de foto",
                    "zh_Hans": "按照图片方向过滤"
                  },
                  "label": {
                    "en_US": "Orientation",
                    "pt_BR": "Orientação",
                    "zh_Hans": "图片方向"
                  },
                  "llm_description": "Filter photos by orientation (landscape, portrait, squarish)",
                  "max": null,
                  "min": null,
                  "name": "orientation",
                  "options": [
                    {
                      "label": {
                        "en_US": "Landscape",
                        "pt_BR": "Paisagem",
                        "zh_Hans": "横向"
                      },
                      "value": "landscape"
                    },
                    {
                      "label": {
                        "en_US": "Portrait",
                        "pt_BR": "Retrato",
                        "zh_Hans": "纵向"
                      },
                      "value": "portrait"
                    },
                    {
                      "label": {
                        "en_US": "Square",
                        "pt_BR": "Quadrado",
                        "zh_Hans": "方形"
                      },
                      "value": "squarish"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Filter by dominant color in the photo",
                    "pt_BR": "Filtrar pela cor dominante na foto",
                    "zh_Hans": "按照图片主色调过滤"
                  },
                  "label": {
                    "en_US": "Color",
                    "pt_BR": "Cor",
                    "zh_Hans": "颜色"
                  },
                  "llm_description": "Filter results by color",
                  "max": null,
                  "min": null,
                  "name": "color",
                  "options": [
                    {
                      "label": {
                        "en_US": "Black and White",
                        "pt_BR": "Preto e Branco",
                        "zh_Hans": "黑白"
                      },
                      "value": "black_and_white"
                    },
                    {
                      "label": {
                        "en_US": "Black",
                        "pt_BR": "Preto",
                        "zh_Hans": "黑色"
                      },
                      "value": "black"
                    },
                    {
                      "label": {
                        "en_US": "White",
                        "pt_BR": "Branco",
                        "zh_Hans": "白色"
                      },
                      "value": "white"
                    },
                    {
                      "label": {
                        "en_US": "Yellow",
                        "pt_BR": "Amarelo",
                        "zh_Hans": "黄色"
                      },
                      "value": "yellow"
                    },
                    {
                      "label": {
                        "en_US": "Orange",
                        "pt_BR": "Laranja",
                        "zh_Hans": "橙色"
                      },
                      "value": "orange"
                    },
                    {
                      "label": {
                        "en_US": "Red",
                        "pt_BR": "Vermelho",
                        "zh_Hans": "红色"
                      },
                      "value": "red"
                    },
                    {
                      "label": {
                        "en_US": "Purple",
                        "pt_BR": "Roxo",
                        "zh_Hans": "紫色"
                      },
                      "value": "purple"
                    },
                    {
                      "label": {
                        "en_US": "Magenta",
                        "pt_BR": "Magenta",
                        "zh_Hans": "品红"
                      },
                      "value": "magenta"
                    },
                    {
                      "label": {
                        "en_US": "Green",
                        "pt_BR": "Verde",
                        "zh_Hans": "绿色"
                      },
                      "value": "green"
                    },
                    {
                      "label": {
                        "en_US": "Teal",
                        "pt_BR": "Azul-petróleo",
                        "zh_Hans": "青色"
                      },
                      "value": "teal"
                    },
                    {
                      "label": {
                        "en_US": "Blue",
                        "pt_BR": "Azul",
                        "zh_Hans": "蓝色"
                      },
                      "value": "blue"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Get a random high-quality photo from Unsplash",
                  "pt_BR": "Obtenha uma foto aleatória de alta qualidade do Unsplash",
                  "zh_Hans": "从Unsplash获取一张随机高质量图片"
                },
                "llm": "A tool for getting random high-quality photos from Unsplash. You can specify topics, orientation, and more."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "stvlynn",
                "label": {
                  "en_US": "Random Photo",
                  "pt_BR": "Foto Aleatória",
                  "zh_Hans": "随机图片"
                },
                "name": "random_photo"
              },
              "output_schema": {
                "properties": {
                  "photos": {
                    "items": {
                      "properties": {
                        "alt_description": {
                          "type": "string"
                        },
                        "description": {
                          "type": "string"
                        },
                        "id": {
                          "type": "string"
                        },
                        "links": {
                          "type": "object"
                        },
                        "urls": {
                          "type": "object"
                        },
                        "user": {
                          "type": "object"
                        }
                      },
                      "type": "object"
                    },
                    "type": "array"
                  }
                },
                "type": "object"
              },
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional keywords to filter random photos by topic",
                    "pt_BR": "Palavras-chave opcionais para filtrar fotos aleatórias por tópico",
                    "zh_Hans": "可选的关键词，用于按主题筛选随机图片"
                  },
                  "label": {
                    "en_US": "Search Query",
                    "pt_BR": "Consulta de Pesquisa",
                    "zh_Hans": "搜索关键词"
                  },
                  "llm_description": "Optional keywords to filter random photos by topic or category",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Filter by photo orientation",
                    "pt_BR": "Filtrar por orientação de foto",
                    "zh_Hans": "按照图片方向过滤"
                  },
                  "label": {
                    "en_US": "Orientation",
                    "pt_BR": "Orientação",
                    "zh_Hans": "图片方向"
                  },
                  "llm_description": "Filter photos by orientation (landscape, portrait, squarish)",
                  "max": null,
                  "min": null,
                  "name": "orientation",
                  "options": [
                    {
                      "label": {
                        "en_US": "Landscape",
                        "pt_BR": "Paisagem",
                        "zh_Hans": "横向"
                      },
                      "value": "landscape"
                    },
                    {
                      "label": {
                        "en_US": "Portrait",
                        "pt_BR": "Retrato",
                        "zh_Hans": "纵向"
                      },
                      "value": "portrait"
                    },
                    {
                      "label": {
                        "en_US": "Square",
                        "pt_BR": "Quadrado",
                        "zh_Hans": "方形"
                      },
                      "value": "squarish"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Filter by dominant color in the photo",
                    "pt_BR": "Filtrar pela cor dominante na foto",
                    "zh_Hans": "按照图片主色调过滤"
                  },
                  "label": {
                    "en_US": "Color",
                    "pt_BR": "Cor",
                    "zh_Hans": "颜色"
                  },
                  "llm_description": "Filter results by color",
                  "max": null,
                  "min": null,
                  "name": "color",
                  "options": [
                    {
                      "label": {
                        "en_US": "Black and White",
                        "pt_BR": "Preto e Branco",
                        "zh_Hans": "黑白"
                      },
                      "value": "black_and_white"
                    },
                    {
                      "label": {
                        "en_US": "Black",
                        "pt_BR": "Preto",
                        "zh_Hans": "黑色"
                      },
                      "value": "black"
                    },
                    {
                      "label": {
                        "en_US": "White",
                        "pt_BR": "Branco",
                        "zh_Hans": "白色"
                      },
                      "value": "white"
                    },
                    {
                      "label": {
                        "en_US": "Yellow",
                        "pt_BR": "Amarelo",
                        "zh_Hans": "黄色"
                      },
                      "value": "yellow"
                    },
                    {
                      "label": {
                        "en_US": "Orange",
                        "pt_BR": "Laranja",
                        "zh_Hans": "橙色"
                      },
                      "value": "orange"
                    },
                    {
                      "label": {
                        "en_US": "Red",
                        "pt_BR": "Vermelho",
                        "zh_Hans": "红色"
                      },
                      "value": "red"
                    },
                    {
                      "label": {
                        "en_US": "Purple",
                        "pt_BR": "Roxo",
                        "zh_Hans": "紫色"
                      },
                      "value": "purple"
                    },
                    {
                      "label": {
                        "en_US": "Magenta",
                        "pt_BR": "Magenta",
                        "zh_Hans": "品红"
                      },
                      "value": "magenta"
                    },
                    {
                      "label": {
                        "en_US": "Green",
                        "pt_BR": "Verde",
                        "zh_Hans": "绿色"
                      },
                      "value": "green"
                    },
                    {
                      "label": {
                        "en_US": "Teal",
                        "pt_BR": "Azul-petróleo",
                        "zh_Hans": "青色"
                      },
                      "value": "teal"
                    },
                    {
                      "label": {
                        "en_US": "Blue",
                        "pt_BR": "Azul",
                        "zh_Hans": "蓝色"
                      },
                      "value": "blue"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 1,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Number of random photos to return (max 30)",
                    "pt_BR": "Número de fotos aleatórias a retornar (máximo 30)",
                    "zh_Hans": "返回的随机图片数量（最多30张）"
                  },
                  "label": {
                    "en_US": "Count",
                    "pt_BR": "Quantidade",
                    "zh_Hans": "数量"
                  },
                  "llm_description": "Number of random photos to return (maximum 30)",
                  "max": null,
                  "min": null,
                  "name": "count",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-09T09:03:43Z",
        "version_updated_at": "2025-04-09T09:03:43Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "kintone Plugin",
          "ja_JP": "kintone Plugin",
          "pt_BR": "kintone Plugin",
          "zh_Hans": "kintone Plugin"
        },
        "category": "tool",
        "created_at": "2025-03-05T04:08:32Z",
        "endpoint": {},
        "icon": "r3-yamauchi/packages/kintone_integration/_assets/icon.svg",
        "index_id": "r3-yamauchi___kintone_integration",
        "install_count": 127,
        "introduction": "# kintone_integration\n\n**Author:** r3-yamauchi\n**Version:** 0.0.5\n**Type:** tool\n\n## Description\n\nThis is a plugin for interacting with [kintone](https://kintone.cybozu.co.jp/) apps. By using this plugin, you can easily access and manage the information stored in your kintone app.\n\n## Features\n\n- Retrieve records by specifying the kintone domain and app ID.\n- Filter records by passing a query string to retrieve only specific records.\n- Limit the retrieved fields to avoid unnecessary data collection.\n- Add new records to your kintone app with custom field values.\n- Update or insert multiple records at once (upsert) to your kintone app with custom field values.\n- Download files from your kintone app using file keys.\n\n## Prerequisites\n\n- An API token with appropriate permissions for the target kintone app:\n  - View permissions for retrieving records\n  - Add permissions for adding new records\n  - Update permissions for updating existing records\n\n## Configuration\n\nThis plugin has no configuration settings.\n\n## Usage Examples\n\n### 1. kintone Query\n\n#### 1. Retrieve all records from the specified kintone app:\n\n```json\n{\n  \"kintone_domain\": \"dev-demo.cybozu.com\",\n  \"kintone_app_id\": 123,\n  \"kintone_api_token\": \"abcdefghijklmnopqrstuvwxyz\"\n}\n```\n\n#### 2. Retrieve only records where the value of `field1` is 100 or higher:\n\n```json\n{\n  \"kintone_domain\": \"dev-demo.cybozu.com\",\n  \"kintone_app_id\": 123,\n  \"kintone_api_token\": \"abcdefghijklmnopqrstuvwxyz\",\n  \"query\": \"field1 >= 100\"\n}\n```\n\n#### 3. Retrieve only the values of the specified fields:\n\n```json\n{\n  \"kintone_domain\": \"dev-demo.cybozu.com\",\n  \"kintone_app_id\": 123,\n  \"kintone_api_token\": \"abcdefghijklmnopqrstuvwxyz\",\n  \"fields\": \"field1, field2, field3\"\n}\n```\n\n### 2. kintone Add Record\n\n#### 1. Add a new record to the kintone app:\n\n```json\n{\n  \"kintone_domain\": \"dev-demo.cybozu.com\",\n  \"kintone_app_id\": 123,\n  \"kintone_api_token\": \"abcdefghijklmnopqrstuvwxyz\",\n  \"record_data\": {\n    \"text_field\": {\"value\": \"サンプルテキスト\"},\n    \"number_field\": {\"value\": \"100\"},\n    \"date_field\": {\"value\": \"2025-03-09\"}\n  }\n}\n```\n\n### 3. kintone Upsert Records\n\n#### 1. Add multiple new records to the kintone app:\n\n```json\n{\n  \"kintone_domain\": \"dev-demo.cybozu.com\",\n  \"kintone_app_id\": 123,\n  \"kintone_api_token\": \"abcdefghijklmnopqrstuvwxyz\",\n  \"records_data\": {\n    \"records\": [\n      {\n        \"record\": {\n          \"text_field\": {\"value\": \"サンプルテキスト1\"},\n          \"number_field\": {\"value\": \"100\"},\n          \"date_field\": {\"value\": \"2025-03-09\"}\n        }\n      },\n      {\n        \"record\": {\n          \"text_field\": {\"value\": \"サンプルテキスト2\"},\n          \"number_field\": {\"value\": \"200\"},\n          \"date_field\": {\"value\": \"2025-03-10\"}\n        }\n      }\n    ]\n  }\n}\n```\n\n#### 2. Update existing records using updateKey:\n\n```json\n{\n  \"kintone_domain\": \"dev-demo.cybozu.com\",\n  \"kintone_app_id\": 123,\n  \"kintone_api_token\": \"abcdefghijklmnopqrstuvwxyz\",\n  \"records_data\": {\n    \"records\": [\n      {\n        \"updateKey\": {\n          \"field\": \"key_field\",\n          \"value\": \"unique_value_1\"\n        },\n        \"record\": {\n          \"text_field\": {\"value\": \"更新テキスト1\"},\n          \"number_field\": {\"value\": \"150\"}\n        }\n      },\n      {\n        \"updateKey\": {\n          \"field\": \"key_field\",\n          \"value\": \"unique_value_2\"\n        },\n        \"record\": {\n          \"text_field\": {\"value\": \"更新テキスト2\"},\n          \"number_field\": {\"value\": \"250\"}\n        }\n      }\n    ]\n  }\n}\n```\n\n#### 3. Mix of updates and additions in a single request:\n\n```json\n{\n  \"kintone_domain\": \"dev-demo.cybozu.com\",\n  \"kintone_app_id\": 123,\n  \"kintone_api_token\": \"abcdefghijklmnopqrstuvwxyz\",\n  \"records_data\": {\n    \"records\": [\n      {\n        \"updateKey\": {\n          \"field\": \"key_field\",\n          \"value\": \"existing_value\"\n        },\n        \"record\": {\n          \"text_field\": {\"value\": \"更新されたテキスト\"},\n          \"number_field\": {\"value\": \"300\"}\n        }\n      },\n      {\n        \"record\": {\n          \"key_field\": {\"value\": \"new_value\"},\n          \"text_field\": {\"value\": \"新規テキスト\"},\n          \"number_field\": {\"value\": \"400\"}\n        }\n      }\n    ]\n  }\n}\n```\n\n## Field Format for Adding Records\n\nWhen adding records using the `kintone_add_record` tool, you need to follow kintone's field format. Here are some common field types and their formats:\n\n### Text Field (SINGLE_LINE_TEXT, MULTI_LINE_TEXT)\n```json\n\"field_code\": {\"value\": \"テキスト値\"}\n```\n\n### Number Field (NUMBER)\n```json\n\"field_code\": {\"value\": \"123\"}\n```\n\n### Date Field (DATE)\n```json\n\"field_code\": {\"value\": \"2025-03-09\"}\n```\n\n### Time Field (TIME)\n```json\n\"field_code\": {\"value\": \"12:34\"}\n```\n\n### Datetime Field (DATETIME)\n```json\n\"field_code\": {\"value\": \"2025-03-09T12:34:56Z\"}\n```\n\n### Checkbox Field (CHECK_BOX)\n```json\n\"field_code\": {\"value\": [\"選択肢1\", \"選択肢2\"]}\n```\n\n### Radio Button Field (RADIO_BUTTON)\n```json\n\"field_code\": {\"value\": \"選択肢1\"}\n```\n\n### Dropdown Field (DROP_DOWN)\n```json\n\"field_code\": {\"value\": \"選択肢1\"}\n```\n\n### Multi-select Field (MULTI_SELECT)\n```json\n\"field_code\": {\"value\": [\"選択肢1\", \"選択肢2\"]}\n```\n\n### User Selection Field (USER_SELECT)\n```json\n\"field_code\": {\"value\": [{\"code\": \"user1\", \"type\": \"USER\"}]}\n```\n\n### Department Selection Field (ORGANIZATION_SELECT)\n```json\n\"field_code\": {\"value\": [{\"code\": \"dept1\", \"type\": \"ORGANIZATION\"}]}\n```\n\n### Group Selection Field (GROUP_SELECT)\n```json\n\"field_code\": {\"value\": [{\"code\": \"group1\", \"type\": \"GROUP\"}]}\n```\n\n### 4. kintone Download File\n\n#### 1. Download a file from kintone using file key:\n\n```json\n{\n  \"kintone_domain\": \"dev-demo.cybozu.com\",\n  \"kintone_api_token\": \"abcdefghijklmnopqrstuvwxyz\",\n  \"file_key\": \"20250301010101E3C4F3D8871A4BA28360BA3F798D0455165\"\n}\n```\n\n#### File Key Retrieval\n\nTo get the file key:\n1. Use the `kintone_query` tool to retrieve records with attachment fields\n2. Look for the attachment field value in the response (e.g., `\"添付ファイル\": [{\"fileKey\": \"xxxxxxxx\"}]`)\n3. Use the `fileKey` value as the `file_key` parameter for this tool\n\n## Privacy Policy\n\nThis plugin only collects the following necessary information for interacting with kintone:\n\n1. kintone domain, app ID, and API token with appropriate permissions\n2. User-provided query parameters for filtering records and selecting fields\n3. User-provided record data for adding or updating records\n\nThis information is used solely for retrieving records from the specified kintone app and will not be used for other purposes or shared with third parties.\n\nData retrieval uses kintone's official REST API. For related privacy policies, please refer to: [cybozu.com Terms of Use](https://www.cybozu.com/jp/terms/).\n\n## Support\n\nIf you encounter any issues or have questions, please:\n\n1. Raise an issue on the GitHub repository\n2. Contact the plugin author\n",
        "label": {
          "en_US": "kintone_integration",
          "ja_JP": "kintone_integration",
          "pt_BR": "kintone_integration",
          "zh_Hans": "kintone_integration"
        },
        "latest_package_identifier": "r3-yamauchi/kintone_integration:0.0.5@154632d35c58cffe19466d6ef929ff53be3ec6aa60559579211b27f32ab0d5ba",
        "latest_version": "0.0.5",
        "model": {},
        "name": "kintone_integration",
        "org": "r3-yamauchi",
        "plugin_id": "r3-yamauchi/kintone_integration",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/kintone_provider.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "r3-yamauchi",
            "description": {
              "en_US": "kintone Plugin",
              "ja_JP": "kintone プラグイン",
              "pt_BR": "kintone Plugin",
              "zh_Hans": "kintone Plugin"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "kintone",
              "ja_JP": "kintone",
              "pt_BR": "kintone",
              "zh_Hans": "kintone"
            },
            "name": "kintone",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Query records from kintone app",
                  "ja_JP": "kintoneアプリからレコードを検索",
                  "pt_BR": "Query records from kintone app",
                  "zh_Hans": "Query records from kintone app"
                },
                "llm": "Query records from kintone app"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "r3-yamauchi",
                "label": {
                  "en_US": "kintone Query",
                  "ja_JP": "kintone クエリ",
                  "pt_BR": "kintone Query",
                  "zh_Hans": "kintone Query"
                },
                "name": "kintone_query"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Your kintone domain (e.g., your-subdomain.cybozu.com)",
                    "ja_JP": "お使いのkintoneのURLのうち、https:// より後ろの部分（例: your-subdomain.cybozu.com）"
                  },
                  "label": {
                    "en_US": "kintone Domain",
                    "ja_JP": "cybozu.com ドメイン"
                  },
                  "llm_description": "kintone domain where the app is hosted",
                  "max": null,
                  "min": null,
                  "name": "kintone_domain",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of your kintone application",
                    "ja_JP": "使用するkintoneアプリのID"
                  },
                  "label": {
                    "en_US": "kintone App ID",
                    "ja_JP": "kintone アプリID"
                  },
                  "llm_description": "ID of the kintone app to query",
                  "max": null,
                  "min": null,
                  "name": "kintone_app_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "API token generated from your kintone app",
                    "ja_JP": "kintone アプリで発行したAPIトークン"
                  },
                  "label": {
                    "en_US": "kintone API Token",
                    "ja_JP": "対象の kintoneアプリの APIトークン"
                  },
                  "llm_description": "API token with view permissions for the kintone app",
                  "max": null,
                  "min": null,
                  "name": "kintone_api_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Keyword or text to search in kintone",
                    "ja_JP": "kintoneへ渡すquery文字列",
                    "pt_BR": "Keyword or text to search in kintone",
                    "zh_Hans": "Keyword or text to search in kintone"
                  },
                  "label": {
                    "en_US": "Query string",
                    "ja_JP": "kintoneへ渡すquery文字列",
                    "pt_BR": "Query string",
                    "zh_Hans": "查询语句"
                  },
                  "llm_description": "Query string to filter records in kintone query format",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Comma-separated list of field names to retrieve from kintone (e.g., field1,field2,field3)",
                    "ja_JP": "kintoneから取得するフィールド名をカンマ区切りで指定（例: フィールド1,フィールド2,フィールド3）"
                  },
                  "label": {
                    "en_US": "Fields to retrieve",
                    "ja_JP": "取得するフィールド"
                  },
                  "llm_description": "Comma-separated list of field names to retrieve from kintone records",
                  "max": null,
                  "min": null,
                  "name": "fields",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Add a record to kintone app",
                  "ja_JP": "kintoneアプリにレコードを追加",
                  "pt_BR": "Add a record to kintone app",
                  "zh_Hans": "Add a record to kintone app"
                },
                "llm": "Add a record to kintone app"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "r3-yamauchi",
                "label": {
                  "en_US": "kintone Add Record",
                  "ja_JP": "kintone レコード追加",
                  "pt_BR": "kintone Add Record",
                  "zh_Hans": "kintone Add Record"
                },
                "name": "kintone_add_record"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Your kintone domain (e.g., your-subdomain.cybozu.com)",
                    "ja_JP": "お使いのkintoneのURLのうち、https:// より後ろの部分（例: your-subdomain.cybozu.com）"
                  },
                  "label": {
                    "en_US": "kintone Domain",
                    "ja_JP": "cybozu.com ドメイン"
                  },
                  "llm_description": "kintone domain where the app is hosted",
                  "max": null,
                  "min": null,
                  "name": "kintone_domain",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of your kintone application",
                    "ja_JP": "使用するkintoneアプリのID"
                  },
                  "label": {
                    "en_US": "kintone App ID",
                    "ja_JP": "kintone アプリID"
                  },
                  "llm_description": "ID of the kintone app to add records to",
                  "max": null,
                  "min": null,
                  "name": "kintone_app_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "API token generated from your kintone app with add record permission",
                    "ja_JP": "kintone アプリで発行した追加権限を持つAPIトークン"
                  },
                  "label": {
                    "en_US": "kintone API Token",
                    "ja_JP": "対象の kintoneアプリの APIトークン"
                  },
                  "llm_description": "API token with add record permission for the kintone app",
                  "max": null,
                  "min": null,
                  "name": "kintone_api_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "JSON format data to add as a new record (e.g., {\"field_code1\": {\"value\": \"value1\"}, \"field_code2\": {\"value\": \"value2\"}})",
                    "ja_JP": "新規レコードとして追加するJSONフォーマットのデータ（例: {\"フィールドコード1\": {\"value\": \"値1\"}, \"フィールドコード2\": {\"value\": \"値2\"}}）"
                  },
                  "label": {
                    "en_US": "Record Data",
                    "ja_JP": "レコードデータ"
                  },
                  "llm_description": "JSON format data to add as a new record in kintone",
                  "max": null,
                  "min": null,
                  "name": "record_data",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Update or insert multiple records to kintone app",
                  "ja_JP": "kintoneアプリに複数レコードを更新または追加",
                  "pt_BR": "Update or insert multiple records to kintone app",
                  "zh_Hans": "Update or insert multiple records to kintone app"
                },
                "llm": "Update or insert multiple records to kintone app"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "r3-yamauchi",
                "label": {
                  "en_US": "kintone Upsert Records",
                  "ja_JP": "kintone レコード一括更新/追加",
                  "pt_BR": "kintone Upsert Records",
                  "zh_Hans": "kintone Upsert Records"
                },
                "name": "kintone_upsert_records"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Your kintone domain (e.g., your-subdomain.cybozu.com)",
                    "ja_JP": "お使いのkintoneのURLのうち、https:// より後ろの部分（例: your-subdomain.cybozu.com）"
                  },
                  "label": {
                    "en_US": "kintone Domain",
                    "ja_JP": "cybozu.com ドメイン"
                  },
                  "llm_description": "kintone domain where the app is hosted",
                  "max": null,
                  "min": null,
                  "name": "kintone_domain",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of your kintone application",
                    "ja_JP": "使用するkintoneアプリのID"
                  },
                  "label": {
                    "en_US": "kintone App ID",
                    "ja_JP": "kintone アプリID"
                  },
                  "llm_description": "ID of the kintone app to update or add records to",
                  "max": null,
                  "min": null,
                  "name": "kintone_app_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "API token generated from your kintone app with update and add record permissions",
                    "ja_JP": "kintone アプリで発行した更新・追加権限を持つAPIトークン"
                  },
                  "label": {
                    "en_US": "kintone API Token",
                    "ja_JP": "対象の kintoneアプリの APIトークン"
                  },
                  "llm_description": "API token with update and add record permissions for the kintone app",
                  "max": null,
                  "min": null,
                  "name": "kintone_api_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "JSON format data for multiple records. For updates, include 'updateKey' field. Format: {\"records\": [{\"updateKey\": {\"field\": \"field_code\", \"value\": \"value\"}, \"record\": {\"field_code1\": {\"value\": \"value1\"}}}, ...]}",
                    "ja_JP": "複数レコードのJSONフォーマットデータ。更新の場合は'updateKey'フィールドを含めてください。形式: {\"records\": [{\"updateKey\": {\"field\": \"フィールドコード\", \"value\": \"値\"}, \"record\": {\"フィールドコード1\": {\"value\": \"値1\"}}}, ...]}"
                  },
                  "label": {
                    "en_US": "Records Data",
                    "ja_JP": "レコードデータ"
                  },
                  "llm_description": "JSON format data for multiple records to update or insert in kintone. For updates, include 'updateKey' field.",
                  "max": null,
                  "min": null,
                  "name": "records_data",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Download a file from kintone using file key",
                  "ja_JP": "kintoneからファイルをダウンロードします\n\n【file_keyの取得方法】\n1. kintone_queryツールを使用してレコードを取得します\n2. 添付ファイルフィールドの値を確認します（例: \"添付ファイル\": [{\"fileKey\": \"xxxxxxxx\"}]）\n3. fileKeyの値をこのツールのfile_keyパラメータに指定します",
                  "pt_BR": "Baixe um arquivo do kintone usando a chave do arquivo",
                  "zh_Hans": "使用文件密钥从kintone下载文件"
                },
                "llm": "Download a file from kintone using the file key identifier"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "r3-yamauchi",
                "label": {
                  "en_US": "kintone Download File",
                  "ja_JP": "kintone ファイルダウンロード",
                  "pt_BR": "kintone Baixar Arquivo",
                  "zh_Hans": "kintone 下载文件"
                },
                "name": "kintone_download_file"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Your kintone domain (e.g., your-subdomain.cybozu.com)",
                    "ja_JP": "お使いのkintoneのURLのうち、https:// より後ろの部分（例: your-subdomain.cybozu.com）",
                    "pt_BR": "O domínio do seu kintone (ex. your-subdomain.cybozu.com)",
                    "zh_Hans": "您的kintone域名（例如 your-subdomain.cybozu.com）"
                  },
                  "label": {
                    "en_US": "kintone Domain",
                    "ja_JP": "kintone ドメイン",
                    "pt_BR": "Domínio kintone",
                    "zh_Hans": "kintone 域名"
                  },
                  "llm_description": "kintone domain where the file is hosted",
                  "max": null,
                  "min": null,
                  "name": "kintone_domain",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "API token generated from your kintone app with view permissions",
                    "ja_JP": "kintone アプリで発行した閲覧権限を持つAPIトークン",
                    "pt_BR": "Token de API gerado do seu aplicativo kintone com permissões de visualização",
                    "zh_Hans": "从您的kintone应用程序生成的具有查看权限的API令牌"
                  },
                  "label": {
                    "en_US": "kintone API Token",
                    "ja_JP": "kintone APIトークン",
                    "pt_BR": "Token de API kintone",
                    "zh_Hans": "kintone API 令牌"
                  },
                  "llm_description": "API token with view permissions for the kintone app",
                  "max": null,
                  "min": null,
                  "name": "kintone_api_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The file key of the file to download from kintone",
                    "ja_JP": "kintoneからダウンロードするファイルのファイルキー",
                    "pt_BR": "A chave do arquivo a ser baixado do kintone",
                    "zh_Hans": "要从kintone下载的文件的文件密钥"
                  },
                  "label": {
                    "en_US": "File Key",
                    "ja_JP": "ファイルキー",
                    "pt_BR": "Chave do Arquivo",
                    "zh_Hans": "文件密钥"
                  },
                  "llm_description": "The unique file key identifier for the file in kintone",
                  "max": null,
                  "min": null,
                  "name": "file_key",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-11T17:59:22Z",
        "version_updated_at": "2025-03-11T17:59:22Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "A Telegraph plugin that allow you publish your content easily",
          "ja_JP": "コンテンツを簡単に公開できるTelegraphプラグイン",
          "pt_BR": "Um plugin do Telegraph que permite publicar seu conteúdo facilmente",
          "zh_Hans": "一个让您轻松发布内容的Telegraph插件"
        },
        "category": "tool",
        "created_at": "2025-01-14T03:39:54Z",
        "endpoint": {},
        "icon": "langgenius/packages/telegraph/_assets/icon.jpg",
        "index_id": "langgenius___telegraph",
        "install_count": 127,
        "introduction": "## Overview\n\n**Telegraph** is a simple yet powerful plugin that allows you to create richly formatted posts and publish them on the web with just one click. **Telegraph** posts also get beautiful [Instant View](https://telegram.org/blog/instant-view) pages on **Telegram**.\n\nThis means you can automatically publish results generated by Dify Apps to Telegraph, turning them into publicly accessible internet content.\n\n## Configuration\n\nTo set up Telegraph, follow these steps:\n\n1. **Install Telegraph Tool**\nAccess the Plugin Marketplace and install it.\n\n2. **Apply for a Telegraph API Key**\nGo to the [Telegraph API Keys](https://telegra.ph/api#createAccount) page, create a new API Key, and ensure your account has sufficient balance.\n\n3. **Authorize Telegraph**\nNavigate to **Plugins > Telegraph > To Authorize** in Dify, and input your API Key to enable the tool.\n\n![](./_assets/telegraph-01.png)\n\nYou need to request a URL to get your Telegraph pages' access API. For more details about Telegraph, please check it here.\n\n![](./_assets/telegraph-02.png)\n\n## Usage\n\n### Telegraph\n\nThe basic Telegraph action enables you to publish content with minimal setup. Ideal for users who want a fast and straightforward publishing experience. Input your **Post title / Post content** to publish it directly.\n\n<img src=\"./_assets/telegraph-03.png\" width=\"400\" />\n\n### Telegraph Advanced\n\nThe advanced mode allows for more control over the publishing process, including:\n\n* **Post Title** (*String, Required*): Define the title of the post. This is a mandatory field that will appear as the headline of your published content.\n* **Post Content** (*String, Required*): Add the main body of the post. This is a required field containing the core content to be published.\n* **Author Name** (*String, Optional*): Specify the name of the author to display below the article's title. If provided, this will override the default author's name associated with the account.\n* **Author URL** (*String, Optional*): Provide a URL to link the author's name. This link will open when users click on the author's name below the title. If provided, it replaces the default profile link. Ensure the URL starts with `http://` or `https:/`\n* **Alternative Telegraph Access Token** (*String, Optional*): Use a different Telegraph access token for this specific post. This allows you to post under an account other than the default one associated with the tool.\n\n<img src=\"./_assets/telegraph-04.png\" width=\"400\" />\n\n## Usage\n\nTelegraph can seamlessly integrate **Chatflow / Workflow Apps** and **Agent Apps**.\n\n### Chatflow / Workflow Apps\n\n1. Add the Telegraph node to your Chatflow or Workflow pipeline.\n2. Select either the **Telegraph** or **Telegraph Advanced** action, depending on your needs.\n3. Input the content and configure additional settings (for Telegraph Advanced).\n4. You can go ahead and execute the pipeline to publish the content directly.\n\n![](./_assets/telegraph-05.png)\n\n### Agent Apps\n\nTelegraph can be seamlessly integrated into an Agent App to enable dynamic, real-time content publishing:\n\n1. Add the **Telegraph** tool to the Agent application.\n2. Input the post title, author name, and content directly into the chat.\n3. The LLM will publish the content on Telegraph as you instructed and provide a URL linking to the online document.\n\nThis streamlined process ensures fast and effective publishing, making your content available online.\n\n![](./_assets/telegraph-06.png)\n\n## Use Cases\n\n* **Quick Content Sharing**: Use Telegraph for fast, minimal-effort publishing of blog posts, announcements, or updates.\n* **Customizable Publishing**: Leverage Telegraph Advanced for personalized layouts, metadata, or integration with external systems.\n* **Automation**: Integrate Telegraph into workflows for automated content generation and publication.\n",
        "label": {
          "en_US": "Telegraph",
          "ja_JP": "Telegraph",
          "pt_BR": "Telegraph",
          "zh_Hans": "Telegraph"
        },
        "latest_package_identifier": "langgenius/telegraph:0.0.5@9353dc6a9d5496cb627d2bd20895169a70ed6da49fde967de80ff73e937addd5",
        "latest_version": "0.0.5",
        "model": {},
        "name": "telegraph",
        "org": "langgenius",
        "plugin_id": "langgenius/telegraph",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/telegraph.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "How to get your Telegraph access token",
                "ja_JP": "Telegraphアクセストークンの取得方法",
                "pt_BR": "Como obter seu token de acesso do Telegraph",
                "zh_Hans": "如何获取 Telegraph 访问令牌"
              },
              "label": {
                "en_US": "Telegraph Access Token",
                "ja_JP": "Telegraphアクセストークン",
                "pt_BR": "Token de Acesso do Telegraph",
                "zh_Hans": "Telegraph 访问令牌"
              },
              "name": "telegraph_access_token",
              "options": null,
              "placeholder": {
                "en_US": "Enter your Telegraph access token",
                "ja_JP": "Telegraphアクセストークンを入力してください",
                "pt_BR": "Digite seu token de acesso do Telegraph",
                "zh_Hans": "请输入您的 Telegraph 访问令牌"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://telegra.ph/api#createAccount"
            }
          ],
          "identity": {
            "author": "langgenius",
            "description": {
              "en_US": "A Telegraph plugin that allows you to publish your content easily",
              "ja_JP": "コンテンツを簡単に公開できるTelegraphプラグイン",
              "pt_BR": "Um plugin do Telegraph que permite publicar seu conteúdo facilmente",
              "zh_Hans": "一个让您轻松发布内容的Telegraph插件"
            },
            "icon": "icon.jpg",
            "label": {
              "en_US": "Telegraph",
              "pt_BR": "Telegraph",
              "zh_Hans": "Telegraph"
            },
            "name": "telegraph",
            "tags": [
              "productivity",
              "utilities"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A simple telegraph plugin that allow you publish your content easily",
                  "pt_BR": "Um plugin telegraph simples que permite publicar seu conteúdo facilmente",
                  "zh_Hans": "一个简单的 telegraph 插件，可以让您轻松发布内容"
                },
                "llm": "A simple telegraph plugin that allow you publish your content easily, your content will be published to telegraph, the format of the content you providing should be in markdown."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Telegraph",
                  "pt_BR": "Telegraph",
                  "zh_Hans": "Telegraph"
                },
                "name": "telegraph"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The title of the post",
                    "pt_BR": "O título do post",
                    "zh_Hans": "文章标题"
                  },
                  "label": {
                    "en_US": "Post title",
                    "pt_BR": "Título do post",
                    "zh_Hans": "文章标题"
                  },
                  "llm_description": "The title of the post, should be pure plain text, short and meaningful.",
                  "max": null,
                  "min": null,
                  "name": "p_title",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The content of the post",
                    "pt_BR": "O conteúdo do post",
                    "zh_Hans": "文章内容"
                  },
                  "label": {
                    "en_US": "Post content",
                    "pt_BR": "Conteúdo do post",
                    "zh_Hans": "文章内容"
                  },
                  "llm_description": "The content of the post, should be in markdown format.",
                  "max": null,
                  "min": null,
                  "name": "p_content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A Telegraph plugin that allows you to publish your content with custom settings",
                  "ja_JP": "カスタム設定でコンテンツを公開できるTelegraphプラグイン",
                  "pt_BR": "Um plugin do Telegraph que permite publicar seu conteúdo com configurações personalizadas",
                  "zh_Hans": "一个允许您使用自定义设置发布内容的Telegraph插件"
                },
                "llm": "A telegraph plugin that allows you to publish content as posts. Your content will be published to Telegraph, and the content you provide should be in markdown format."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Telegraph Advanced",
                  "ja_JP": "Telegraph アドバンスド",
                  "pt_BR": "Telegraph Avançado",
                  "zh_Hans": "Telegraph 高级版"
                },
                "name": "telegraph_advanced"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The title of the post",
                    "ja_JP": "投稿のタイトル",
                    "pt_BR": "O título da publicação",
                    "zh_Hans": "文章的标题"
                  },
                  "label": {
                    "en_US": "Post Title",
                    "ja_JP": "投稿タイトル",
                    "pt_BR": "Título da Publicação",
                    "zh_Hans": "文章标题"
                  },
                  "llm_description": "The title of the post, should be pure plain text, short and meaningful.",
                  "max": null,
                  "min": null,
                  "name": "p_title",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The content of the post",
                    "ja_JP": "投稿の内容",
                    "pt_BR": "O conteúdo da publicação",
                    "zh_Hans": "文章的内容"
                  },
                  "label": {
                    "en_US": "Post Content",
                    "ja_JP": "投稿内容",
                    "pt_BR": "Conteúdo da Publicação",
                    "zh_Hans": "文章内容"
                  },
                  "llm_description": "The content of the post, should be in markdown format.",
                  "max": null,
                  "min": null,
                  "name": "p_content",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The Telegraph Access Token for temporary replacement. This article will use this account (Token) instead of the default account for publication.",
                    "ja_JP": "一時的な代替用のTelegraphアクセストークン。この記事は、デフォルトアカウントの代わりにこのアカウント（トークン）を使用して公開されます。",
                    "pt_BR": "O Token de Acesso do Telegraph para substituição temporária. Este artigo usará esta conta (Token) em vez da conta padrão para publicação.",
                    "zh_Hans": "临时替代的Telegraph访问令牌。本文将使用此账号（令牌）而不是默认账号来发布。"
                  },
                  "label": {
                    "en_US": "Alternative Telegraph Access Token",
                    "ja_JP": "代替のTelegraphアクセストークン",
                    "pt_BR": "Token de Acesso Alternativo do Telegraph",
                    "zh_Hans": "替代Telegraph访问令牌"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "a_telegraph_access_token",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional. Author name displayed below the article's title. This will replace the default name associated with the account.",
                    "ja_JP": "オプション。記事のタイトルの下に表示される著者名。アカウントに関連付けられているデフォルトの名前を置き換えます。",
                    "pt_BR": "Opcional. Nome do autor exibido abaixo do título do artigo. Isso substituirá o nome padrão associado à conta.",
                    "zh_Hans": "可选。显示在文章标题下方的作者姓名。这将替换与账号关联的默认名称。"
                  },
                  "label": {
                    "en_US": "Author Name",
                    "ja_JP": "著者名",
                    "pt_BR": "Nome do Autor",
                    "zh_Hans": "作者姓名"
                  },
                  "llm_description": "Author name, 0-128 characters in length. If not provided, the default name associated with the account will be used.",
                  "max": null,
                  "min": null,
                  "name": "a_author_name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional. Profile link for the author, opened when users click on the author's name below the title. This will replace the default link associated with the account. Please provide a valid URL, usually start with http:// or https://.",
                    "ja_JP": "オプション。タイトルの下の著者名をクリックした時に開くプロフィールリンク。アカウントに関連付けられているデフォルトのリンクを置き換えます。有効なURL（通常はhttp://またはhttps://で始まる）を入力してください。",
                    "pt_BR": "Link do perfil do autor, aberto quando os usuários clicam no nome do autor abaixo do título. Isso substituirá o link padrão associado à conta. Forneça um URL válido, geralmente começando com http:// ou https://.",
                    "zh_Hans": "可选。作者的个人资料链接，用户点击标题下方的作者姓名时打开。这将替换与账号关联的默认链接。请提供有效的URL，通常以http://或https://开头。"
                  },
                  "label": {
                    "en_US": "Author URL",
                    "ja_JP": "著者URL",
                    "pt_BR": "URL do Autor",
                    "zh_Hans": "作者链接"
                  },
                  "llm_description": "Profile link for the author, 0-512 characters in length. Can be any link, not necessarily a Telegram profile or channel link. If not provided, the default link associated with the account will be used. Please provide a valid URL, usually start with http:// or https://.",
                  "max": null,
                  "min": null,
                  "name": "a_author_url",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-25T02:27:48Z",
        "version_updated_at": "2025-03-25T02:27:48Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Save notes to Blinko service",
          "ja_JP": "Save notes to Blinko service",
          "pt_BR": "Save notes to Blinko service",
          "zh_Hans": "将笔记内容保存到Blinko服务"
        },
        "category": "tool",
        "created_at": "2025-04-01T21:20:26Z",
        "endpoint": {},
        "icon": "blinkosapce/packages/blinko/_assets/icon.png",
        "index_id": "blinkosapce___blinko",
        "install_count": 124,
        "introduction": "# Blinko Plugin for Dify\n\nThis Dify plugin allows you to save notes to the Blinko service.\n\n## Features\n\n- Save text notes to Blinko service\n\n## Prerequisites\n\nBefore using this plugin, you need to:\n\n1. Obtain a Blinko service access token\n2. Copy `.env.example` to `.env` and fill in your token\n\n## Environment Variables\n\n- `BLINKO_TOKEN`: Your Blinko access token (required)\n- `BLINKO_DOMAIN`: Blinko service domain (required)\n\n## Usage\n\nAfter installing the plugin, you can use it through Dify's tool functionality to save notes. Simply provide the note content as a query parameter.\n\n## Developer Information\n\n- Author: blinkosapce\n\n**Author:** blinkosapce\n**Version:** 0.0.1\n**Type:** tool\n\n### Description\n\nA tool plugin for Dify that enables saving notes to the Blinko service. The plugin provides a simple interface for users to save their notes and manage them through the Blinko platform.\n\n\n\n",
        "label": {
          "en_US": "Blinko",
          "ja_JP": "Blinko",
          "pt_BR": "Blinko",
          "zh_Hans": "Blinko笔记"
        },
        "latest_package_identifier": "blinkosapce/blinko:0.0.1@80d7a9f8a118ca708b14e6f756da1b586eca3cbde5664f29ac6f0a5d234f8425",
        "latest_version": "0.0.1",
        "model": {},
        "name": "blinko",
        "org": "blinkosapce",
        "plugin_id": "blinkosapce/blinko",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/blinko.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {}
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Blinko Token",
                "zh_Hans": "Blinko访问令牌"
              },
              "name": "BLINKO_TOKEN",
              "options": null,
              "placeholder": {
                "en_US": "Your Blinko API Token",
                "zh_Hans": "您的Blinko API令牌"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Blinko Domain",
                "zh_Hans": "Blinko服务域名"
              },
              "name": "BLINKO_DOMAIN",
              "options": null,
              "placeholder": {
                "en_US": "your domain",
                "zh_Hans": "您的域名"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            }
          ],
          "identity": {
            "author": "blinkosapce",
            "description": {
              "en_US": "Save notes to Blinko service",
              "pt_BR": "Save notes to Blinko service",
              "zh_Hans": "将笔记内容保存到Blinko服务"
            },
            "icon": "icon.png",
            "label": {
              "en_US": "Blinko",
              "pt_BR": "Blinko",
              "zh_Hans": "Blinko笔记"
            },
            "name": "blinko",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Save notes to Blinko",
                  "pt_BR": "Save notes to Blinko",
                  "zh_Hans": "将笔记内容保存到Blinko"
                },
                "llm": "A tool for saving notes to Blinko service"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "blinkosapce",
                "label": {
                  "en_US": "Blinko",
                  "pt_BR": "Blinko",
                  "zh_Hans": "Blinko笔记"
                },
                "name": "Blinko"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The content of the note to be saved",
                    "pt_BR": "The content of the note to be saved",
                    "zh_Hans": "要保存的笔记内容"
                  },
                  "label": {
                    "en_US": "Note content",
                    "pt_BR": "Note content",
                    "zh_Hans": "笔记内容"
                  },
                  "llm_description": "The text content to be saved as a note in Blinko",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-01T21:20:33Z",
        "version_updated_at": "2025-04-01T21:20:33Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "The Agora Conversational AI extension enables developers to build voice assistants powered by Dify Agent.",
          "ja_JP": "Agora会話型AI拡張機能は、開発者がDify Agentを活用して高機能な音声アシスタントを構築できるようにします。",
          "pt_BR": "A extensão de IA Conversacional da Agora permite que desenvolvedores criem assistentes de voz poderosos com o suporte do Dify Agent.",
          "zh_Hans": "Agora 会话式 AI 插件让开发者能够借助 Dify Agent 构建功能强大的语音助手。"
        },
        "category": "extension",
        "created_at": "2025-03-31T07:12:39Z",
        "endpoint": {
          "endpoints": [
            {
              "hidden": false,
              "method": "POST",
              "path": "/convoai/<action>"
            },
            {
              "hidden": false,
              "method": "GET",
              "path": "/convoai-token/<channel>/<uid>"
            },
            {
              "hidden": false,
              "method": "GET",
              "path": "/convoai-web/<file>"
            }
          ],
          "settings": [
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "App",
                "pt_BR": "App",
                "zh_Hans": "App"
              },
              "name": "app",
              "options": null,
              "placeholder": null,
              "required": true,
              "scope": "chat",
              "type": "app-selector",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Agora App ID",
                "pt_BR": "Agora App ID",
                "zh_Hans": "Agora App ID"
              },
              "name": "agora_app_id",
              "options": null,
              "placeholder": {
                "en_US": "App ID for your Agora project",
                "pt_BR": "App ID for your Agora project",
                "zh_Hans": "你的 Agora 项目的 App ID"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Agora RESTful Customer ID",
                "pt_BR": "Agora RESTful Customer ID",
                "zh_Hans": "Agora RESTful 鉴权 ID"
              },
              "name": "agora_restful_customer_id",
              "options": null,
              "placeholder": {
                "en_US": "This value is used to authenticate your Agora RESTful API",
                "pt_BR": "This value is used to authenticate your Agora RESTful API",
                "zh_Hans": "这个值用于鉴权你的 Agora RESTful API"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Agora RESTful Customer Secret",
                "pt_BR": "Agora RESTful Customer Secret",
                "zh_Hans": "Agora RESTful 鉴权 Secret"
              },
              "name": "agora_restful_customer_secret",
              "options": null,
              "placeholder": {
                "en_US": "This value is used to authenticate your Agora RESTful API",
                "pt_BR": "This value is used to authenticate your Agora RESTful API",
                "zh_Hans": "这个值用于鉴权你的 Agora RESTful API"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "TTS Vendor",
                "pt_BR": "TTS tts_vendor",
                "zh_Hans": "TTS 供应商"
              },
              "name": "tts_vendor",
              "options": [
                {
                  "label": {
                    "en_US": "ElevenLabs",
                    "pt_BR": "ElevenLabs",
                    "zh_Hans": "ElevenLabs"
                  },
                  "value": "elevenlabs"
                },
                {
                  "label": {
                    "en_US": "Azure",
                    "pt_BR": "Azure",
                    "zh_Hans": "Azure"
                  },
                  "value": "microsoft"
                }
              ],
              "placeholder": null,
              "required": true,
              "scope": null,
              "type": "select",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "TTS Params",
                "pt_BR": "TTS Params",
                "zh_Hans": "TTS 参数"
              },
              "name": "tts_params",
              "options": null,
              "placeholder": {
                "en_US": "TTS Params in JSON format",
                "pt_BR": "TTS Params in JSON format",
                "zh_Hans": "TTS 参数以 JSON 格式填写"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Greeting Message",
                "pt_BR": "Greeting Message",
                "zh_Hans": "欢迎语"
              },
              "name": "greeting_message",
              "options": null,
              "placeholder": {
                "en_US": "This message will be sent to the user when they first start the conversation",
                "pt_BR": "This message will be sent to the user when they first start the conversation",
                "zh_Hans": "这个消息会在用户第一次开始对话时发送给用户"
              },
              "required": false,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Failure Message",
                "pt_BR": "Failure Message",
                "zh_Hans": "错误信息"
              },
              "name": "failure_message",
              "options": null,
              "placeholder": {
                "en_US": "This message will be sent to the user when the conversation has error",
                "pt_BR": "This message will be sent to the user when the conversation has error",
                "zh_Hans": "这个消息会在对话出现错误时发送给用户"
              },
              "required": false,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Agora App Certificate",
                "pt_BR": "Agora App Certificate",
                "zh_Hans": "Agora App Certificate"
              },
              "name": "agora_app_cert",
              "options": null,
              "placeholder": {
                "en_US": "This value is only needed when you have turned on security token for your Agora project",
                "pt_BR": "This value is only needed when you have turned on security token for your Agora project",
                "zh_Hans": "只有在你开启了 Agora 安全Token时才需要填写"
              },
              "required": false,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "API key",
                "pt_BR": "API key",
                "zh_Hans": "API key"
              },
              "name": "api_key",
              "options": null,
              "placeholder": {
                "en_US": "This is used to protect your API endpoint",
                "pt_BR": "This is used to protect your API endpoint",
                "zh_Hans": "这个值用于保护你的 API Endpoint"
              },
              "required": false,
              "scope": null,
              "type": "secret-input",
              "url": null
            }
          ]
        },
        "icon": "qz/packages/convoai/_assets/icon.svg",
        "index_id": "qz___convoai",
        "install_count": 122,
        "introduction": "## Agora Conversational AI\r\n\r\n**Author:** plutoless\r\n**Version:** 0.0.7\r\n**Type:** extension\r\n\r\n### Description\r\n\r\n#### Overview\r\n\r\nThis extension provides an endpoint to make Dify agents work with Agora’s Conversational AI Engine to easily turn your Dify agents into voice assistants.\r\n\r\n#### Prerequisites\r\n\r\n- **Agora Account**\r\n    You need an Agora account to use the Agora Conversational AI service. You can sign up for a free account at [Agora](https://sso.agora.io/en/signup/).\r\n- **Agora App ID / App Certificate / RESTful Customer ID / RESTful Customer Secret**\r\n    You need to create an Agora project and get the App ID, App Certificate, RESTful Customer ID and RESTful Customer Secret from [Agora Console](https://console.agora.io/v2). Note to enable the Agora Conversational AI service in the Agora Console.\r\n- **TTS Vendor Account**\r\n    You need an account for the TTS vendor you choose. The TTS vendor provides the voice synthesis service for the voice assistant. \r\n\r\n#### Configuration\r\n\r\n- **APP**\r\n    To turn a Dify agent into a voice assistant, choose one from your agent library.\r\n- **Agora App ID**\r\n    In the [Agora Console](https://console.agora.io/v2), get your Agora App ID and enable the Conversational AI Engine service.\r\n- **Agora RESTful Customer ID**\r\n   In the [Agora Console](https://console.agora.io/v2), get the Agora RESTful Customer ID.\r\n- **Agora RESTful Customer Secret**\r\n   In the [Agora Console](https://console.agora.io/v2), get the Agora RESTful Customer Secret.\r\n- **TTS Vendor**\r\n    The TTS vendor to use for voice synthesis. Choose one from the list below.\r\n  - **Azure**\r\n  - **ElevenLabs**\r\n- **TTS Vendor Params**\r\n    The parameters for the TTS vendor. The parameters are different for each vendor, please refer to the vendor's documentation for more information.\r\n  - **Azure**\r\n\r\n    ```json\r\n    {\r\n        \"key\": \"<your api key>\",\r\n        \"region\": \"eastasia\",\r\n        \"voice_name\": \"en-US-AndrewMultilingualNeural\"\r\n    }\r\n    ```\r\n\r\n  - **ElevenLabs**\r\n\r\n    ```json\r\n    {\r\n        \"key\": \"<your api key>\",\r\n        \"model_id\": \"eleven_flash_v2_5\",\r\n        \"voice_id\": \"pNInz6obpgDQGcFmaJgB\"\r\n    }\r\n    ```\r\n\r\n- **Greeting Message**\r\n    The message to greet the user when the conversation starts.\r\n- **Failure Message**\r\n    The message to tell the user when the conversation fails.\r\n- **Agora App Certificate**\r\n    The Agora App Certificate to use for RTC service. Get it from [Agora Console](https://console.agora.io/v2). Only needed when security token is enabled for your Agora project.\r\n- **API Key**\r\n    The API Key to protect your Dify endpoint.\r\n\r\n#### Usage\r\n\r\nOnce you finish the configuration, you'll fnd the APl in the endpoint as follows:\r\n\r\n`https://qv90***.ai-plugin.io/convoai-web/<file>`\r\n\r\nReplace `<file>` with `index.html`,\r\n\r\nThen you may navigate to the following URL to access the integrated Conversational Al web page.\r\n\r\n`https://qv90***.ai-plugin.io/convoai-web/index.html`\r\n\r\n#### Using API without Web Page\r\n\r\nYou can also use the API directly without the web page. The API endpoint is:\r\n\r\n##### Start Conversation\r\n\r\nAPI Endpoint: `https://qv90***.ai-plugin.io/convoai-start`\r\n\r\n| key | value |\r\n| --- | --- |\r\n| base_url | The base url of the extension |\r\n| channel | The channel id of the extension |\r\n\r\nExample cURL:\r\n\r\n```bash\r\ncurl 'https://qv90***.ai-plugin.io/convoai/convoai-start' \\\r\n  -H 'accept: application/json, text/plain, */*' \\\r\n  -H 'accept-language: zh,en;q=0.9,zh-CN;q=0.8' \\\r\n  -H 'cache-control: no-cache' \\\r\n  -H 'content-type: application/json' \\\r\n  --data-raw '{\"base_url\":\"https://qv90***.ai-plugin.io\",\"channel\":\"jh0y8fgk7\"}'\r\n```\r\n\r\n##### Stop Conversation\r\n\r\nAPI Endpoint: `https://qv90***.ai-plugin.io/convoai-stop`\r\n\r\n| key | value |\r\n| --- | --- |\r\n| agent_id | The agent id of the extension |\r\n\r\nExample cURL:\r\n\r\n```bash\r\ncurl 'https://qv90***.ai-plugin.io/convoai/convoai-stop' \\\r\n  -H 'accept: application/json, text/plain, */*' \\\r\n  -H 'accept-language: zh,en;q=0.9,zh-CN;q=0.8' \\\r\n  -H 'cache-control: no-cache' \\\r\n  -H 'content-type: application/json' \\\r\n  --data-raw '{\"agent_id\":\"1NT29X0ZX0JYPJ96CCL8F4Y4VUEGR566\"}'\r\n```\r\n",
        "label": {
          "en_US": "Agora Conversational AI",
          "ja_JP": "Agora Conversational AI",
          "pt_BR": "Agora Conversational AI",
          "zh_Hans": "Agora Conversational AI"
        },
        "latest_package_identifier": "qz/convoai:0.0.7@6895aef2b14c24bff990d890193463945056914b97c245152a192bc8c7cc7fa0",
        "latest_version": "0.0.7",
        "model": {},
        "name": "convoai",
        "org": "qz",
        "plugin_id": "qz/convoai",
        "plugins": {
          "agent_strategies": null,
          "endpoints": [
            "group/convoai.yaml"
          ],
          "models": null,
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-03-31T07:12:45Z",
        "version_updated_at": "2025-03-31T07:12:45Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Get Minecraft server information",
          "ja_JP": "Minecraft サーバー情報を取得する",
          "pt_BR": "Obter informações do servidor Minecraft",
          "zh_Hans": "获取 Minecraft 服务器信息"
        },
        "category": "tool",
        "created_at": "2025-03-31T17:16:49Z",
        "endpoint": {},
        "icon": "lzy123/packages/mc_ping/_assets/icon.svg",
        "index_id": "lzy123___mc_ping",
        "install_count": 119,
        "introduction": "## mc_ping\n\n**Author:** lzy123\n**Version:** 0.0.4\n**Type:** tool\n\n### Description\n\n这个插件可以帮你获取Minecraft服务器的信息，支持SRV解析。\n让LLM传入HOTS（IP/域名）与端口（可选，默认为25565）。\n响应示例\n```json\n{\n    \"mc_ping\": {\n        \"data\": {\n            \"description\": \"服务器介绍\",\n            \"max\": 1024,\n            \"online\": 125,\n            \"queryTime\": \"2025-03-29 13:05:51\",\n            \"version\": \"1.21.5\"\n        },\n        \"status\": \"success\"\n    }\n}\n```\n\n---\n\n## mc_ping (English)\n\n**Author:** lzy123\n**Version:** 0.0.3\n**Type:** tool\n\n### Description\n\nThis plugin helps you retrieve information from Minecraft servers, with support for SRV resolution.\nLet the LLM input the HOST (IP/domain name) and port (optional, default is 25565).\nResponse example:\n```json\n{\n    \"mc_ping\": {\n        \"data\": {\n            \"description\": \"Server description\",\n            \"max\": 1024,\n            \"online\": 125,\n            \"queryTime\": \"2025-03-29 13:05:51\",\n            \"version\": \"1.21.5\"\n        },\n        \"status\": \"success\"\n    }\n}\n```\n\n",
        "label": {
          "en_US": "MC Server info",
          "ja_JP": "Minecraft サーバー情報",
          "pt_BR": "Informações do Servidor Minecraft",
          "zh_Hans": "Minecraft 服务器信息"
        },
        "latest_package_identifier": "lzy123/mc_ping:0.0.4@c05629d258b563b94658188677e98753d94285241c56ab78b0429a82e1da7ef4",
        "latest_version": "0.0.4",
        "model": {},
        "name": "mc_ping",
        "org": "lzy123",
        "plugin_id": "lzy123/mc_ping",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/mc_ping.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "lzy123",
            "description": {
              "en_US": "Get Minecraft server information",
              "pt_BR": "Get Minecraft server information",
              "zh_Hans": "Get Minecraft server information"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "mc_ping",
              "pt_BR": "mc_ping",
              "zh_Hans": "mc_ping"
            },
            "name": "mc_ping",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Get information about a Minecraft server including version, players, and status",
                  "pt_BR": "Obter informações sobre um servidor Minecraft, incluindo versão, jogadores e status",
                  "zh_Hans": "获取Minecraft服务器的版本、玩家数量和在线状态等信息"
                },
                "llm": "This tool allows you to retrieve information about a Minecraft server such as its version, online status, player count, and other details by providing the server address."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "lzy123",
                "label": {
                  "en_US": "Minecraft Server Info",
                  "pt_BR": "Informações do Servidor Minecraft",
                  "zh_Hans": "Minecraft服务器信息"
                },
                "name": "mc_ping"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Enter the Minecraft server address (e.g., mc.hypixel.net) to get information about it",
                    "pt_BR": "Digite o endereço do servidor Minecraft (ex： mc.hypixel.net) para obter informações sobre ele",
                    "zh_Hans": "输入Minecraft服务器地址（例如：mc.hypixel.net）以获取相关信息"
                  },
                  "label": {
                    "en_US": "Server Address",
                    "pt_BR": "Endereço do Servidor",
                    "zh_Hans": "服务器地址"
                  },
                  "llm_description": "The server address to query. This should be a valid Minecraft server address like 'mc.hypixel.net' or 'play.mydomain.com'. You can optionally include a port like 'mc.example.com:25565'.",
                  "max": null,
                  "min": null,
                  "name": "host",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional port number for the Minecraft server (default is 25565)",
                    "pt_BR": "Número da porta opcional para o servidor Minecraft (padrão é 25565)",
                    "zh_Hans": "Minecraft服务器的可选端口号（默认是25565）"
                  },
                  "label": {
                    "en_US": "port",
                    "pt_BR": "Porta",
                    "zh_Hans": "端口"
                  },
                  "llm_description": "Optional port number for the Minecraft server. If not specified, the default port 25565 will be used.",
                  "max": null,
                  "min": null,
                  "name": "port",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-31T17:16:56Z",
        "version_updated_at": "2025-03-31T17:16:56Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Post, delete tweets and perform other operations via X API",
          "ja_JP": "X APIを通じて投稿、削除などの操作を行います",
          "zh_Hans": "通过X API发帖、删帖等操作"
        },
        "category": "tool",
        "created_at": "2025-04-15T11:27:49Z",
        "endpoint": {},
        "icon": "stvlynn/packages/x/_assets/icon.jpg",
        "index_id": "stvlynn___x",
        "install_count": 115,
        "introduction": "## X (formerly Twitter) Dify Plugin\n\n**Author:** [Steven Lynn](https://github.com/stvlynn)\n**Version:** 0.0.1\n**Type:** tool\n\n### Description\n\nThis plugin allows you to interact with the X (formerly Twitter) platform through their official API. \n\nIt provides tools to send and delete tweets.\n\n### Features\n\n- **Post Tweet**: Send tweets to your X account and receive the tweet ID in response\n- **Delete Tweet**: Delete tweets by their ID\n- **Post Media Tweet**: Send tweets with media attachments (images or videos)\n\n### Setup\n\n1. Create a developer account at [X Developer Portal](https://developer.twitter.com/)\n2. Create a project and app to obtain your API keys:\n   - Go to the [Developer Portal Dashboard](https://developer.twitter.com/en/portal/dashboard)\n   - Click \"Create Project\" and follow the steps\n   ![](./_assets/app_permission.png)\n   - Within your project, create an app to get your API keys and tokens\n   - Navigate to the \"Keys and tokens\" section to find your Consumer Keys (API Key and Secret)\n   ![](./_assets/consumer_key.png)\n3. Set up authentication:\n   - Clone this repository to your local machine:\n     ```\n     git clone https://github.com/stvlynn/X-Dify-Plugin.git\n     cd X-Dify-Plugin\n     ```\n   - Edit the `auth.py` file and fill in your Consumer Key and Secret\n   ![](./_assets/script.png)\n   - Run the authentication script:\n     ```\n     python auth.py\n     ```\n   - The script will provide an authorization URL. Open it in your browser\n   - Authorize your application and enter the verification code when prompted\n   ![](./_assets/verification.png)\n   - The script will output your ACCESS_TOKEN and ACCESS_TOKEN_SECRET\n4. Configure the plugin in Dify:\n   - Install the X Plugin from the Dify Marketplace\n   - In the plugin settings, enter the following credentials:\n     - **API Key**: Your X API Key (Consumer Key)\n     - **API Secret**: Your X API Secret (Consumer Secret)\n     - **Access Token**: OAuth 1.0a Access Token generated from auth.py\n     - **Access Token Secret**: OAuth 1.0a Access Token Secret generated from auth.py\n\n### Authentication Notes\n\n- All credentials are stored securely and used only for authenticating with the X API\n- You need Read and Write permissions for your app to post and delete tweets\n- To verify your credentials are working, the plugin will make a test API call to the X API\n\n### Usage\n\n#### Posting a Tweet\n\n![](./_assets/post.png)\n\n```json\n{\n  \"text\": \"Your tweet content here\"\n}\n```\n\nResponse:\n```json\n{\n  \"status\": \"success\",\n  \"tweet_id\": \"1234567890123456789\",\n  \"text\": \"Your tweet content here\",\n  \"message\": \"Tweet published successfully with ID: 1234567890123456789\"\n}\n```\n\n#### Deleting a Tweet\n\n![](./_assets/delete.png)\n\n```json\n{\n  \"tweet_id\": \"1234567890123456789\"\n}\n```\n\nResponse:\n```json\n{\n  \"status\": \"success\",\n  \"message\": \"Tweet with ID 1234567890123456789 deleted successfully\"\n}\n```\n\n#### Posting a Media Tweet\n\nThis action allows you to upload and attach media (images or videos) to your tweets.\n\n![](./_assets/post_media.png)\n\nParameters:\n- `text`: The text content of your tweet (max 280 characters)\n- `media`: The media file to attach (image or video)\n\nSupported media formats:\n- Images: JPEG, PNG, GIF\n- Videos: MP4 (H.264 codec recommended)\n\nNote: Videos may take longer to process on X platform before the tweet is published.\n\n```json\n{\n  \"text\": \"Check out this awesome media!\",\n  \"media\": [Binary file data]\n}\n```\n\nResponse:\n```json\n{\n  \"status\": \"success\",\n  \"tweet_id\": \"1234567890123456789\",\n  \"text\": \"Check out this awesome media!\",\n  \"media_id\": \"9876543210987654321\",\n  \"message\": \"Tweet with media published successfully with ID: 1234567890123456789\"\n}\n```\n\n## Feedback and Issues\n\nIf you encounter any problems or have suggestions for improvements:\n\n1. Please open an issue in the [plugin's GitHub repository](https://github.com/stvlynn/X-Dify-Plugin/issues)\n\n2. Provide details about your problem, including error messages and steps to reproduce\n\n3. **Do not** submit issues to the main [Dify](https://github.com/langgenius/dify) repository for plugin-specific problems\n\n## License\n\n[MIT](./LICENSE)",
        "label": {
          "en_US": "X (formerly Twitter)",
          "ja_JP": "X（旧Twitter）",
          "zh_Hans": "X（前Twitter）"
        },
        "latest_package_identifier": "stvlynn/x:0.0.1@3dce87528c8667c508f7741c844aa741b2f94b69c27e3000c9e9becf19718cff",
        "latest_version": "0.0.1",
        "model": {},
        "name": "x",
        "org": "stvlynn",
        "plugin_id": "stvlynn/x",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/x.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {}
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "API Key from your X developer account",
                "ja_JP": "XデベロッパーアカウントからのAPIキー",
                "zh_Hans": "您X开发者账户中的API密钥"
              },
              "label": {
                "en_US": "API Key",
                "ja_JP": "APIキー",
                "zh_Hans": "API密钥"
              },
              "name": "api_key",
              "options": null,
              "placeholder": {
                "en_US": "Your X API Key",
                "ja_JP": "あなたのX APIキー",
                "zh_Hans": "您的X API密钥"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://developer.twitter.com/en/portal/dashboard"
            },
            {
              "default": null,
              "help": {
                "en_US": "API Secret from your X developer account",
                "ja_JP": "XデベロッパーアカウントからのAPIシークレット",
                "zh_Hans": "您X开发者账户中的API密钥"
              },
              "label": {
                "en_US": "API Secret",
                "ja_JP": "APIシークレット",
                "zh_Hans": "API密钥"
              },
              "name": "api_secret",
              "options": null,
              "placeholder": {
                "en_US": "Your X API Secret",
                "ja_JP": "あなたのX APIシークレット",
                "zh_Hans": "您的X API密钥"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://developer.twitter.com/en/portal/dashboard"
            },
            {
              "default": null,
              "help": {
                "en_US": "OAuth 1.0a Access Token for your X app",
                "ja_JP": "XアプリのOAuth 1.0aアクセストークン",
                "zh_Hans": "您X应用的OAuth 1.0a访问令牌"
              },
              "label": {
                "en_US": "Access Token",
                "ja_JP": "アクセストークン",
                "zh_Hans": "访问令牌"
              },
              "name": "access_token",
              "options": null,
              "placeholder": {
                "en_US": "Your X Access Token",
                "ja_JP": "あなたのXアクセストークン",
                "zh_Hans": "您的X访问令牌"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://developer.twitter.com/en/portal/dashboard"
            },
            {
              "default": null,
              "help": {
                "en_US": "OAuth 1.0a Access Token Secret for your X app",
                "ja_JP": "XアプリのOAuth 1.0aアクセストークンシークレット",
                "zh_Hans": "您X应用的OAuth 1.0a访问令牌密钥"
              },
              "label": {
                "en_US": "Access Token Secret",
                "ja_JP": "アクセストークンシークレット",
                "zh_Hans": "访问令牌密钥"
              },
              "name": "access_token_secret",
              "options": null,
              "placeholder": {
                "en_US": "Your X Access Token Secret",
                "ja_JP": "あなたのXアクセストークンシークレット",
                "zh_Hans": "您的X访问令牌密钥"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://developer.twitter.com/en/portal/dashboard"
            }
          ],
          "identity": {
            "author": "stvlynn",
            "description": {
              "en_US": "Interact with the X (formerly Twitter) platform through their official API.",
              "ja_JP": "公式APIを通じてX（旧Twitter）プラットフォームと対話します。",
              "zh_Hans": "通过官方API与X（前Twitter）平台交互。"
            },
            "icon": "icon.jpg",
            "label": {
              "en_US": "X (formerly Twitter)",
              "ja_JP": "X（旧Twitter）",
              "zh_Hans": "X（前Twitter）"
            },
            "name": "x",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Post a tweet using the X API V2",
                  "ja_JP": "X API V2を使用してツイートを投稿します",
                  "zh_Hans": "使用X API V2发送推文"
                },
                "llm": "Send a tweet directly using the X API V2 endpoint /2/tweets"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "stvlynn",
                "label": {
                  "en_US": "Post Tweet",
                  "ja_JP": "ツイートを投稿",
                  "zh_Hans": "发送推文"
                },
                "name": "post_tweet"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The text content of your tweet (max 280 characters)",
                    "ja_JP": "ツイートの内容（最大280文字）",
                    "zh_Hans": "推文的内容（最多280个字符）"
                  },
                  "label": {
                    "en_US": "Tweet Text",
                    "ja_JP": "ツイート内容",
                    "zh_Hans": "推文内容"
                  },
                  "llm_description": "The text content of the tweet, limited to 280 characters. The tweet will be posted to the X account associated with the provided credentials.",
                  "max": null,
                  "min": null,
                  "name": "text",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Delete a tweet using the X API",
                  "ja_JP": "X APIを使用してツイートを削除します",
                  "zh_Hans": "使用X API删除推文"
                },
                "llm": "Delete an existing tweet using its ID via the X API V2 endpoint /2/tweets/:id"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "stvlynn",
                "label": {
                  "en_US": "Delete Tweet",
                  "ja_JP": "ツイートを削除",
                  "zh_Hans": "删除推文"
                },
                "name": "delete_tweet"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ID of the tweet to delete",
                    "ja_JP": "削除するツイートのID",
                    "zh_Hans": "要删除的推文的ID"
                  },
                  "label": {
                    "en_US": "Tweet ID",
                    "ja_JP": "ツイートID",
                    "zh_Hans": "推文ID"
                  },
                  "llm_description": "The ID of the tweet to delete, obtained when the tweet was published. Only tweets from the authenticated user can be deleted.",
                  "max": null,
                  "min": null,
                  "name": "tweet_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Post a tweet with media (image or video) using X API",
                  "ja_JP": "X APIを使用して画像や動画が含まれるツイートを投稿します",
                  "zh_Hans": "使用X API发送包含图片或视频的推文"
                },
                "llm": "Post a tweet with media (image or video) using the X API V2 endpoints"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "stvlynn",
                "label": {
                  "en_US": "Post Media Tweet",
                  "ja_JP": "メディア付きツイートを投稿",
                  "zh_Hans": "发送带媒体的推文"
                },
                "name": "media_tweet"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The text content of your tweet (max 280 characters)",
                    "ja_JP": "ツイートの内容（最大280文字）",
                    "zh_Hans": "推文的内容（最多280个字符）"
                  },
                  "label": {
                    "en_US": "Tweet Text",
                    "ja_JP": "ツイート内容",
                    "zh_Hans": "推文内容"
                  },
                  "llm_description": "The text content of the tweet, limited to 280 characters.",
                  "max": null,
                  "min": null,
                  "name": "text",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Image or video file to attach to the tweet",
                    "ja_JP": "ツイートに添付する画像または動画ファイル",
                    "zh_Hans": "添加到推文的图片或视频文件"
                  },
                  "label": {
                    "en_US": "Media File",
                    "ja_JP": "メディアファイル",
                    "zh_Hans": "媒体文件"
                  },
                  "llm_description": "Image (.jpg, .png, .gif) or video (.mp4) to attach to the tweet. Supported formats for X platform.",
                  "max": null,
                  "min": null,
                  "name": "media",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "file"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-15T11:28:07Z",
        "version_updated_at": "2025-04-15T11:28:07Z"
      },
      {
        "agent_strategy": null,
        "badges": [],
        "brief": {
          "en_US": "Generate meme-style images featuring famous personalities with AI-generated speech captions, similar to viral static background speech memes",
          "ja_JP": "有名人のスピーチミーム画像を生成し、AIで作成した字幕を追加することができます",
          "pt_BR": "Gere imagens estilo meme com personalidades famosas e legendas de discurso geradas por IA, semelhante aos memes virais de discurso com fundo estático",
          "zh_Hans": "生成类似于网络上流行的名人演讲静态背景图片，配以AI生成的演讲字幕，实现自动化制作演讲梗图"
        },
        "category": "tool",
        "created_at": "2024-12-18T07:53:42Z",
        "endpoint": {
          "endpoints": [
            {
              "method": "POST",
              "path": "/images/upload"
            },
            {
              "method": "GET",
              "path": "/"
            },
            {
              "method": "GET",
              "path": "/images/list"
            }
          ],
          "settings": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "API key",
                "pt_BR": "API key",
                "zh_Hans": "API key"
              },
              "name": "api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your API key",
                "pt_BR": "Please input your API key",
                "zh_Hans": "请输入你的 API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            }
          ]
        },
        "icon": "yixiao0/packages/fabricatedspeech/_assets/icon.svg",
        "index_id": "yixiao0___fabricatedspeech",
        "install_count": 102,
        "introduction": "## fabricatedspeech\n\n**Author:** yixiao0\n\n**Version:** 0.0.1\n\n**Date:** 2024-12-10\n\n**Type:** tool\n\n### Description\n\nGenerate meme-style images featuring famous personalities with AI-generated speech captions, similar to viral static background speech memes\n\n### Usage\n\n1. Select a character from the available list:\n   - Donald Trump\n   - Elon Musk\n   - Sam Altman\n   - BoJack Horseman\n   - Uncle Chan\n   - Jensen Huang\n2. Provide your desired speech content or let the AI generate one automatically.\n\n3. The tool will generate a meme-style image with:\n   - The selected character as the background\n   - The speech caption overlaid on the image\n   - Character-appropriate styling and formatting\n",
        "label": {
          "en_US": "fabricatedspeech",
          "ja_JP": "fabricatedspeech",
          "pt_BR": "fabricatedspeech",
          "zh_Hans": "fabricatedspeech"
        },
        "latest_package_identifier": "yixiao0/fabricatedspeech:0.0.1@e51fac5125e5aad9f0b05cf1dd404be6c63f673d6753fd07699fe0081b833d92",
        "latest_version": "0.0.1",
        "model": {},
        "name": "fabricatedspeech",
        "org": "yixiao0",
        "plugin_id": "yixiao0/fabricatedspeech",
        "plugins": {
          "endpoints": [
            "group/fabricatedspeech.yaml"
          ],
          "models": null,
          "tools": [
            "provider/fabricatedspeech.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "yixiao0",
            "description": {
              "en_US": "used to generate fabricated speeches",
              "pt_BR": "used to generate fabricated speeches",
              "zh_Hans": "used to generate fabricated speeches"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "fabricatedspeech",
              "pt_BR": "fabricatedspeech",
              "zh_Hans": "fabricatedspeech"
            },
            "name": "fabricatedspeech",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Generate viral meme-style images featuring famous personalities with AI-generated speech captions, similar to static background speech memes",
                  "zh_Hans": "生成类似于网络上流行的名人演讲静态背景图片，配以AI生成的演讲字幕，实现自动化制作演讲梗图"
                },
                "llm": "A tool for generating meme-style images with static backgrounds of wellknown personalities, overlaid with AI-generated speech captions"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "yixiao0",
                "label": {
                  "en_US": "AI Speech Meme Generator",
                  "zh_Hans": "AI演讲梗图生成器"
                },
                "name": "fabricatedspeech"
              },
              "output_schema": null,
              "parameters": [
                {
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Select a famous personality to generate a viral meme-style speech image with AI-generated captions (e.g., Donald Trump, Elon Musk, Jensen Huang, or Sam Altman)",
                    "zh_Hans": "选择一位知名人物来生成带有AI生成字幕的演讲梗图（例如特朗普、马斯克、黄仁勋或奥特曼）"
                  },
                  "label": {
                    "en_US": "LLM",
                    "zh_Hans": "LLM"
                  },
                  "llm_description": "Select a famous personality from Donald Trump, Elon Musk, Jensen Huang, or Sam Altman to generate a viral meme-style speech image with AI-generated captions",
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": null,
                  "required": true,
                  "scope": "llm",
                  "type": "model-selector"
                },
                {
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Select a famous personality to generate a viral meme-style speech image with AI-generated captions (e.g., Donald Trump, Elon Musk, Jensen Huang, or Sam Altman)",
                    "zh_Hans": "选择一位知名人物来生成带有AI生成字幕的演讲梗图（例如特朗普、马斯克、黄仁勋或奥特曼）"
                  },
                  "label": {
                    "en_US": "Character",
                    "zh_Hans": "人物"
                  },
                  "llm_description": "Select a famous personality from Donald Trump, Elon Musk, Jensen Huang, or Sam Altman to generate a viral meme-style speech image with AI-generated captions",
                  "max": null,
                  "min": null,
                  "name": "character",
                  "options": [
                    {
                      "label": {
                        "en_US": "Donald Trump",
                        "zh_Hans": "特朗普"
                      },
                      "value": "donald_trump"
                    },
                    {
                      "label": {
                        "en_US": "Elon Musk",
                        "zh_Hans": "马斯克"
                      },
                      "value": "elon_musk"
                    },
                    {
                      "label": {
                        "en_US": "Jensen Huang",
                        "zh_Hans": "黄仁勋"
                      },
                      "value": "jensen_huang"
                    },
                    {
                      "label": {
                        "en_US": "Sam Altman",
                        "zh_Hans": "奥特曼"
                      },
                      "value": "sam_altman"
                    },
                    {
                      "label": {
                        "en_US": "Uncle Chan",
                        "zh_Hans": "成龙历险记老爹"
                      },
                      "value": "uncle_chan"
                    },
                    {
                      "label": {
                        "en_US": "BoJack Horseman",
                        "zh_Hans": "马男波杰克"
                      },
                      "value": "bojack_horseman"
                    }
                  ],
                  "required": false,
                  "scope": null,
                  "type": "select"
                },
                {
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Description of the speech content",
                    "zh_Hans": "演讲内容的描述"
                  },
                  "label": {
                    "en_US": "Speech Description",
                    "zh_Hans": "演讲描述"
                  },
                  "llm_description": "Brief description of what the speech should be about",
                  "max": null,
                  "min": null,
                  "name": "description",
                  "options": null,
                  "required": true,
                  "scope": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2024-12-23T12:29:17Z",
        "version_updated_at": "2024-12-23T12:29:17Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Fetching data from the database using natural language.",
          "ja_JP": "Fetching data from the database using natural language.",
          "pt_BR": "Fetching data from the database using natural language.",
          "zh_Hans": "自然语言查询 Hologres 数据."
        },
        "category": "tool",
        "created_at": "2025-04-18T20:28:35Z",
        "endpoint": {},
        "icon": "hologres_dev/packages/hologres_text2data/_assets/hologram.svg",
        "index_id": "hologres_dev___hologres_text2data",
        "install_count": 102,
        "introduction": "\n# hologres_text2data  \n\n**Author:** hologres_dev  \n**Version:** 0.1.0  \n**Type:** Tool  \n\n## Description  \nA tool that converts natural language into secure and optimized SQL queries supporting Hologres syntax.  \n\n## Quick Start  \n### SQL Generation Component  \n1. Introduce the `hologres_text2data` plugin.  \n2. Complete basic parameter configuration.  \n\n| Parameter Name | Type       | Required | Description                        |  \n|----------------|------------|----------|------------------------------------|  \n| db_type        | Select     | Yes      | Database type (hologres)           |  \n| host           | String     | Yes      | Database host address              |  \n| port           | Number     | Yes      | Database port (1-65535)            |  \n| db_name        | String     | Yes      | Target database name               |  \n| table_name     | String     | No       | Multiple tables separated by commas (empty for all databases) |  \n\n3. Select a model  \nThe `Qwen2.5-72b-instruct` model is recommended. Other models can be tried independently. DeepSeek models are not supported.  \n\n4. Use natural language to generate SQL query statements.  \n\n### SQL Execution Component  \n1. Introduce the `hologres_excute_sql` plugin.  \n2. Complete basic parameter configuration.  \n\n| Parameter Name | Type       | Required | Description                        |  \n|----------------|------------|----------|------------------------------------|  \n| db_type        | Select     | Yes      | Database type (hologres)           |  \n| host           | String     | Yes      | Database host address              |  \n| port           | Number     | Yes      | Database port (1-65535)            |  \n| db_name        | String     | Yes      | Target database name               |  \n| sql            | String     | Yes      | SQL query statement                |  \n\n3. Click \"Execute\" to run the SQL statement.\n\n# NOTICE\nThis plugin is developed by Alibaba Cloud and based on [https://github.com/jaguarliuu/rookie_text2data](https://github.com/jaguarliuu/rookie_text2data)  program.\nCode is distributed under the Apache License (Version 2.0).",
        "label": {
          "en_US": "hologres_text2data",
          "ja_JP": "hologres_text2data",
          "pt_BR": "hologres_text2data",
          "zh_Hans": "hologres_text2data"
        },
        "latest_package_identifier": "hologres_dev/hologres_text2data:0.1.0@07dbe36e9493e1ae4eb968c9bece259dfbabc198bb662be08b3e7e00fe62337c",
        "latest_version": "0.1.0",
        "model": {},
        "name": "hologres_text2data",
        "org": "hologres_dev",
        "plugin_id": "hologres_dev/hologres_text2data",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/hologres_text2data.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "hologres_dev",
            "description": {
              "en_US": "Fetching data from the database using natural language.",
              "pt_BR": "Fetching data from the database using natural language.",
              "zh_Hans": "使用自然语言获取 Hologres 数据库数据."
            },
            "icon": "hologram.svg",
            "label": {
              "en_US": "hologres_text2data",
              "pt_BR": "hologres_text2data",
              "zh_Hans": "hologres_text2data"
            },
            "name": "hologres_text2data",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Fetching data from the database using natural language.",
                  "pt_BR": "Fetching data from the database using natural language.",
                  "zh_Hans": "使用自然语言获取 Hologres 数据库数据."
                },
                "llm": "Fetching data from the database using natural language."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "hologres_dev",
                "label": {
                  "en_US": "hologres_text2data",
                  "pt_BR": "hologres_text2data",
                  "zh_Hans": "hologres_text2data"
                },
                "name": "hologres_text2data"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": "hologres",
                  "form": "form",
                  "human_description": {
                    "en_US": "Database type",
                    "pt_BR": "Database type",
                    "zh_Hans": "数据库类型"
                  },
                  "label": {
                    "en_US": "Database type",
                    "pt_BR": "Database type",
                    "zh_Hans": "数据库类型"
                  },
                  "llm_description": "Database type",
                  "max": null,
                  "min": null,
                  "name": "db_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "Hologres"
                      },
                      "value": "hologres"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 100,
                  "form": "form",
                  "human_description": {
                    "en_US": "limit, default 100",
                    "pt_BR": "limit, default 100",
                    "zh_Hans": "SQL返回数据量限制，默认100行"
                  },
                  "label": {
                    "en_US": "limit, default 100",
                    "pt_BR": "limit,default 100",
                    "zh_Hans": "SQL返回数据量限制，默认100行"
                  },
                  "llm_description": "limit",
                  "max": 1000,
                  "min": 1,
                  "name": "limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "text",
                  "form": "form",
                  "human_description": {
                    "en_US": "result_format",
                    "pt_BR": "result_format",
                    "zh_Hans": "返回数据格式"
                  },
                  "label": {
                    "en_US": "result_format",
                    "pt_BR": "result_format",
                    "zh_Hans": "返回数据格式"
                  },
                  "llm_description": "result_format",
                  "max": null,
                  "min": null,
                  "name": "result_format",
                  "options": [
                    {
                      "label": {
                        "en_US": "JSON",
                        "zh_Hans": "JSON"
                      },
                      "value": "json"
                    },
                    {
                      "label": {
                        "en_US": "TEXT",
                        "zh_Hans": "TEXT"
                      },
                      "value": "text"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Database ip/host",
                    "pt_BR": "Database ip/host",
                    "zh_Hans": "数据库IP/域名"
                  },
                  "label": {
                    "en_US": "Database ip/host",
                    "pt_BR": "Database ip/host",
                    "zh_Hans": "数据库IP/域名"
                  },
                  "llm_description": "Database ip/host",
                  "max": null,
                  "min": null,
                  "name": "host",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Database port",
                    "pt_BR": "Database port",
                    "zh_Hans": "数据库端口"
                  },
                  "label": {
                    "en_US": "Database port",
                    "pt_BR": "Database port",
                    "zh_Hans": "数据库端口"
                  },
                  "llm_description": "Database port",
                  "max": 65535,
                  "min": 1,
                  "name": "port",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Database name",
                    "pt_BR": "Database name",
                    "zh_Hans": "数据库名称"
                  },
                  "label": {
                    "en_US": "Database name",
                    "pt_BR": "Database name",
                    "zh_Hans": "数据库名称"
                  },
                  "llm_description": "Database name",
                  "max": null,
                  "min": null,
                  "name": "db_name",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "table_names",
                    "pt_BR": "table_names",
                    "zh_Hans": "数据表名称"
                  },
                  "label": {
                    "en_US": "table_names",
                    "pt_BR": "table_names",
                    "zh_Hans": "数据表名称"
                  },
                  "llm_description": "table_names",
                  "max": null,
                  "min": null,
                  "name": "table_names",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Username",
                    "pt_BR": "Username",
                    "zh_Hans": "用户名"
                  },
                  "label": {
                    "en_US": "Username",
                    "pt_BR": "Username",
                    "zh_Hans": "用户名"
                  },
                  "llm_description": "Username",
                  "max": null,
                  "min": null,
                  "name": "username",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Password",
                    "pt_BR": "Password",
                    "zh_Hans": "密码"
                  },
                  "label": {
                    "en_US": "Password",
                    "pt_BR": "Password",
                    "zh_Hans": "密码"
                  },
                  "llm_description": "Password",
                  "max": null,
                  "min": null,
                  "name": "password",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "LLM model for text2data.",
                    "pt_BR": "LLM model for text2data.",
                    "zh_Hans": "LLM model for text2data."
                  },
                  "label": {
                    "en_US": "Model",
                    "pt_BR": "Model",
                    "zh_Hans": "模型"
                  },
                  "llm_description": "LLM model for text2data.",
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": "llm",
                  "template": null,
                  "type": "model-selector"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Fetching data from the database using natural language.",
                    "pt_BR": "Fetching data from the database using natural language.",
                    "zh_Hans": "Fetching data from the database using natural language."
                  },
                  "label": {
                    "en_US": "Query string",
                    "pt_BR": "Query string",
                    "zh_Hans": "查询语句"
                  },
                  "llm_description": "Fetching data from the database using natural language.",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "custom_prompt",
                    "pt_BR": "custom_prompt",
                    "zh_Hans": "自定义提示"
                  },
                  "label": {
                    "en_US": "custom_prompt",
                    "pt_BR": "custom_prompt",
                    "zh_Hans": "自定义提示"
                  },
                  "llm_description": "custom_prompt",
                  "max": null,
                  "min": null,
                  "name": "custom_prompt",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "with_comment",
                    "pt_BR": "with_comment",
                    "zh_Hans": "是否包含注释"
                  },
                  "label": {
                    "en_US": "with_comment",
                    "pt_BR": "with_comment",
                    "zh_Hans": "是否包含注释"
                  },
                  "llm_description": "with_comment",
                  "max": null,
                  "min": null,
                  "name": "with_comment",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "excute sql",
                  "pt_BR": "excute sql",
                  "zh_Hans": "sql 执行器"
                },
                "llm": "excute sql"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "hologres_dev",
                "label": {
                  "en_US": "hologres_excute_sql",
                  "pt_BR": "hologres_excute_sql",
                  "zh_Hans": "hologres_excute_sql"
                },
                "name": "hologres_excute_sql"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": "hologres",
                  "form": "form",
                  "human_description": {
                    "en_US": "Database type",
                    "pt_BR": "Database type",
                    "zh_Hans": "数据库类型"
                  },
                  "label": {
                    "en_US": "Database type",
                    "pt_BR": "Database type",
                    "zh_Hans": "数据库类型"
                  },
                  "llm_description": "Database type",
                  "max": null,
                  "min": null,
                  "name": "db_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "Hologres"
                      },
                      "value": "hologres"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Database ip/host",
                    "pt_BR": "Database ip/host",
                    "zh_Hans": "数据库IP/域名"
                  },
                  "label": {
                    "en_US": "Database ip/host",
                    "pt_BR": "Database ip/host",
                    "zh_Hans": "数据库IP/域名"
                  },
                  "llm_description": "Database ip/host",
                  "max": null,
                  "min": null,
                  "name": "host",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Database port",
                    "pt_BR": "Database port",
                    "zh_Hans": "数据库端口"
                  },
                  "label": {
                    "en_US": "Database port",
                    "pt_BR": "Database port",
                    "zh_Hans": "数据库端口"
                  },
                  "llm_description": "Database port",
                  "max": 65535,
                  "min": 1,
                  "name": "port",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Database name",
                    "pt_BR": "Database name",
                    "zh_Hans": "数据库名称"
                  },
                  "label": {
                    "en_US": "Database name",
                    "pt_BR": "Database name",
                    "zh_Hans": "数据库名称"
                  },
                  "llm_description": "Database name",
                  "max": null,
                  "min": null,
                  "name": "db_name",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Username",
                    "pt_BR": "Username",
                    "zh_Hans": "用户名"
                  },
                  "label": {
                    "en_US": "Username",
                    "pt_BR": "Username",
                    "zh_Hans": "用户名"
                  },
                  "llm_description": "Username",
                  "max": null,
                  "min": null,
                  "name": "username",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Password",
                    "pt_BR": "Password",
                    "zh_Hans": "密码"
                  },
                  "label": {
                    "en_US": "Password",
                    "pt_BR": "Password",
                    "zh_Hans": "密码"
                  },
                  "llm_description": "Password",
                  "max": null,
                  "min": null,
                  "name": "password",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Fetching data from the database using natural language.",
                    "pt_BR": "Fetching data from the database using natural language.",
                    "zh_Hans": "Fetching data from the database using natural language."
                  },
                  "label": {
                    "en_US": "SQL string",
                    "pt_BR": "SQL string",
                    "zh_Hans": "待执行的 SQL 语句"
                  },
                  "llm_description": "Fetching data from the database using natural language.",
                  "max": null,
                  "min": null,
                  "name": "sql",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "json",
                  "form": "form",
                  "human_description": {
                    "en_US": "result_format",
                    "pt_BR": "result_format",
                    "zh_Hans": "返回数据格式"
                  },
                  "label": {
                    "en_US": "result_format",
                    "pt_BR": "result_format",
                    "zh_Hans": "返回数据格式"
                  },
                  "llm_description": "result_format",
                  "max": null,
                  "min": null,
                  "name": "result_format",
                  "options": [
                    {
                      "label": {
                        "en_US": "JSON",
                        "zh_Hans": "JSON"
                      },
                      "value": "json"
                    },
                    {
                      "label": {
                        "en_US": "TEXT",
                        "zh_Hans": "TEXT"
                      },
                      "value": "text"
                    },
                    {
                      "label": {
                        "en_US": "CSV",
                        "zh_Hans": "CSV"
                      },
                      "value": "csv"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-18T20:28:42Z",
        "version_updated_at": "2025-04-18T20:28:42Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Compatible Dify App's API with Huawei MetaStudio third-party llm api",
          "zh_Hans": "提供将 Dify App 适配华为 MetaStudio 第三方 LLM 接口的扩展插件"
        },
        "category": "extension",
        "created_at": "2025-04-02T08:09:33Z",
        "endpoint": {
          "endpoints": [
            {
              "hidden": false,
              "method": "POST",
              "path": "/metastudio_dify_app/chat"
            }
          ],
          "settings": [
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Base URL",
                "zh_Hans": "Base URL"
              },
              "name": "base_url",
              "options": null,
              "placeholder": {
                "en_US": "Please input your base URL",
                "zh_Hans": "请输入你的基础访问地址"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "API key",
                "zh_Hans": "API key"
              },
              "name": "api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your API key",
                "zh_Hans": "请输入你的 API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "App",
                "zh_Hans": "App"
              },
              "name": "app_id",
              "options": null,
              "placeholder": {
                "en_US": "Please select an app",
                "zh_Hans": "请选择一个应用"
              },
              "required": true,
              "scope": "chat",
              "type": "app-selector",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Memory Mode",
                "zh_Hans": "记忆模式"
              },
              "name": "memory_mode",
              "options": [
                {
                  "label": {
                    "en_US": "Last User Message",
                    "zh_Hans": "使用最后一条用户消息"
                  },
                  "value": "last_user_message"
                }
              ],
              "placeholder": {
                "en_US": "Please select a memory mode, it will decide how the Endpoint manage the context",
                "zh_Hans": "请选择一个上下文模式，它将决定该 Endpoint 使用哪种方式管理上下文"
              },
              "required": true,
              "scope": null,
              "type": "select",
              "url": null
            }
          ]
        },
        "icon": "zxi2002/packages/metastudio_dify_app/_assets/icon.svg",
        "index_id": "zxi2002___metastudio_dify_app",
        "install_count": 95,
        "introduction": "## metastudio_dify_app\n\n**Author:** zxi2002<zix2002@gmail.com>\n**Version:** 0.0.1\n**Type:** extension\n\n### Description\n\nThis plugin is used to adapt the Dify App to the third-party LLM interface of Huawei MetaStudio.\n\n### Configure the plugin\n\n- Click the plugin, click `+` to add `API Endpoint`\n- Input the `Endpoint Name`, for example `/meta-studio/chat`\n- Input the `BASE URL`, your `dify` public access base url, for example `http://localhost:1438`, `https://dify.yourdomain.com`\n- Input the `API Key`, your `dify` api key, for example `sk-xxxxxx`\n- Select the `App` and `Memory Mode`\n- Click `Save`\n\nIf the `SERVICE OK`, the configuration is successful\n\n### Use the plugin\n\nCopy the public access url, for example `http://localhost:1438/e/1m4lpn4s7i3tb523/metastudio_dify_app/chat`,\nwhere `1m4lpn4s7i3tb523` is the `App ID` of `MetaStudio`\n\nIn the `MetaStudio` `Interactive Digital Human` page, you need to configure the following 3 parameters\n\n- `APPID`: `1m4lpn4s7i3tb523`\n- `APPKey`: `sk-xxxxxx`\n- `Third-party LLM address`: `http://localhost:1438/e/1m4lpn4s7i3tb523/metastudio_dify_app/chat`\n\n\n### Notice\n\n1. If you want to install the plugin locally, please modify the `/docker/.env` file, set `FORCE_VERIFYING_SIGNATURE` to `false`\n\n```env\nFORCE_VERIFYING_SIGNATURE=false\n```\n\nThen restart the `dify` container, refresh the page, and then reinstall the plugin\n\n```bash\ndocker compose down\ndocker compose up -d\n```\n\n2. If your extension APP is `Agent mode`, you can only use `stream` mode\nPlease open `Stream response` in the `MetaStudio` `Interactive Digital Human` configuration page\n\n\n",
        "label": {
          "en_US": "metastudio_dify_app",
          "zh_Hans": "metastudio_dify_app"
        },
        "latest_package_identifier": "zxi2002/metastudio_dify_app:0.0.1@cfd71db015b1cf9d4bf317cb669b11c997abf690f107a8b73d98d6d7143f648c",
        "latest_version": "0.0.1",
        "model": {},
        "name": "metastudio_dify_app",
        "org": "zxi2002",
        "plugin_id": "zxi2002/metastudio_dify_app",
        "plugins": {
          "agent_strategies": null,
          "endpoints": [
            "group/metastudio_dify_app.yaml"
          ],
          "models": null,
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-02T08:09:38Z",
        "version_updated_at": "2025-04-02T08:09:38Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Search for movies, TV shows and people on The Movie Database (TMDB).",
          "ja_JP": "The Movie Database (TMDB) で映画、テレビ番組、人物を検索します。",
          "pt_BR": "Pesquise filmes, programas de TV e pessoas no The Movie Database (TMDB).",
          "zh_Hans": "在 The Movie Database (TMDB) 上搜索电影、电视节目和人物。"
        },
        "category": "tool",
        "created_at": "2025-04-10T15:09:36Z",
        "endpoint": {},
        "icon": "lcandy/packages/tmdb/_assets/icon.svg",
        "index_id": "lcandy___tmdb",
        "install_count": 87,
        "introduction": "# Dify Tool Plugin - The Movie Database (TMDB)\n\nThis plugin allows you to search The Movie Database (TMDB) for movies, TV shows, and people. It provides comprehensive metadata and information from TMDB's extensive entertainment database.\n\n## Features\n\n- **Movie Search**: Search for movies by title, keywords, or phrases\n- **TV Show Search**: Search for TV shows by name, keywords, or phrases\n- **Multi Search**: Combined search for movies, TV shows, and people in a single request\n\n## Setup\n\n1. Register for a TMDB account at [https://www.themoviedb.org](https://www.themoviedb.org)\n2. Generate an API Read Access Token (v4 auth) at [https://developer.themoviedb.org/reference/intro/authentication](https://developer.themoviedb.org/reference/intro/authentication)\n3. Install the plugin in your Dify instance\n4. Configure the plugin with your TMDB API Read Access Token\n\n## Usage\n\n### Movie Search\n\nSearch for movies by title or keywords:\n\n- **Parameters**:\n  - `query` (required): Movie title or keywords\n  - `language` (optional): ISO 639-1 language code (default: en-US)\n  - `year` (optional): Filter by release year\n  - `results_limit` (optional): Number of results to return (1-20, default: 5)\n\n### TV Show Search\n\nSearch for TV shows by title or keywords:\n\n- **Parameters**:\n  - `query` (required): TV show title or keywords\n  - `language` (optional): ISO 639-1 language code (default: en-US)\n  - `first_air_date_year` (optional): Filter by first air date year\n  - `results_limit` (optional): Number of results to return (1-20, default: 5)\n\n### Multi Search\n\nSearch for movies, TV shows, and people in a single request:\n\n- **Parameters**:\n  - `query` (required): Search keywords\n  - `language` (optional): ISO 639-1 language code (default: en-US)\n  - `include_adult` (optional): Whether to include adult content (default: false)\n  - `results_limit` (optional): Number of results to return (1-20, default: 10)\n\n## Development\n\n### Requirements\n\n- Python 3.12+\n- Dify Plugin SDK\n\n### Local Development\n\n1. Clone this repository\n2. Create a virtual environment and install dependencies:\n   ```\n   python -m venv venv\n   source venv/bin/activate  # On Windows: venv\\Scripts\\activate\n   pip install -r requirements.txt\n   ```\n3. Copy `.env.example` to `.env` and configure your development environment\n4. Run the plugin:\n   ```\n   python -m main\n   ```\n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n## Acknowledgments\n\n- This plugin uses the [TMDB API](https://developer.themoviedb.org/docs)\n- Data and images provided by [The Movie Database (TMDB)](https://www.themoviedb.org)\n\n\n\n",
        "label": {
          "en_US": "The Movie Database (TMDB)",
          "ja_JP": "The Movie Database (TMDB)",
          "pt_BR": "The Movie Database (TMDB)",
          "zh_Hans": "The Movie Database (TMDB)"
        },
        "latest_package_identifier": "lcandy/tmdb:0.0.1@e8e6be9803ee41bd1bea5cd8ae56bf00540e1662eca8225d54bf66e7fc7caf3e",
        "latest_version": "0.0.1",
        "model": {},
        "name": "tmdb",
        "org": "lcandy",
        "plugin_id": "lcandy/tmdb",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/tmdb.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Get your API Read Access Token (v4 auth) from TMDB",
                "ja_JP": "TMDB からAPI読み取りアクセストークン（v4認証）を取得してください",
                "pt_BR": "Obtenha seu Token de Acesso de Leitura da API (autenticação v4) do TMDB",
                "zh_Hans": "从 TMDB 获取您的 API 读取访问令牌（v4 认证）"
              },
              "label": {
                "en_US": "API Read Access Token",
                "ja_JP": "API 読み取りアクセストークン (Read Access Token)",
                "pt_BR": "Token de Acesso de Leitura da API (Read Access Token)",
                "zh_Hans": "API 读取访问令牌 (Read Access Token)"
              },
              "name": "api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your TMDB API Read Access Token",
                "ja_JP": "TMDB API 読み取りアクセストークンを入力してください",
                "pt_BR": "Por favor, insira seu Token de Acesso de Leitura da API TMDB",
                "zh_Hans": "请输入您的 TMDB API 读取访问令牌"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://developer.themoviedb.org/reference/intro/authentication"
            }
          ],
          "identity": {
            "author": "lcandy",
            "description": {
              "en_US": "Search for movies, TV shows and people on The Movie Database (TMDB).",
              "ja_JP": "The Movie Database (TMDB) で映画、テレビ番組、人物を検索します。",
              "pt_BR": "Pesquise filmes, programas de TV e pessoas no The Movie Database (TMDB).",
              "zh_Hans": "在 The Movie Database (TMDB) 上搜索电影、电视节目和人物。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "The Movie Database (TMDB)",
              "ja_JP": "The Movie Database (TMDB)",
              "pt_BR": "The Movie Database (TMDB)",
              "zh_Hans": "The Movie Database (TMDB)"
            },
            "name": "tmdb",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Search for movies by title, keywords or phrases. Returns movie details including title, overview, release date, and ratings.",
                  "ja_JP": "タイトル、キーワード、またはフレーズで映画を検索します。タイトル、概要、公開日、評価などの映画詳細を返します。",
                  "pt_BR": "Pesquise filmes por título, palavras-chave ou frases. Retorna detalhes do filme incluindo título, visão geral, data de lançamento e classificações.",
                  "zh_Hans": "通过标题、关键词或短语搜索电影。返回电影详情，包括标题、概述、发行日期和评分。"
                },
                "llm": "Search for movies by title, keywords or phrases. This tool searches The Movie Database (TMDB) and returns movie information."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "lcandy",
                "label": {
                  "en_US": "Search Movies",
                  "ja_JP": "映画を検索",
                  "pt_BR": "Pesquisar Filmes",
                  "zh_Hans": "搜索电影"
                },
                "name": "tmdb_movie_search"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The title or keywords to search for movies",
                    "ja_JP": "映画を検索するためのタイトルまたはキーワード",
                    "pt_BR": "O título ou palavras-chave para pesquisar filmes",
                    "zh_Hans": "用于搜索电影的标题或关键词"
                  },
                  "label": {
                    "en_US": "Movie Title or Keywords",
                    "ja_JP": "映画のタイトルまたはキーワード",
                    "pt_BR": "Título do Filme ou Palavras-chave",
                    "zh_Hans": "电影标题或关键词"
                  },
                  "llm_description": "The movie title or keywords to search for in TMDB",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "en-US",
                  "form": "form",
                  "human_description": {
                    "en_US": "The ISO 639-1 language code to search in (default is en-US)",
                    "ja_JP": "検索するISO 639-1言語コード（デフォルトはen-US）",
                    "pt_BR": "O código de idioma ISO 639-1 para pesquisar (o padrão é en-US)",
                    "zh_Hans": "要搜索的 ISO 639-1 语言代码（默认为 en-US）"
                  },
                  "label": {
                    "en_US": "Language",
                    "ja_JP": "言語",
                    "pt_BR": "Idioma",
                    "zh_Hans": "语言"
                  },
                  "llm_description": "The ISO 639-1 language code to search in (e.g., en-US, zh-CN, fr-FR)",
                  "max": null,
                  "min": null,
                  "name": "language",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Filter results by specific release year",
                    "ja_JP": "特定の公開年で結果をフィルタリング",
                    "pt_BR": "Filtrar resultados por ano específico de lançamento",
                    "zh_Hans": "按特定发行年份筛选结果"
                  },
                  "label": {
                    "en_US": "Release Year",
                    "ja_JP": "公開年",
                    "pt_BR": "Ano de Lançamento",
                    "zh_Hans": "发行年份"
                  },
                  "llm_description": "Specify a year to filter results to movies released in that year",
                  "max": null,
                  "min": null,
                  "name": "year",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 5,
                  "form": "form",
                  "human_description": {
                    "en_US": "Maximum number of results to return (1-20, default is 5)",
                    "ja_JP": "返す結果の最大数（1-20、デフォルトは5）",
                    "pt_BR": "Número máximo de resultados a serem retornados (1-20, o padrão é 5)",
                    "zh_Hans": "要返回的最大结果数（1-20，默认为5）"
                  },
                  "label": {
                    "en_US": "Number of Results",
                    "ja_JP": "結果の数",
                    "pt_BR": "Número de Resultados",
                    "zh_Hans": "结果数量"
                  },
                  "llm_description": "Maximum number of movies to return in results (1-20)",
                  "max": 20,
                  "min": 1,
                  "name": "results_limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Search for TV shows by title, keywords or phrases. Returns TV show details including title, overview, first air date, and ratings.",
                  "ja_JP": "タイトル、キーワード、またはフレーズでテレビ番組を検索します。タイトル、概要、初回放送日、評価などの詳細を返します。",
                  "pt_BR": "Pesquise programas de TV por título, palavras-chave ou frases. Retorna detalhes do programa incluindo título, visão geral, data de estreia e classificações.",
                  "zh_Hans": "通过标题、关键词或短语搜索电视节目。返回电视节目详情，包括标题、概述、首播日期和评分。"
                },
                "llm": "Search for TV shows by title, keywords or phrases. This tool searches The Movie Database (TMDB) and returns TV show information."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "lcandy",
                "label": {
                  "en_US": "Search TV Shows",
                  "ja_JP": "テレビ番組を検索",
                  "pt_BR": "Pesquisar Programas de TV",
                  "zh_Hans": "搜索电视节目"
                },
                "name": "tmdb_tv_search"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The title or keywords to search for TV shows",
                    "ja_JP": "テレビ番組を検索するためのタイトルまたはキーワード",
                    "pt_BR": "O título ou palavras-chave para pesquisar programas de TV",
                    "zh_Hans": "用于搜索电视节目的标题或关键词"
                  },
                  "label": {
                    "en_US": "TV Show Title or Keywords",
                    "ja_JP": "テレビ番組のタイトルまたはキーワード",
                    "pt_BR": "Título do Programa de TV ou Palavras-chave",
                    "zh_Hans": "电视节目标题或关键词"
                  },
                  "llm_description": "The TV show title or keywords to search for in TMDB",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "en-US",
                  "form": "form",
                  "human_description": {
                    "en_US": "The ISO 639-1 language code to search in (default is en-US)",
                    "ja_JP": "検索するISO 639-1言語コード（デフォルトはen-US）",
                    "pt_BR": "O código de idioma ISO 639-1 para pesquisar (o padrão é en-US)",
                    "zh_Hans": "要搜索的 ISO 639-1 语言代码（默认为 en-US）"
                  },
                  "label": {
                    "en_US": "Language",
                    "ja_JP": "言語",
                    "pt_BR": "Idioma",
                    "zh_Hans": "语言"
                  },
                  "llm_description": "The ISO 639-1 language code to search in (e.g., en-US, zh-CN, fr-FR)",
                  "max": null,
                  "min": null,
                  "name": "language",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Filter results by specific first air date year",
                    "ja_JP": "特定の初回放送年で結果をフィルタリング",
                    "pt_BR": "Filtrar resultados por ano específico de estreia",
                    "zh_Hans": "按特定首播年份筛选结果"
                  },
                  "label": {
                    "en_US": "First Air Date Year",
                    "ja_JP": "初回放送年",
                    "pt_BR": "Ano de Estreia",
                    "zh_Hans": "首播年份"
                  },
                  "llm_description": "Specify a year to filter results to TV shows that first aired in that year",
                  "max": null,
                  "min": null,
                  "name": "first_air_date_year",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 5,
                  "form": "form",
                  "human_description": {
                    "en_US": "Maximum number of results to return (1-20, default is 5)",
                    "ja_JP": "返す結果の最大数（1-20、デフォルトは5）",
                    "pt_BR": "Número máximo de resultados a serem retornados (1-20, o padrão é 5)",
                    "zh_Hans": "要返回的最大结果数（1-20，默认为5）"
                  },
                  "label": {
                    "en_US": "Number of Results",
                    "ja_JP": "結果の数",
                    "pt_BR": "Número de Resultados",
                    "zh_Hans": "结果数量"
                  },
                  "llm_description": "Maximum number of TV shows to return in results (1-20)",
                  "max": 20,
                  "min": 1,
                  "name": "results_limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Search for movies, TV shows, and people in a single request. Returns results of multiple types with their respective details.",
                  "ja_JP": "映画、テレビ番組、人物を一度のリクエストで検索します。複数のタイプの結果とそれぞれの詳細を返します。",
                  "pt_BR": "Pesquise filmes, programas de TV e pessoas em uma única solicitação. Retorna resultados de vários tipos com seus respectivos detalhes.",
                  "zh_Hans": "在单个请求中搜索电影、电视节目和人物。返回多种类型的结果及其各自的详情。"
                },
                "llm": "Search for movies, TV shows, and people in a single request. This tool searches The Movie Database (TMDB) across multiple content types."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "lcandy",
                "label": {
                  "en_US": "Multi Search",
                  "ja_JP": "マルチ検索",
                  "pt_BR": "Pesquisa Múltipla",
                  "zh_Hans": "多类型搜索"
                },
                "name": "tmdb_multi_search"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The keywords to search for movies, TV shows, and people",
                    "ja_JP": "映画、テレビ番組、人物を検索するためのキーワード",
                    "pt_BR": "As palavras-chave para pesquisar filmes, programas de TV e pessoas",
                    "zh_Hans": "用于搜索电影、电视节目和人物的关键词"
                  },
                  "label": {
                    "en_US": "Search Keywords",
                    "ja_JP": "検索キーワード",
                    "pt_BR": "Palavras-chave de Pesquisa",
                    "zh_Hans": "搜索关键词"
                  },
                  "llm_description": "The keywords to search for in TMDB across movies, TV shows, and people",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "en-US",
                  "form": "form",
                  "human_description": {
                    "en_US": "The ISO 639-1 language code to search in (default is en-US)",
                    "ja_JP": "検索するISO 639-1言語コード（デフォルトはen-US）",
                    "pt_BR": "O código de idioma ISO 639-1 para pesquisar (o padrão é en-US)",
                    "zh_Hans": "要搜索的 ISO 639-1 语言代码（默认为 en-US）"
                  },
                  "label": {
                    "en_US": "Language",
                    "ja_JP": "言語",
                    "pt_BR": "Idioma",
                    "zh_Hans": "语言"
                  },
                  "llm_description": "The ISO 639-1 language code to search in (e.g., en-US, zh-CN, fr-FR)",
                  "max": null,
                  "min": null,
                  "name": "language",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "form",
                  "human_description": {
                    "en_US": "Whether to include adult content in search results",
                    "ja_JP": "検索結果にアダルトコンテンツを含めるかどうか",
                    "pt_BR": "Se deve incluir conteúdo adulto nos resultados da pesquisa",
                    "zh_Hans": "是否在搜索结果中包括成人内容"
                  },
                  "label": {
                    "en_US": "Include Adult Content",
                    "ja_JP": "アダルトコンテンツを含める",
                    "pt_BR": "Incluir Conteúdo Adulto",
                    "zh_Hans": "包括成人内容"
                  },
                  "llm_description": "Set to true to include adult content in search results, false to exclude",
                  "max": null,
                  "min": null,
                  "name": "include_adult",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": 10,
                  "form": "form",
                  "human_description": {
                    "en_US": "Maximum number of results to return (1-20, default is 10)",
                    "ja_JP": "返す結果の最大数（1-20、デフォルトは10）",
                    "pt_BR": "Número máximo de resultados a serem retornados (1-20, o padrão é 10)",
                    "zh_Hans": "要返回的最大结果数（1-20，默认为10）"
                  },
                  "label": {
                    "en_US": "Number of Results",
                    "ja_JP": "結果の数",
                    "pt_BR": "Número de Resultados",
                    "zh_Hans": "结果数量"
                  },
                  "llm_description": "Maximum total number of results to return across all types (1-20)",
                  "max": 20,
                  "min": 1,
                  "name": "results_limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-10T15:09:43Z",
        "version_updated_at": "2025-04-10T15:09:43Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Query Aliyun SLS logs",
          "ja_JP": "クエリ阿里云SLSログ",
          "pt_BR": "Query Aliyun SLS logs",
          "zh_Hans": "查询阿里云SLS日志"
        },
        "category": "tool",
        "created_at": "2025-03-31T08:19:55Z",
        "endpoint": {},
        "icon": "lework/packages/aliyun-sls/_assets/icon.svg",
        "index_id": "lework___aliyun-sls",
        "install_count": 74,
        "introduction": "# Alibaba Cloud Log Service (SLS) plugin\r\n\r\n**Author:** lework\r\n**Version:** 0.0.1\r\n**Type:** tool\r\n**REPO:** [dify-plugin-aliyun-sls](https://github.com/lework/dify-plugin-aliyun-sls)\r\n\r\nThis is a Dify plugin for querying log data in Alibaba Cloud Log Service (SLS).\r\n\r\n## Function\r\n\r\n- Query log data in Alibaba Cloud SLS Log Service\r\n- Supports specifying query statements, log libraries, time ranges and other parameters\r\n- Supports custom query result quantity limits\r\n\r\n## Configuration\r\n\r\nTo use this plugin, you need to provide the following Alibaba Cloud credentials:\r\n\r\n- Endpoint: Endpoint of Alibaba Cloud SLS service, for example: cn-hangzhou.log.aliyuncs.com\r\n- Access Key ID: Access Key ID of Alibaba Cloud account\r\n- Access Key Secret: Access Key Secret of Alibaba Cloud account\r\n- Project: Project name of Alibaba Cloud SLS\r\n- Logstore (optional): Log library name of Alibaba Cloud SLS, which can also be specified when querying\r\n\r\n## Usage examples\r\n\r\n```\r\nQuery logs containing \"error\" in the last 15 minutes\r\n```\r\n\r\n```\r\nQuery all logs in the last 1 hour in logstore \"nginx-access\", and limit the return to 50\r\n```\r\n\r\n## Query syntax\r\n\r\nSupports query syntax of Alibaba Cloud SLS, for details, please refer to [Alibaba Cloud SLS Query syntax documentation](https://help.aliyun.com/document_detail/29060.html).\r\n",
        "label": {
          "en_US": "Aliyun-SLS",
          "ja_JP": "阿里云SLS",
          "pt_BR": "Aliyun-SLS",
          "zh_Hans": "阿里云SLS"
        },
        "latest_package_identifier": "lework/aliyun-sls:0.0.1@ecb14aede2de267b5889abe685b90e2bf8a9cf4eb3087020a5ea31040c59df7b",
        "latest_version": "0.0.1",
        "model": {},
        "name": "aliyun-sls",
        "org": "lework",
        "plugin_id": "lework/aliyun-sls",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/aliyun-sls.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Get your endpoint from Aliyun SLS",
                "zh_Hans": "从阿里云日志服务获取您的端点"
              },
              "label": {
                "en_US": "Endpoint",
                "zh_Hans": "端点"
              },
              "name": "endpoint",
              "options": null,
              "placeholder": {
                "en_US": "Please input your endpoint",
                "zh_Hans": "请输入你的端点"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://sls.console.aliyun.com/lognext/project/list"
            },
            {
              "default": null,
              "help": {
                "en_US": "Get your access key id from Aliyun SLS",
                "zh_Hans": "从阿里云日志服务获取您的访问密钥ID"
              },
              "label": {
                "en_US": "Access Key ID",
                "zh_Hans": "访问密钥ID"
              },
              "name": "access_key_id",
              "options": null,
              "placeholder": {
                "en_US": "Please input your access key id",
                "zh_Hans": "请输入你的访问密钥ID"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://sls.console.aliyun.com/lognext/project/list"
            },
            {
              "default": null,
              "help": {
                "en_US": "Get your access key secret from Aliyun SLS",
                "zh_Hans": "从阿里云日志服务获取您的访问密钥密钥"
              },
              "label": {
                "en_US": "Access Key Secret",
                "zh_Hans": "访问密钥密钥"
              },
              "name": "access_key_secret",
              "options": null,
              "placeholder": {
                "en_US": "Please input your access key secret",
                "zh_Hans": "请输入你的访问密钥密钥"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "help": {
                "en_US": "Get your project from Aliyun SLS",
                "zh_Hans": "从阿里云日志服务获取您的项目"
              },
              "label": {
                "en_US": "Project",
                "zh_Hans": "默认项目"
              },
              "name": "project",
              "options": null,
              "placeholder": {
                "en_US": "Please input your project",
                "zh_Hans": "请输入你的项目"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Logstore",
                "zh_Hans": "默认日志库"
              },
              "name": "logstore",
              "options": null,
              "placeholder": {
                "en_US": "Please input your logstore",
                "zh_Hans": "请输入你的日志库"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            }
          ],
          "identity": {
            "author": "lework",
            "description": {
              "en_US": "Query logs from Aliyun SLS (Simple Log Service)",
              "pt_BR": "Query logs from Aliyun SLS (Simple Log Service)",
              "zh_Hans": "查询阿里云日志服务(SLS)中的日志数据"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Aliyun SLS",
              "pt_BR": "Aliyun SLS",
              "zh_Hans": "阿里云日志服务"
            },
            "name": "aliyun-sls",
            "tags": [
              "other"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Query Aliyun SLS logs",
                  "pt_BR": "Query Aliyun SLS logs",
                  "zh_Hans": "查询阿里云SLS日志服务中的日志数据"
                },
                "llm": "查询阿里云SLS日志服务中的日志数据，支持指定查询语句、日志库、时间范围等参数"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "lework",
                "label": {
                  "en_US": "aliyun-sls",
                  "pt_BR": "aliyun-sls",
                  "zh_Hans": "阿里云SLS日志查询"
                },
                "name": "aliyun-sls"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The query string to search logs",
                    "pt_BR": "The query string to search logs",
                    "zh_Hans": "用于搜索日志的查询语句，支持阿里云SLS查询语法"
                  },
                  "label": {
                    "en_US": "Query string",
                    "pt_BR": "Query string",
                    "zh_Hans": "查询语句"
                  },
                  "llm_description": "用于搜索日志的查询语句，支持阿里云SLS查询语法",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The name of the project to query",
                    "pt_BR": "The name of the project to query",
                    "zh_Hans": "要查询的项目名称，如不提供则使用凭证中配置的默认项目"
                  },
                  "label": {
                    "en_US": "Project",
                    "pt_BR": "Project",
                    "zh_Hans": "项目名称"
                  },
                  "llm_description": "要查询的项目名称，如不提供则使用凭证中配置的默认项目",
                  "max": null,
                  "min": null,
                  "name": "project",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The name of the logstore to query",
                    "pt_BR": "The name of the logstore to query",
                    "zh_Hans": "要查询的日志库名称，如不提供则使用凭证中配置的默认日志库"
                  },
                  "label": {
                    "en_US": "Logstore",
                    "pt_BR": "Logstore",
                    "zh_Hans": "日志库"
                  },
                  "llm_description": "要查询的日志库名称，如不提供则使用凭证中配置的默认日志库",
                  "max": null,
                  "min": null,
                  "name": "logstore",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The start time for the query (ISO format)",
                    "pt_BR": "The start time for the query (ISO format)",
                    "zh_Hans": "查询的开始时间（ISO格式），如不提供则默认为15分钟前"
                  },
                  "label": {
                    "en_US": "From Time",
                    "pt_BR": "From Time",
                    "zh_Hans": "开始时间"
                  },
                  "llm_description": "查询的开始时间（ISO格式），如不提供则默认为15分钟前",
                  "max": null,
                  "min": null,
                  "name": "from_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The end time for the query (ISO format)",
                    "pt_BR": "The end time for the query (ISO format)",
                    "zh_Hans": "查询的结束时间（ISO格式），如不提供则默认为当前时间"
                  },
                  "label": {
                    "en_US": "To Time",
                    "pt_BR": "To Time",
                    "zh_Hans": "结束时间"
                  },
                  "llm_description": "查询的结束时间（ISO格式），如不提供则默认为当前时间",
                  "max": null,
                  "min": null,
                  "name": "to_time",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Maximum number of logs to return",
                    "pt_BR": "Maximum number of logs to return",
                    "zh_Hans": "最多返回的日志条数，默认为100"
                  },
                  "label": {
                    "en_US": "Limit",
                    "pt_BR": "Limit",
                    "zh_Hans": "返回数量限制"
                  },
                  "llm_description": "最多返回的日志条数，默认为100",
                  "max": null,
                  "min": null,
                  "name": "limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-31T08:20:01Z",
        "version_updated_at": "2025-03-31T08:20:01Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Send message to channel",
          "ja_JP": "チャンネルにメッセージを送信する",
          "pt_BR": "Enviar uma mensagem para o canal",
          "zh_Hans": "向频道发送消息"
        },
        "category": "tool",
        "created_at": "2025-04-13T17:15:35Z",
        "endpoint": {},
        "icon": "edtechools/packages/mattermost/_assets/icon.svg",
        "index_id": "edtechools___mattermost",
        "install_count": 68,
        "introduction": "**Author:** Jiahua Cui\n**Version:** 0.0.2\n**Type:** tool\n\n### Overview 👀\n\n> Mattermost is an open-core, self-hosted collaboration platform that provides persistent chat and ChatOps, workflow and toolchain automation, integrated voice, screen, file, and content sharing, as well as AI-enhanced information synthesis. The platform is designed to be fully extensible, supporting a rich ecosystem of third-party applications and integrations. Mattermost can be easily enhanced and customized through open APIs, developer frameworks, open-source customization, and community-driven enhancements.\n\nThis plugin contains two tools:\n\n1️⃣ Incoming Webhook Integration:<br />\nEnables external integrations to send messages to specific Mattermost channels through the webhook feature.\n\n2️⃣ Bot Account Integration:<br />\nAllows sending messages to designated Mattermost channels using bot accounts.\n\n### 1️⃣. Incoming hook tool 🪝\n\n#### Mattermost Configuration ⚙️\n\n> Please refer to this website:\n> https://developers.mattermost.com/integrate/webhooks/incoming/\n\n1. In Mattermost, go to Product menu > Integrations > Incoming Webhook.\n   > If you don’t have the Integrations option, incoming webhooks may not be enabled on your Mattermost server or may be disabled for non-admins. They can be enabled by a System Admin from System Console > Integrations > Integration Management. Once incoming webhooks are enabled, continue with the steps below.\n2. Select Add Incoming Webhook and add a name and description for the webhook. The description can be up to 500 characters.\n3. Select the channel to receive webhook payloads, then select Add to create the webhook.\n   > You will end up with a webhook endpoint that looks like so:\n   > https://your-mattermost-server.com/hooks/xxx-generatedkey-xxx<hr />\n   > Treat this endpoint as a secret. Anyone who has it will be able to post messages to your Mattermost instance.\n\n#### Configuring the Mattermost Tool ⚙️\n\n1. Install the Mattermost tool from the marketplace.\n\n2. Add the Mattermost node to your workflow.\n\n3. Paste Incoming Webhook.\n\n---\n\n### 2️⃣. Bot Accounts tool 🤖\n\n#### Mattermost Configuration⚙️\n\n> Please refer to this website:\n> https://developers.mattermost.com/integrate/reference/bot-accounts/\n\n1. Go to System Console > Integrations > Bot Accounts.\n2. Set Enable Bot Account Creation to true.\n\n> Once set, System Admin can create bot accounts for integrations using the Integrations > Bot Accounts link in the description provided.\n\n##### Using User interface (UI) to create bot accounts\n\n1. Go to the Product menu and select Integrations > Bot Accounts.\n2. Select Add Bot Account.\n3. Set the Username of the bot. The username must begin with a letter, and contain between 3 and 22 lowercase characters made up of numbers, letters, and symbols including “.”, “-”, or “\\_”.\n4. (Optional) Upload an image for the Bot Icon. This will be used as the profile image of the bot throughout Mattermost.\n5. (Optional) Set a Display Name and Description.\n6. (Optional) Choose what role the bot should have. Defaults to Member. If you assign System Admin, the bot will have read and write access for any Public channels, Private channels, and Direct Messages.\n7. (Optional) Select additional permissions for the account. Enable the bot to post to all Mattermost channels, or post to all Mattermost Public channels.\n8. Select Create Bot Account.\n9. Copy the token displayed on the Setup Successful page before you select Done as you won’t have access to the token again once you close the screen.\n\n##### After the bot account is created, make sure to:\n\n1. Copy the generated bot access token for your integration.\n2. To add the bot account to teams and channels you want it to interact in, select the team drop-down menu, then select Invite People. Next, select Invite Member and enter the bot account in the Add or Invite People field. Then select Invite Members. You should now be able to add the bot account to channels like any other user.\n\n#### Configuring the Mattermost Tool ⚙️\n\n1. Install the Mattermost tool from the marketplace.\n2. Add the Mattermost node to your workflow.\n3. Enter the following information:\n   - Mattermost server URL (domain and port)\n   - Channel ID for message destination\n   - Message type (select ephemeral if sending to a specific user, in which case you'll need to provide their user ID)\n   - Bot account access token\n",
        "label": {
          "en_US": "Mattermost",
          "ja_JP": "Mattermost",
          "pt_BR": "Mattermost",
          "zh_Hans": "Mattermost"
        },
        "latest_package_identifier": "edtechools/mattermost:0.0.2@ebd569ebb57120ad81dcd383bd00cc74da3c1116cfb3bcdab2c4078a478a2656",
        "latest_version": "0.0.2",
        "model": {},
        "name": "mattermost",
        "org": "edtechools",
        "plugin_id": "edtechools/mattermost",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/mattermost.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "social"
          }
        ],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "edtechools",
            "description": {
              "en_US": "Send message to channel",
              "ja_JP": "チャンネルにメッセージを送信する",
              "pt_BR": "Enviar uma mensagem para o canal",
              "zh_Hans": "向频道发送消息"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Mattermost",
              "pt_BR": "Mattermost",
              "zh_Hans": "Mattermost"
            },
            "name": "mattermost",
            "tags": [
              "social",
              "productivity"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Send messages via Incoming Webhook",
                  "pt_BR": "Enviar mensagens através de um Webhook de entrada",
                  "zh_Hans": "通过传入Webhook发送消息"
                },
                "llm": "Send messages via Incoming Webhook"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "edtechools",
                "label": {
                  "en_US": "Send messages via Incoming Webhook",
                  "pt_BR": "Enviar mensagens através de um Webhook de entrada",
                  "zh_Hans": "通过传入Webhook发送消息"
                },
                "name": "incoming_webhook"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The messages you want to send",
                    "pt_BR": "Mensagem a ser enviada",
                    "zh_Hans": "要发送的消息"
                  },
                  "label": {
                    "en_US": "The messages you want to send",
                    "pt_BR": "Mensagem a ser enviada",
                    "zh_Hans": "要发送的消息"
                  },
                  "llm_description": "The messages you want to send",
                  "max": null,
                  "min": null,
                  "name": "message",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Mattermost Incoming Webhook URL",
                    "pt_BR": "URL do Webhook de entrada no Mattermost",
                    "zh_Hans": "Mattermost 中的 传入Webhook 网址"
                  },
                  "label": {
                    "en_US": "Mattermost Incoming Webhook URL",
                    "pt_BR": "URL do Webhook de entrada no Mattermost",
                    "zh_Hans": "Mattermost 中的 传入Webhook 网址"
                  },
                  "llm_description": "Mattermost Incoming Webhook URL",
                  "max": null,
                  "min": null,
                  "name": "webhook_url",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Send messages via the Bot account",
                  "pt_BR": "Enviar mensagens através da conta do bot",
                  "zh_Hans": "通过Bot账号发送消息"
                },
                "llm": "Send messages via the Bot account"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "edtechools",
                "label": {
                  "en_US": "Send messages via the Bot account",
                  "pt_BR": "Enviar mensagens através da conta do bot",
                  "zh_Hans": "通过Bot账号发送消息"
                },
                "name": "bot_accounts"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The messages you want to send",
                    "pt_BR": "Mensagem a ser enviada",
                    "zh_Hans": "要发送的消息"
                  },
                  "label": {
                    "en_US": "The messages you want to send",
                    "pt_BR": "Mensagem a ser enviada",
                    "zh_Hans": "要发送的消息"
                  },
                  "llm_description": "The messages you want to send",
                  "max": null,
                  "min": null,
                  "name": "message",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Channel ID where the message will be sent",
                    "pt_BR": "ID do canal de destino da mensagem",
                    "zh_Hans": "消息要发送到的频道的ID"
                  },
                  "label": {
                    "en_US": "Channel ID where the message will be sent",
                    "pt_BR": "ID do canal de destino da mensagem",
                    "zh_Hans": "消息要发送到的频道的ID"
                  },
                  "llm_description": "Channel ID where the message will be sent",
                  "max": null,
                  "min": null,
                  "name": "channel_id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Message type",
                    "pt_BR": "Tipo de mensagem",
                    "zh_Hans": "消息的类型"
                  },
                  "label": {
                    "en_US": "Message type",
                    "pt_BR": "Tipo de mensagem",
                    "zh_Hans": "消息的类型"
                  },
                  "llm_description": "TMessage type",
                  "max": null,
                  "min": null,
                  "name": "message_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "normal post",
                        "pt_BR": "Postagem normal",
                        "zh_Hans": "普通消息"
                      },
                      "value": "normal"
                    },
                    {
                      "label": {
                        "en_US": "ephemeral post",
                        "pt_BR": "Post efêmero",
                        "zh_Hans": "即时消息"
                      },
                      "value": "ephemeral"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The ID of the user to whom the instant message is to be sent",
                    "pt_BR": "O ID do usuário para quem a mensagem instantânea deve ser enviada",
                    "zh_Hans": "即时消息要发送给的用户的id"
                  },
                  "label": {
                    "en_US": "The ID of the user to whom the instant message is to be sent",
                    "pt_BR": "O ID do usuário para quem a mensagem instantânea deve ser enviada",
                    "zh_Hans": "即时消息要发送给的用户的id"
                  },
                  "llm_description": "The ID of the user to whom the instant message is to be sent",
                  "max": null,
                  "min": null,
                  "name": "user_id",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "bot's access token",
                    "pt_BR": "Token de acesso do bot",
                    "zh_Hans": "bot的访问令牌"
                  },
                  "label": {
                    "en_US": "Bot access token",
                    "pt_BR": "Token de acesso do bot",
                    "zh_Hans": "Bot的访问令牌"
                  },
                  "llm_description": "Bot access token",
                  "max": null,
                  "min": null,
                  "name": "bot_access_token",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "secret-input"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The domain name used to deploy the Mattermost service.",
                    "pt_BR": "O domínio para implantar o serviço Mattermost.",
                    "zh_Hans": "部署Mattermost服务的域名"
                  },
                  "label": {
                    "en_US": "Domain name for the Mattermost service",
                    "pt_BR": "Domínio para implantação do Mattermost.",
                    "zh_Hans": "部署Mattermost服务的域名"
                  },
                  "llm_description": "The domain name used to deploy the Mattermost service",
                  "max": null,
                  "min": null,
                  "name": "mattermost_domain",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 443,
                  "form": "form",
                  "human_description": {
                    "en_US": "Operating port for the Mattermost service",
                    "pt_BR": "Porta de operação do serviço Mattermost",
                    "zh_Hans": "Mattermost服务的运行端口"
                  },
                  "label": {
                    "en_US": "Mattermost service port",
                    "pt_BR": "Porta do serviço Mattermost",
                    "zh_Hans": "Mattermost服务的运行端口"
                  },
                  "llm_description": "Mattermost service port",
                  "max": null,
                  "min": null,
                  "name": "mattermost_port",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-17T15:49:31Z",
        "version_updated_at": "2025-04-17T15:49:31Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "A collection of tools for GPG operations: encrypt, decrypt, sign, verify messages, and generate key pairs using pgpy.",
          "ja_JP": "Encrypt, decrypt, sign, and verify text messages using GPG (GnuPG).",
          "pt_BR": "Encrypt, decrypt, sign, and verify text messages using GPG (GnuPG).",
          "zh_Hans": "一套用于 GPG 操作的工具集：使用 pgpy 进行消息加密、解密、签名、验证以及生成密钥对。"
        },
        "category": "tool",
        "created_at": "2025-04-21T20:56:04Z",
        "endpoint": {},
        "icon": "alterxyz/packages/gpg_text/_assets/icon.svg",
        "index_id": "alterxyz___gpg_text",
        "install_count": 58,
        "introduction": "# GPG Text Tools Plugin for Dify\n\nThis plugin provides a suite of tools for performing common GPG (GNU Privacy Guard) operations on text directly within Dify, utilizing the `pgpy` Python library. It allows users and AI agents to encrypt, decrypt, sign, and verify messages, as well as generate new GPG key pairs.\n\n## Features\n\nThe plugin includes the following tools:\n\n1.  **GPG Encrypt Message (`encrypt_message`)**: Encrypts a plaintext message using a recipient's GPG public key.\n2.  **GPG Decrypt Message (`decrypt_message`)**: Decrypts a GPG-encrypted message using the recipient's private key and optional passphrase.\n3.  **GPG Sign Message (`sign_message`)**: Creates a detached GPG signature for a plaintext message using the signer's private key and optional passphrase.\n4.  **GPG Verify Signature (`verify_message`)**: Verifies a detached GPG signature against the original message using the signer's public key.\n5.  **GPG Generate Key Pair (`generate_key_pair`)**: Generates a new GPG key pair (public and private keys) with specified user details and optional parameters.\n\n## Setup\n\nNo specific setup is required beyond adding the plugin to Dify. The necessary `pgpy` library is included in the plugin's requirements.\n\n## Usage\n\nEach tool requires specific inputs, typically provided as parameters within Dify.\n\n### 1. Encrypt Message\n\n*   **Parameters**:\n    *   `plaintext`: The text message you want to encrypt.\n    *   `recipient_pubkey_str`: The recipient's full ASCII-armored GPG public key block.\n*   **Output**: The encrypted message in ASCII-armored PGP format.\n\n### 2. Decrypt Message\n\n*   **Parameters**:\n    *   `encrypted_message_str`: The full ASCII-armored PGP encrypted message block.\n    *   `private_key_str`: Your full ASCII-armored GPG private key block. **Handle with extreme care.**\n    *   `passphrase` (Optional): The passphrase protecting your private key, if applicable.\n*   **Output**: The decrypted plaintext message.\n\n### 3. Sign Message\n\n*   **Parameters**:\n    *   `message_to_sign`: The text message you want to sign.\n    *   `signer_private_key_str`: Your full ASCII-armored GPG private key block used for signing. **Handle with extreme care.**\n    *   `passphrase` (Optional): The passphrase protecting your private key, if applicable.\n*   **Output**: The detached ASCII-armored GPG signature.\n\n### 4. Verify Signature\n\n*   **Parameters**:\n    *   `original_message`: The original plaintext message that was signed.\n    *   `signature_blob`: The detached ASCII-armored GPG signature block.\n    *   `signer_pubkey_str`: The signer's full ASCII-armored GPG public key block.\n*   **Output**: A boolean value (`true` or `false`) indicating if the signature is valid, along with a descriptive text message.\n\n### 5. Generate Key Pair\n\n*   **Parameters**:\n    *   `real_name`: The name to associate with the key (e.g., \"Alice Wonderland\").\n    *   `email`: The email address to associate with the key (e.g., \"alice@example.com\").\n    *   `passphrase` (Optional): A passphrase to protect the generated private key. Highly recommended.\n    *   `key_type` (Optional): The primary key algorithm (e.g., `EdDSA`, `RSAEncryptOrSign`). Defaults to `EdDSA`.\n    *   `key_param` (Optional): Key length (for RSA/DSA) or curve name (for ECC). Defaults depend on `key_type`.\n*   **Output**: The generated public key and private key in ASCII-armored format. **Securely store the private key and passphrase immediately.**\n\n## Security Considerations\n\n*   **Private Key Handling**: Private keys and passphrases are highly sensitive. This plugin requires them as direct input parameters for decryption and signing. Be extremely cautious about how and where you provide this information within Dify. Avoid storing them directly in prompts or workflow configurations if possible. Consider using secure credential management features if available in your Dify setup.\n*   **No Key Storage**: This plugin does not store any keys or passphrases beyond the immediate execution scope of a tool invocation. The responsibility for secure key management lies entirely with the user.\n*   **Generated Keys**: When generating keys, immediately copy and securely store the private key and its passphrase outside of Dify. The plugin will output them, but does not retain them.\n\n## Underlying Library\n\nThis plugin uses the [pgpy](https://pgpy.readthedocs.io/en/latest/) library for all cryptographic operations.\n\n\n\n",
        "label": {
          "en_US": "GPG Text Tools",
          "ja_JP": "gpg_text",
          "pt_BR": "gpg_text",
          "zh_Hans": "GPG 文本工具"
        },
        "latest_package_identifier": "alterxyz/gpg_text:0.0.1@8598cc71f5d45a5fbdd2c1da8c20b279d7c2b0b94b907ca1dbf8126ef07feace",
        "latest_version": "0.0.1",
        "model": {},
        "name": "gpg_text",
        "org": "alterxyz",
        "plugin_id": "alterxyz/gpg_text",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/gpg_text.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {}
        },
        "status": "active",
        "tags": [
          {
            "name": "utilities"
          }
        ],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "alterxyz",
            "description": {
              "en_US": "Provides tools to encrypt, decrypt, sign, verify text messages, and generate GPG key pairs.",
              "zh_Hans": "提供加密、解密、签名、验证文本消息以及生成 GPG 密钥对的工具。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "gpg_text",
              "pt_BR": "gpg_text",
              "zh_Hans": "gpg_text"
            },
            "name": "gpg_text",
            "tags": [
              "utilities"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Encrypts a text message using a recipient's GPG public key.",
                  "zh_Hans": "使用接收者的 GPG 公钥加密文本消息。"
                },
                "llm": "Use this tool to encrypt a given plaintext message using the recipient's ASCII-armored GPG public key. Returns the encrypted message as an ASCII-armored string."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "alterxyz",
                "label": {
                  "en_US": "GPG Encrypt Message",
                  "zh_Hans": "GPG 加密消息"
                },
                "name": "encrypt_message"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The text message you want to encrypt.",
                    "zh_Hans": "你想要加密的文本消息。"
                  },
                  "label": {
                    "en_US": "Plaintext Message",
                    "zh_Hans": "明文消息"
                  },
                  "llm_description": "The plaintext content that needs to be encrypted.",
                  "max": null,
                  "min": null,
                  "name": "plaintext",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The recipient's ASCII-armored GPG public key string (starts with '-----BEGIN PGP PUBLIC KEY BLOCK-----').",
                    "zh_Hans": "接收者的 ASCII 封装 GPG 公钥字符串（以 '-----BEGIN PGP PUBLIC KEY BLOCK-----' 开头）。"
                  },
                  "label": {
                    "en_US": "Recipient Public Key",
                    "zh_Hans": "接收者公钥"
                  },
                  "llm_description": "The full ASCII-armored PGP public key block of the intended recipient. It must start with '-----BEGIN PGP PUBLIC KEY BLOCK-----' and end with '-----END PGP PUBLIC KEY BLOCK-----'.",
                  "max": null,
                  "min": null,
                  "name": "recipient_pubkey_str",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Decrypts a GPG encrypted message using your private key.",
                  "zh_Hans": "使用你的私钥解密 GPG 加密的消息。"
                },
                "llm": "Use this tool to decrypt a GPG encrypted message (ASCII-armored format) using the recipient's private key. Requires the private key string."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "alterxyz",
                "label": {
                  "en_US": "GPG Decrypt Message",
                  "zh_Hans": "GPG 解密消息"
                },
                "name": "decrypt_message"
              },
              "output_schema": {
                "properties": {
                  "decrypted_message": {
                    "description": "The decrypted plaintext message.",
                    "type": "string"
                  }
                },
                "type": "object"
              },
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ASCII-armored GPG encrypted message string (starts with '-----BEGIN PGP MESSAGE-----').",
                    "zh_Hans": "ASCII 封装的 GPG 加密消息字符串（以 '-----BEGIN PGP MESSAGE-----' 开头）。"
                  },
                  "label": {
                    "en_US": "Encrypted Message",
                    "zh_Hans": "加密消息"
                  },
                  "llm_description": "The complete ASCII-armored PGP encrypted message block that needs to be decrypted.",
                  "max": null,
                  "min": null,
                  "name": "encrypted_message_str",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Your ASCII-armored GPG private key string (starts with '-----BEGIN PGP PRIVATE KEY BLOCK-----'). Keep this secure!",
                    "zh_Hans": "你的 ASCII 封装 GPG 私钥字符串（以 '-----BEGIN PGP PRIVATE KEY BLOCK-----' 开头）。请妥善保管！"
                  },
                  "label": {
                    "en_US": "Private Key",
                    "zh_Hans": "私钥"
                  },
                  "llm_description": "The full ASCII-armored PGP private key block corresponding to the recipient's public key used for encryption. It must start with '-----BEGIN PGP PRIVATE KEY BLOCK-----'. This is highly sensitive.",
                  "max": null,
                  "min": null,
                  "name": "private_key_str",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The passphrase for your private key, if it's protected.",
                    "zh_Hans": "如果你的私钥受密码保护，请输入密码短语。"
                  },
                  "label": {
                    "en_US": "Passphrase (Optional)",
                    "zh_Hans": "密码短语（可选）"
                  },
                  "llm_description": "The passphrase needed to unlock the provided private key, if applicable.",
                  "max": null,
                  "min": null,
                  "name": "passphrase",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Creates a detached GPG signature for a text message using your private key.",
                  "zh_Hans": "使用你的私钥为文本消息创建分离式 GPG 签名。"
                },
                "llm": "Use this tool to create a detached ASCII-armored GPG signature for a given plaintext message using the signer's private key. Requires the private key string."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "alterxyz",
                "label": {
                  "en_US": "GPG Sign Message",
                  "zh_Hans": "GPG 签名消息"
                },
                "name": "sign_message"
              },
              "output_schema": {
                "properties": {
                  "signature": {
                    "description": "The detached ASCII-armored GPG signature.",
                    "type": "string"
                  }
                },
                "type": "object"
              },
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The text message you want to create a signature for.",
                    "zh_Hans": "你想要为其创建签名的文本消息。"
                  },
                  "label": {
                    "en_US": "Message to Sign",
                    "zh_Hans": "要签名的消息"
                  },
                  "llm_description": "The plaintext content for which a detached GPG signature should be generated.",
                  "max": null,
                  "min": null,
                  "name": "message_to_sign",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Your ASCII-armored GPG private key string (starts with '-----BEGIN PGP PRIVATE KEY BLOCK-----') used for signing. Keep this secure!",
                    "zh_Hans": "用于签名的你的 ASCII 封装 GPG 私钥字符串（以 '-----BEGIN PGP PRIVATE KEY BLOCK-----' 开头）。请妥善保管！"
                  },
                  "label": {
                    "en_US": "Signer Private Key",
                    "zh_Hans": "签名者私钥"
                  },
                  "llm_description": "The full ASCII-armored PGP private key block of the signer. It must start with '-----BEGIN PGP PRIVATE KEY BLOCK-----'. This is highly sensitive.",
                  "max": null,
                  "min": null,
                  "name": "signer_private_key_str",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The passphrase for your private key, if it's protected.",
                    "zh_Hans": "如果你的私钥受密码保护，请输入密码短语。"
                  },
                  "label": {
                    "en_US": "Passphrase (Optional)",
                    "zh_Hans": "密码短语（可选）"
                  },
                  "llm_description": "The passphrase needed to unlock the provided private key for signing, if applicable.",
                  "max": null,
                  "min": null,
                  "name": "passphrase",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Verifies a detached GPG signature against an original message using the signer's public key.",
                  "zh_Hans": "使用签名者的公钥验证原始消息的独立 GPG 签名。"
                },
                "llm": "Use this tool to verify if a detached GPG signature (ASCII-armored) is valid for a given original message and the signer's public key (ASCII-armored). Returns true if valid, false otherwise."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "alterxyz",
                "label": {
                  "en_US": "GPG Verify Signature",
                  "zh_Hans": "GPG 验证签名"
                },
                "name": "verify_message"
              },
              "output_schema": {
                "properties": {
                  "is_valid": {
                    "description": "True if the signature is valid, False otherwise.",
                    "type": "boolean"
                  }
                },
                "type": "object"
              },
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The original plaintext message that was signed.",
                    "zh_Hans": "被签名的原始明文消息。"
                  },
                  "label": {
                    "en_US": "Original Message",
                    "zh_Hans": "原始消息"
                  },
                  "llm_description": "The exact original plaintext message content that the signature corresponds to.",
                  "max": null,
                  "min": null,
                  "name": "original_message",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The ASCII-armored detached GPG signature string (starts with '-----BEGIN PGP SIGNATURE-----').",
                    "zh_Hans": "ASCII 封装的独立 GPG 签名字符串（以 '-----BEGIN PGP SIGNATURE-----' 开头）。"
                  },
                  "label": {
                    "en_US": "Detached Signature",
                    "zh_Hans": "独立签名"
                  },
                  "llm_description": "The full ASCII-armored PGP detached signature block.",
                  "max": null,
                  "min": null,
                  "name": "signature_blob",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The signer's ASCII-armored GPG public key string (starts with '-----BEGIN PGP PUBLIC KEY BLOCK-----').",
                    "zh_Hans": "签名者的 ASCII 封装 GPG 公钥字符串（以 '-----BEGIN PGP PUBLIC KEY BLOCK-----' 开头）。"
                  },
                  "label": {
                    "en_US": "Signer Public Key",
                    "zh_Hans": "签名者公钥"
                  },
                  "llm_description": "The full ASCII-armored PGP public key block of the person or entity who supposedly signed the message.",
                  "max": null,
                  "min": null,
                  "name": "signer_pubkey_str",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Generates a new GPG key pair (public and private keys).",
                  "zh_Hans": "生成一个新的 GPG 密钥对（公钥和私钥）。"
                },
                "llm": "Use this tool to generate a new PGP/GPG key pair. Requires a real name and email address. Optionally accepts a passphrase to protect the private key, a key type (e.g., EdDSA, RSAEncryptOrSign), and key parameters (e.g., curve name or key length). Returns both the public and private keys in ASCII-armored format."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "alterxyz",
                "label": {
                  "en_US": "GPG Generate Key Pair",
                  "zh_Hans": "GPG 生成密钥对"
                },
                "name": "generate_key"
              },
              "output_schema": {
                "properties": {
                  "private_key": {
                    "description": "The generated private key in ASCII-armored format. Handle with extreme care.",
                    "type": "string"
                  },
                  "public_key": {
                    "description": "The generated public key in ASCII-armored format.",
                    "type": "string"
                  }
                },
                "type": "object"
              },
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The name associated with the key (e.g., \"Alice Wonderland\").",
                    "zh_Hans": "与密钥关联的名称（例如，“张三”）。"
                  },
                  "label": {
                    "en_US": "Real Name",
                    "zh_Hans": "真实姓名"
                  },
                  "llm_description": "The real name to be included in the User ID of the generated key.",
                  "max": null,
                  "min": null,
                  "name": "real_name",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The email address associated with the key (e.g., \"alice@example.com\").",
                    "zh_Hans": "与密钥关联的电子邮件地址（例如，“zhangsan@example.com”）。"
                  },
                  "label": {
                    "en_US": "Email Address",
                    "zh_Hans": "电子邮件地址"
                  },
                  "llm_description": "The email address to be included in the User ID of the generated key.",
                  "max": null,
                  "min": null,
                  "name": "email",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "An optional passphrase to protect the generated private key. Highly recommended.",
                    "zh_Hans": "用于保护生成的私钥的可选密码短语。强烈推荐使用。"
                  },
                  "label": {
                    "en_US": "Passphrase (Optional)",
                    "zh_Hans": "密码短语（可选）"
                  },
                  "llm_description": "An optional secret passphrase to encrypt the generated private key. If not provided, the private key will not be password-protected.",
                  "max": null,
                  "min": null,
                  "name": "passphrase",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "EdDSA",
                  "form": "form",
                  "human_description": {
                    "en_US": "The algorithm for the primary key (e.g., EdDSA, RSAEncryptOrSign, ECDSA). Defaults to EdDSA.",
                    "zh_Hans": "主密钥的算法（例如，EdDSA、RSAEncryptOrSign、ECDSA）。默认为 EdDSA。"
                  },
                  "label": {
                    "en_US": "Key Type (Optional)",
                    "zh_Hans": "密钥类型（可选）"
                  },
                  "llm_description": "The desired primary key algorithm. Common choices: 'EdDSA' (modern, default), 'ECDSA', 'RSAEncryptOrSign' (legacy compatibility). If a signing-only type is chosen (EdDSA, ECDSA, RSASign), an appropriate encryption subkey will be added automatically.",
                  "max": null,
                  "min": null,
                  "name": "key_type",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Key length (e.g., 3072 for RSA) or curve name (e.g., Ed25519 for EdDSA, NIST_P256 for ECDSA). Defaults depend on Key Type.",
                    "zh_Hans": "密钥长度（例如，RSA 为 3072）或曲线名称（例如，EdDSA 为 Ed25519，ECDSA 为 NIST_P256）。默认值取决于密钥类型。"
                  },
                  "label": {
                    "en_US": "Key Parameter (Optional)",
                    "zh_Hans": "密钥参数（可选）"
                  },
                  "llm_description": "Optional parameter specific to the key type. For RSA/DSA/ElGamal, this is the key length in bits (e.g., '3072'). For EdDSA/ECDSA/ECDH, this is the curve name (e.g., 'Ed25519', 'NIST_P256', 'Curve25519'). If omitted, suitable defaults will be used based on the key_type.",
                  "max": null,
                  "min": null,
                  "name": "key_param",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-21T20:56:10Z",
        "version_updated_at": "2025-04-21T20:56:10Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Tencent Cloud Log Service",
          "ja_JP": "Tencent Cloud Log Service",
          "pt_BR": "Tencent Cloud Log Service",
          "zh_Hans": "腾讯云日志服务CLS"
        },
        "category": "tool",
        "created_at": "2025-04-10T15:29:35Z",
        "endpoint": {},
        "icon": "aurora698/packages/tencentcloud_cls/_assets/icon.svg",
        "index_id": "aurora698___tencentcloud_cls",
        "install_count": 54,
        "introduction": "# Tencent Cloud CLS Plugin for Dify  \n\n## Overview  \n\nThe Tencent Cloud CLS (Cloud Log Service) Plugin enables seamless integration between Dify and Tencent Cloud's powerful log management service.  \n\n## Features  \n\n- ​**Secure Authentication**  \n- ​**Flexible Querying** with CQL support  \n\n\n## Configuration  \n\n### Required Credentials:  \n- SecretId  \n- SecretKey  \n- Default Region (e.g. ap-guangzhou)  \n- Default Topic ID  \n\nGet these from [Tencent Cloud CAM console](https://console.cloud.tencent.com/cam/capi).  \n\n## Usage  \n\n### Basic Query:  \n```\nstatus:404 | select count(*) as error_count\n```\n\n### Advanced Options:  \n- Region override  \n- TopicId override  \n- Time Range (From/To timestamps)  \n- Limit results (default: 20)  \n\n## Examples  \n1. Count 404 errors:  \n```\nstatus:404 | select count(*) as error_count\n```\n2. Find user activities:  \n```\nusername:\"john.doe\" AND action:\"login\"\n```\n\n## Support  \n[Tencent Cloud Online Support](https://cloud.tencent.com/online-service)  \n",
        "label": {
          "en_US": "tencent cloud cls",
          "ja_JP": "tencent cloud cls",
          "pt_BR": "tencent cloud cls",
          "zh_Hans": "腾讯云日志服务"
        },
        "latest_package_identifier": "aurora698/tencentcloud_cls:0.0.1@2a9e56960169b99f4facfd330e48fd35f6f08d9d321e5135de0577084cf1f0c3",
        "latest_version": "0.0.1",
        "model": {},
        "name": "tencentcloud_cls",
        "org": "aurora698",
        "plugin_id": "aurora698/tencentcloud_cls",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/tencent_cls.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Get your SecretId from Tencent Cloud",
                "zh_Hans": "从腾讯云获取您的密钥SecretId"
              },
              "label": {
                "en_US": "SecretId",
                "zh_Hans": "SecretId"
              },
              "name": "SecretId",
              "options": null,
              "placeholder": {
                "en_US": "Please input your SecretId",
                "zh_Hans": "请输入你的密钥SecretId"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://console.cloud.tencent.com/cam/capi"
            },
            {
              "default": null,
              "help": {
                "en_US": "Get your SecretKey from Tencent Cloud",
                "zh_Hans": "从腾讯云获取您的密钥SecretKey"
              },
              "label": {
                "en_US": "SecretKey",
                "zh_Hans": "SecretKey"
              },
              "name": "SecretKey",
              "options": null,
              "placeholder": {
                "en_US": "Please input your SecretKey",
                "zh_Hans": "请输入你的密钥SecretKey"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://console.cloud.tencent.com/cam/capi"
            },
            {
              "default": null,
              "help": {
                "en_US": "Look up the region abbreviation in the documentation.",
                "zh_Hans": "在文档中查询地域简称"
              },
              "label": {
                "en_US": "DefaultRegion",
                "zh_Hans": "默认地域"
              },
              "name": "Region",
              "options": null,
              "placeholder": {
                "en_US": "Please enter your region, for example, ap-guangzhou",
                "zh_Hans": "请输入日志主题所在的地域，例如ap-guangzhou"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": "https://cloud.tencent.com/document/product/614/18940"
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "DefaultLogTopicId",
                "zh_Hans": "默认日志主题ID"
              },
              "name": "TopicId",
              "options": null,
              "placeholder": {
                "en_US": "Please input your TopicId",
                "zh_Hans": "请输入您的日志主题ID"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            }
          ],
          "identity": {
            "author": "aurora698",
            "description": {
              "en_US": "Tencent Cloud Log Service",
              "pt_BR": "Tencent Cloud Log Service",
              "zh_Hans": "腾讯云日志服务CLS"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "tencentcloud cls",
              "pt_BR": "tencentcloud cls",
              "zh_Hans": "腾讯云日志服务"
            },
            "name": "tencentcloud_cls",
            "tags": [
              "other"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Query logs in Tencent Cloud Log Service",
                  "pt_BR": "Query logs in Tencent Cloud Log Service",
                  "zh_Hans": "在腾讯云日志服务中对日志进行检索分析"
                },
                "llm": "Query logs in Tencent Cloud Log Service"
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "cls",
                "label": {
                  "en_US": "cls_log_search",
                  "pt_BR": "cls_log_search",
                  "zh_Hans": "CLS日志检索分析"
                },
                "name": "cls_log_search"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Query statement for log search and analysis",
                    "pt_BR": "Query statement for log search and analysis",
                    "zh_Hans": "日志检索分析语句"
                  },
                  "label": {
                    "en_US": "Query statement",
                    "pt_BR": "Query statement",
                    "zh_Hans": "检索分析语句"
                  },
                  "llm_description": "用于在腾讯云日志服务CLS中查询日志，语法符合日志服务CLS查询语法。该语法在继承 Kibana Query Language(简称KQL)、和 Trino SQL语言特性基础上, 添加了自定义的语言特性及函数，简称为CQL语言(全称CLS Query Language)。例如使用status:404检索响应状态码为404的应用请求日志,使用status:404 | select count(*) as logCounts统计响应状态码为404的日志数量",
                  "max": null,
                  "min": null,
                  "name": "Query",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The log topic's associated region, defaults to the default region when not specified.",
                    "pt_BR": "The log topic's associated region, defaults to the default region when not specified.",
                    "zh_Hans": "日志主题所属地域，未指定时采用默认地域"
                  },
                  "label": {
                    "en_US": "Region",
                    "pt_BR": "Region",
                    "zh_Hans": "地域"
                  },
                  "llm_description": "要查询的日志主题所属的地域，未指定时采用凭证中设置的默认地域",
                  "max": null,
                  "min": null,
                  "name": "Region",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The log topic ID to query, defaults to the default topic when not specified.",
                    "pt_BR": "The log topic ID to query, defaults to the default topic when not specified.",
                    "zh_Hans": "要查询的日志主题ID，未指定时采用默认主题"
                  },
                  "label": {
                    "en_US": "TopicId",
                    "pt_BR": "TopicId",
                    "zh_Hans": "日志主题ID"
                  },
                  "llm_description": "要查询的日志主题ID，未指定时采用凭证中设置的默认主题ID",
                  "max": null,
                  "min": null,
                  "name": "TopicId",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The start time for the logs to be retrieved and analyzed, in Unix timestamp (milliseconds). If not provided, it defaults to 30 minutes ago.",
                    "pt_BR": "The start time for the logs to be retrieved and analyzed, in Unix timestamp (milliseconds). If not provided, it defaults to 30 minutes ago.",
                    "zh_Hans": "查要检索分析的日志的起始时间，Unix时间戳（毫秒），如不提供则默认为30分钟前"
                  },
                  "label": {
                    "en_US": "From Time",
                    "pt_BR": "From Time",
                    "zh_Hans": "起始时间"
                  },
                  "llm_description": "查要检索分析的日志的起始时间，Unix时间戳（毫秒），如不提供则默认为30分钟前",
                  "max": null,
                  "min": null,
                  "name": "From",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The start time for retrieving and analyzing logs, in Unix timestamp (milliseconds). If not provided, it defaults to the current time.",
                    "pt_BR": "The start time for retrieving and analyzing logs, in Unix timestamp (milliseconds). If not provided, it defaults to the current time.",
                    "zh_Hans": "查要检索分析的日志的起始时间，Unix时间戳（毫秒），如不提供则默认为当前时间"
                  },
                  "label": {
                    "en_US": "To Time",
                    "pt_BR": "To Time",
                    "zh_Hans": "结束时间"
                  },
                  "llm_description": "查要检索分析的日志的起始时间，Unix时间戳（毫秒），如不提供则默认为当前时间",
                  "max": null,
                  "min": null,
                  "name": "To",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The number of raw log entries returned in a single query, with a default of 100 and a maximum of 1000",
                    "pt_BR": "The number of raw log entries returned in a single query, with a default of 100 and a maximum of 1000",
                    "zh_Hans": "单次查询返回的原始日志条数，默认为20，最大值为1000"
                  },
                  "label": {
                    "en_US": "Limit",
                    "pt_BR": "Limit",
                    "zh_Hans": "返回数量限制"
                  },
                  "llm_description": "单次查询返回的原始日志条数，默认为20，最大值为1000",
                  "max": null,
                  "min": null,
                  "name": "Limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-10T15:29:41Z",
        "version_updated_at": "2025-04-10T15:29:41Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "This plugin provides Upstash's Redis-based rate limiting service integrated with Dify AI platform.",
          "ja_JP": "This plugin provides Upstash's Redis-based rate limiting service integrated with Dify AI platform.",
          "pt_BR": "This plugin provides Upstash's Redis-based rate limiting service integrated with Dify AI platform.",
          "zh_Hans": "This plugin provides Upstash's Redis-based rate limiting service integrated with Dify AI platform."
        },
        "category": "tool",
        "created_at": "2025-03-31T08:00:10Z",
        "endpoint": {},
        "icon": "elifnurdeniz/packages/upstash-ratelimit/_assets/icon.svg",
        "index_id": "elifnurdeniz___upstash-ratelimit",
        "install_count": 51,
        "introduction": "## upstash-ratelimit\n\n**Author:** elifnurdeniz\n**Version:** 0.0.1\n**Type:** tool\n\n### Description\n\n# Upstash Rate Limit Plugin for Dify\n\n## 🚀 Overview\nThe **Upstash Rate Limit Plugin** integrates Upstash's Redis-based rate limiting service with the Dify AI platform. This plugin allows developers to enforce request limits within a defined time window using **fixed** or **sliding** window strategies.\n\n## ✨ Benefits\n- **Prevents API Exhaustion** – Ensures services are not overwhelmed by excessive requests, protecting system resources.\n- **Protects Against Abuse & Misuse** – Limits excessive requests from malicious actors or misconfigured applications.\n- **Optimizes Costs** – Prevents unnecessary API usage, reducing server costs for cloud-based applications.\n- **Built for Scalability** – Upstash Redis is a serverless database, ensuring the rate limiter scales with flexibility both up and down.\n\n## 🛠️ Features\n- **Redis-Based Rate Limiting**: Leverages Upstash Redis for efficient rate limiting.\n- **Fixed and Sliding Window Support**: Choose between different rate-limiting strategies.\n- **Per User or Global Rate Limiting**: Apply rate limits per user or globally.\n- **Customizable Parameters**: Configure window size, max requests, and rate limit scope.\n\n## 🔧 Setup & Configuration\n\n### 1️⃣ **Prerequisites**\n- A Dify AI instance running\n- An Upstash Redis account ([Sign up here](https://console.upstash.com/))\n- A Redis Database ([Create from here](https://console.upstash.com/redis?teamid=0))\n- Your Upstash Redis **REST URL** and **REST Token**\n\n### 2️⃣ **Installation**\nTo install and activate the plugin:\n1. Navigate to the **Dify Plugin Store**.\n2. Search for **Upstash-Ratelimit**.\n3. Click **Install** and follow the setup instructions.\n\n### 3️⃣ **Plugin Configuration**\nAfter installation, you must provide:\n- **Upstash Redis REST URL**: The REST API endpoint for your Upstash Redis database.\n- **Upstash Redis REST Token**: The API authentication token for your Redis instance.\n\n### 4️⃣ **Usage**\nThis plugin can be used within a Dify **Chatflow / Workflow / Agent**  to control request limits.\nThe plugin outputs structured **JSON data**, including key fields that can be used to handle the request.\nThe **success** or **failure** of a request can be verified using the `status` variable.\nYou can add an `IF/ELSE` condition in the app:\n* If the status contains \"success\", continue the request.\n* If status contains \"error\", take alternative actions (e.g., return a rate limit exceeded message).\n\n![image](./_assets/usage.png)\n\n\n#### 📌 **Available Parameters**\n| Parameter        | Type    | Required | Description |\n|-----------------|---------|----------|-------------|\n| `window type`   | Select  | ✅ Yes   | Defines the rate limit type (`fixed window` or `sliding window`). Learn more [here](https://upstash.com/docs/redis/sdks/ratelimit-py/algorithms). |\n| `window size`   | Number  | ✅ Yes   | Time window size in seconds. |\n| `max requests`  | Number  | ✅ Yes   | Maximum allowed requests within the window. |\n| `rate limit scope` | Select | ✅ Yes  | Applies rate limit rule for all users or per user. |\n| `rate`          | Number  | ❌ No   | Number of requests deducted per operation. Defaults to `1`. |\n\n#### ✅ **Example Usage**\nA sliding window rate limit that allows 10 requests per minute globally:\n```json\n{\n  \"window type\": \"sliding window\",\n  \"window size\": 60,\n  \"max requests\": 10,\n  \"rate limit scope\": \"global\"\n}\n```\n\nIn console:\n<br/>\n\n<img src=\"./_assets/configuration.png\" width=40% />\n\n\n### Author\nGithub: [Elifnurdeniz](https://github.com/Elifnurdeniz)\nMail: elif.deniz@std.bogazici.edu.tr\nRepo: [Upstash Ratelimit Plugin](https://github.com/Elifnurdeniz/Upstash-Rate-Limiting-Plugin-For-Dify)\n\n",
        "label": {
          "en_US": "upstash-ratelimit",
          "ja_JP": "upstash-ratelimit",
          "pt_BR": "upstash-ratelimit",
          "zh_Hans": "upstash-ratelimit"
        },
        "latest_package_identifier": "elifnurdeniz/upstash-ratelimit:0.0.1@ad8c7cf4d1140b62cef4d1ea0ad87aefe1facc1b8633ceef7b93047d0b778031",
        "latest_version": "0.0.1",
        "model": {},
        "name": "upstash-ratelimit",
        "org": "elifnurdeniz",
        "plugin_id": "elifnurdeniz/upstash-ratelimit",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/upstash-ratelimit.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Get your Upstash Redis Rest URL from Upstash",
                "zh_Hans": "从 Upstash 获取您的 Upstash Redis Rest URL"
              },
              "label": {
                "en_US": "Upstash Redis Rest URL",
                "zh_Hans": "Upstash Redis Rest URL"
              },
              "name": "UPSTASH_REDIS_REST_URL",
              "options": null,
              "placeholder": {
                "en_US": "Please enter your Upstash Redis Rest URL",
                "zh_Hans": "请输入你的 Upstash Redis Rest URL"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://console.upstash.com/redis?teamid=0"
            },
            {
              "default": null,
              "help": {
                "en_US": "Get your Upstash Redis Token from Upstash",
                "zh_Hans": "从 Upstash 获取您的 Upstash Redis Token"
              },
              "label": {
                "en_US": "Upstash Redis Token",
                "zh_Hans": "Upstash Redis Token"
              },
              "name": "UPSTASH_REDIS_REST_TOKEN",
              "options": null,
              "placeholder": {
                "en_US": "Please enter your Upstash Redis Token",
                "zh_Hans": "请输入你的 Upstash Redis Token"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://console.upstash.com/redis?teamid=0"
            }
          ],
          "identity": {
            "author": "elifnurdeniz",
            "description": {
              "en_US": "This plugin provides Upstash's Redis-based rate limiting service integrated with Dify AI platform.",
              "zh_Hans": "该插件提供了基于 Upstash 的 Redis 与 Dify AI 平台集成的速率限制服务。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "upstash-ratelimit",
              "zh_Hans": "upstash-ratelimit"
            },
            "name": "upstash-ratelimit",
            "tags": [
              "other"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "This plugin provides Upstash's Redis-based rate limiting service integrated with Dify AI platform.",
                  "zh_Hans": "该插件提供了基于 Upstash 的 Redis 与 Dify AI 平台集成的速率限制服务。"
                },
                "llm": "This plugin provides Upstash's Redis-based rate limiting service integrated with Dify AI platform."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "elifnurdeniz",
                "label": {
                  "en_US": "upstash-ratelimit",
                  "zh_Hans": "upstash-ratelimit"
                },
                "name": "upstash-ratelimit"
              },
              "output_schema": {
                "properties": {
                  "limit": {
                    "description": "The maximum number of requests allowed in the given time window",
                    "type": "integer"
                  },
                  "message": {
                    "description": "Provides a message about the rate limiting result",
                    "type": "string"
                  },
                  "remaining": {
                    "description": "The number of remaining requests in the current window",
                    "type": "integer"
                  },
                  "reset_time": {
                    "description": "The UNIX timestamp (in seconds) when the limit resets",
                    "type": "number"
                  },
                  "status": {
                    "description": "Indicates whether the request was allowed or blocked",
                    "enum": [
                      "success",
                      "error"
                    ],
                    "type": "string"
                  }
                },
                "type": "object"
              },
              "parameters": [
                {
                  "auto_generate": null,
                  "default": "sliding window",
                  "form": "form",
                  "human_description": {
                    "en_US": "The type of window to use for rate limiting. The plugin supports two types of windows, sliding window and fixed window.",
                    "zh_Hans": "用于速率限制的窗口类型。插件支持两种窗口类型，滑动窗口和固定窗口。"
                  },
                  "label": {
                    "en_US": "Window Type",
                    "zh_Hans": "窗口类型"
                  },
                  "llm_description": "This parameter determines window type for rate limiting. The plugin supports two types of windows, sliding window and fixed window.",
                  "max": null,
                  "min": null,
                  "name": "window type",
                  "options": [
                    {
                      "label": {
                        "en_US": "Sliding Window",
                        "zh_Hans": "滑动窗口"
                      },
                      "value": "sliding window"
                    },
                    {
                      "label": {
                        "en_US": "Fixed Window",
                        "zh_Hans": "固定窗口"
                      },
                      "value": "fixed window"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The size of the window in seconds.",
                    "zh_Hans": "窗口的大小（以秒为单位）。"
                  },
                  "label": {
                    "en_US": "Window Size",
                    "zh_Hans": "窗口大小"
                  },
                  "llm_description": "This parameter determines the size of the window in seconds.",
                  "max": null,
                  "min": 1,
                  "name": "window size",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The maximum number of requests allowed within the specified window size.",
                    "zh_Hans": "指定时间窗口内允许的最大请求数。"
                  },
                  "label": {
                    "en_US": "Max Requests",
                    "zh_Hans": "最大请求数"
                  },
                  "llm_description": "Defines the maximum number of requests allowed within the specified window size.",
                  "max": null,
                  "min": 1,
                  "name": "max requests",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": "global",
                  "form": "form",
                  "human_description": {
                    "en_US": "Choose whether the rate limit should apply globally or per user.",
                    "zh_Hans": "选择速率限制是否适用于全局或每个用户。"
                  },
                  "label": {
                    "en_US": "Rate Limit Scope",
                    "zh_Hans": "限速范围"
                  },
                  "llm_description": "Defines whether the rate limit should be applied to all requests (global) or per individual user (user).",
                  "max": null,
                  "min": null,
                  "name": "rate limit scope",
                  "options": [
                    {
                      "label": {
                        "en_US": "Global",
                        "zh_Hans": "全局"
                      },
                      "value": "global"
                    },
                    {
                      "label": {
                        "en_US": "Per User",
                        "zh_Hans": "每个用户"
                      },
                      "value": "per user"
                    }
                  ],
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 1,
                  "form": "form",
                  "human_description": {
                    "en_US": "The number of tokens deducted per request. Defaults to 1 if not provided.",
                    "zh_Hans": "每次操作要减少的令牌数。如果未提供，则默认为 1。"
                  },
                  "label": {
                    "en_US": "Rate",
                    "zh_Hans": "速率"
                  },
                  "llm_description": "Determines how many requests should be subtracted from the rate limit per action.",
                  "max": null,
                  "min": 1,
                  "name": "rate",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-31T08:00:20Z",
        "version_updated_at": "2025-03-31T08:00:20Z"
      },
      {
        "agent_strategy": null,
        "badges": [],
        "brief": {
          "en_US": "A Telegraph plugin that allow you publish your content easily",
          "ja_JP": "コンテンツを簡単に公開できるTelegraphプラグイン",
          "pt_BR": "Um plugin do Telegraph que permite publicar seu conteúdo facilmente",
          "zh_Hans": "一个让您轻松发布内容的Telegraph插件"
        },
        "category": "tool",
        "created_at": "2024-12-18T08:29:41Z",
        "endpoint": {},
        "icon": "alterxyz/packages/telegraph/_assets/icon.svg",
        "index_id": "alterxyz___telegraph",
        "install_count": 47,
        "introduction": "## Telegraph\n\nA simple tool to publish your content to Telegraph!\n\n### Getting Started - Obtain Telegraph Access Token\n\n1. Access Telegraph with your preferred name settings:\n\n    - You can customize the display name\n    - Optionally add a link to your name\n    - Follow the provided authentication link\n\n2. You'll receive a response like this:\n\n```json\n{\"ok\":true,\"result\":{\"short_name\":\"Sandbox\",\"author_name\":\"Anonymous\",\"author_url\":\"/api\",\"access_token\":\"123456uvwxyz\",\"auth_url\":\"https://edit.telegra.ph/auth/abcdefgh\"}}\n```\n\n3. Copy the `access_token` value and use it to configure this plugin.\n\n~~Some link and one-click guide~~\n",
        "label": {
          "en_US": "Telegraph",
          "ja_JP": "Telegraph",
          "pt_BR": "Telegraph",
          "zh_Hans": "Telegraph"
        },
        "latest_package_identifier": "alterxyz/telegraph:0.0.2@2a19a7dd153aae31adc342aa75210cedaba4b8919cae8e7e2e57e488d37b91f2",
        "latest_version": "0.0.2",
        "model": {},
        "name": "telegraph",
        "org": "alterxyz",
        "plugin_id": "alterxyz/telegraph",
        "plugins": {
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/telegraph.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "helper": null,
              "label": {
                "en_US": "Telegraph Access Token",
                "ja_JP": "Telegraph Access Token",
                "pt_BR": "Telegraph Access Token",
                "zh_Hans": "Telegraph Access Token"
              },
              "name": "telegraph_access_token",
              "options": null,
              "placeholder": {
                "en_US": "Please input your Telegraph Access Token",
                "ja_JP": "Telegraphアクセストークンを入力してください",
                "pt_BR": "Por favor, insira seu Token de Acesso do Telegraph",
                "zh_Hans": "请输入您的Telegraph访问令牌"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://telegra.ph/api#createAccount"
            }
          ],
          "identity": {
            "author": "alterxyz",
            "description": {
              "en_US": "A Telegraph plugin that allows you to publish your content easily",
              "ja_JP": "コンテンツを簡単に公開できるTelegraphプラグイン",
              "pt_BR": "Um plugin do Telegraph que permite publicar seu conteúdo facilmente",
              "zh_Hans": "一个让您轻松发布内容的Telegraph插件"
            },
            "icon": "icon.jpg",
            "label": {
              "en_US": "Telegraph",
              "pt_BR": "Telegraph",
              "zh_Hans": "Telegraph"
            },
            "name": "telegraph",
            "tags": [
              "social",
              "productivity",
              "utilities"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A simple telegraph plugin that allow you publish your content easily",
                  "pt_BR": "Um plugin telegraph simples que permite publicar seu conteúdo facilmente",
                  "zh_Hans": "一个简单的 telegraph 插件，可以让您轻松发布内容"
                },
                "llm": "A simple telegraph plugin that allow you publish your content easily, your content will be published to telegraph, the format of the content you providing should be in markdown."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "alterxyz",
                "label": {
                  "en_US": "Telegraph",
                  "pt_BR": "Telegraph",
                  "zh_Hans": "Telegraph"
                },
                "name": "telegraph"
              },
              "output_schema": null,
              "parameters": [
                {
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The title of the post",
                    "pt_BR": "O título do post",
                    "zh_Hans": "文章标题"
                  },
                  "label": {
                    "en_US": "Post title",
                    "pt_BR": "Título do post",
                    "zh_Hans": "文章标题"
                  },
                  "llm_description": "The title of the post, should be pure plain text, short and meaningful.",
                  "max": null,
                  "min": null,
                  "name": "p_title",
                  "options": null,
                  "required": true,
                  "scope": null,
                  "type": "string"
                },
                {
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The content of the post",
                    "pt_BR": "O conteúdo do post",
                    "zh_Hans": "文章内容"
                  },
                  "label": {
                    "en_US": "Post content",
                    "pt_BR": "Conteúdo do post",
                    "zh_Hans": "文章内容"
                  },
                  "llm_description": "The content of the post, should be in markdown format.",
                  "max": null,
                  "min": null,
                  "name": "p_content",
                  "options": null,
                  "required": true,
                  "scope": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "A Telegraph plugin that allows you to publish your content with custom settings",
                  "ja_JP": "カスタム設定でコンテンツを公開できるTelegraphプラグイン",
                  "pt_BR": "Um plugin do Telegraph que permite publicar seu conteúdo com configurações personalizadas",
                  "zh_Hans": "一个允许您使用自定义设置发布内容的Telegraph插件"
                },
                "llm": "A telegraph plugin that allows you to publish content as posts. Your content will be published to Telegraph, and the content you provide should be in markdown format."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "alterxyz",
                "label": {
                  "en_US": "Telegraph Advanced",
                  "ja_JP": "Telegraph アドバンスド",
                  "pt_BR": "Telegraph Avançado",
                  "zh_Hans": "Telegraph 高级版"
                },
                "name": "telegraph_advanced"
              },
              "output_schema": null,
              "parameters": [
                {
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The title of the post",
                    "ja_JP": "投稿のタイトル",
                    "pt_BR": "O título da publicação",
                    "zh_Hans": "文章的标题"
                  },
                  "label": {
                    "en_US": "Post Title",
                    "ja_JP": "投稿タイトル",
                    "pt_BR": "Título da Publicação",
                    "zh_Hans": "文章标题"
                  },
                  "llm_description": "The title of the post, should be pure plain text, short and meaningful.",
                  "max": null,
                  "min": null,
                  "name": "p_title",
                  "options": null,
                  "required": true,
                  "scope": null,
                  "type": "string"
                },
                {
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The content of the post",
                    "ja_JP": "投稿の内容",
                    "pt_BR": "O conteúdo da publicação",
                    "zh_Hans": "文章的内容"
                  },
                  "label": {
                    "en_US": "Post Content",
                    "ja_JP": "投稿内容",
                    "pt_BR": "Conteúdo da Publicação",
                    "zh_Hans": "文章内容"
                  },
                  "llm_description": "The content of the post, should be in markdown format.",
                  "max": null,
                  "min": null,
                  "name": "p_content",
                  "options": null,
                  "required": true,
                  "scope": null,
                  "type": "string"
                },
                {
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "The Telegraph Access Token for temporary replacement. This article will use this account (Token) instead of the default account for publication.",
                    "ja_JP": "一時的な代替用のTelegraphアクセストークン。この記事は、デフォルトアカウントの代わりにこのアカウント（トークン）を使用して公開されます。",
                    "pt_BR": "O Token de Acesso do Telegraph para substituição temporária. Este artigo usará esta conta (Token) em vez da conta padrão para publicação.",
                    "zh_Hans": "临时替代的Telegraph访问令牌。本文将使用此账号（令牌）而不是默认账号来发布。"
                  },
                  "label": {
                    "en_US": "Alternative Telegraph Access Token",
                    "ja_JP": "代替のTelegraphアクセストークン",
                    "pt_BR": "Token de Acesso Alternativo do Telegraph",
                    "zh_Hans": "替代Telegraph访问令牌"
                  },
                  "llm_description": "",
                  "max": null,
                  "min": null,
                  "name": "a_telegraph_access_token",
                  "options": null,
                  "required": false,
                  "scope": null,
                  "type": "string"
                },
                {
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional. Author name displayed below the article's title. This will replace the default name associated with the account.",
                    "ja_JP": "オプション。記事のタイトルの下に表示される著者名。アカウントに関連付けられているデフォルトの名前を置き換えます。",
                    "pt_BR": "Opcional. Nome do autor exibido abaixo do título do artigo. Isso substituirá o nome padrão associado à conta.",
                    "zh_Hans": "可选。显示在文章标题下方的作者姓名。这将替换与账号关联的默认名称。"
                  },
                  "label": {
                    "en_US": "Author Name",
                    "ja_JP": "著者名",
                    "pt_BR": "Nome do Autor",
                    "zh_Hans": "作者姓名"
                  },
                  "llm_description": "Author name, 0-128 characters in length. If not provided, the default name associated with the account will be used.",
                  "max": null,
                  "min": null,
                  "name": "a_author_name",
                  "options": null,
                  "required": false,
                  "scope": null,
                  "type": "string"
                },
                {
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional. Profile link for the author, opened when users click on the author's name below the title. This will replace the default link associated with the account. Please provide a valid URL, usually start with http:// or https://.",
                    "ja_JP": "オプション。タイトルの下の著者名をクリックした時に開くプロフィールリンク。アカウントに関連付けられているデフォルトのリンクを置き換えます。有効なURL（通常はhttp://またはhttps://で始まる）を入力してください。",
                    "pt_BR": "Link do perfil do autor, aberto quando os usuários clicam no nome do autor abaixo do título. Isso substituirá o link padrão associado à conta. Forneça um URL válido, geralmente começando com http:// ou https://.",
                    "zh_Hans": "可选。作者的个人资料链接，用户点击标题下方的作者姓名时打开。这将替换与账号关联的默认链接。请提供有效的URL，通常以http://或https://开头。"
                  },
                  "label": {
                    "en_US": "Author URL",
                    "ja_JP": "著者URL",
                    "pt_BR": "URL do Autor",
                    "zh_Hans": "作者链接"
                  },
                  "llm_description": "Profile link for the author, 0-512 characters in length. Can be any link, not necessarily a Telegram profile or channel link. If not provided, the default link associated with the account will be used. Please provide a valid URL, usually start with http:// or https://.",
                  "max": null,
                  "min": null,
                  "name": "a_author_url",
                  "options": null,
                  "required": false,
                  "scope": null,
                  "type": "string"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2024-12-27T07:13:49Z",
        "version_updated_at": "2024-12-27T07:13:49Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "RhymeFinder is a powerful tool designed to assist songwriters, poets, and language enthusiasts in discovering perfect rhymes for English words.",
          "ja_JP": "RhymeFinder is a powerful tool designed to assist songwriters, poets, and language enthusiasts in discovering perfect rhymes for English words.",
          "pt_BR": "RhymeFinder is a powerful tool designed to assist songwriters, poets, and language enthusiasts in discovering perfect rhymes for English words.",
          "zh_Hans": "RhymeFinder is a powerful tool designed to assist songwriters, poets, and language enthusiasts in discovering perfect rhymes for English words."
        },
        "category": "tool",
        "created_at": "2025-04-15T18:37:59Z",
        "endpoint": {},
        "icon": "whyteawhy/packages/rhymefinder/_assets/icon.svg",
        "index_id": "whyteawhy___rhymefinder",
        "install_count": 44,
        "introduction": "# RhymeFinder\n\n**Author:** whyteawhy  \n**Version:** 0.0.1  \n**Type:** tool  \n\n## 1. Product Introduction\n\nRhymeFinder is a powerful Dify plugin designed to help writers, poets, songwriters, and rap artists find the perfect rhyming words for their creative work. Leveraging advanced language models like Claude 3.7 Sonnet, RhymeFinder generates comprehensive lists of rhyming words organized by syllable count, making it easier to find the exact rhyme you need for your creative projects.\n\nThis plugin not only provides simple rhymes but offers a rich variety of options with different syllable counts, allowing for more flexibility and creativity in your writing. Each suggested rhyming word comes with a song example where it's used, providing context and inspiration for your own work.\n\n## 2. User Story\n\nMeet Sarah, an aspiring songwriter working on her debut album. She's struggling with the chorus of her latest song, trying to find the perfect rhyme for \"heart\" that conveys the emotional depth she wants to express.\n\nBefore discovering RhymeFinder, Sarah would spend hours with a thesaurus and rhyming dictionary, often settling for obvious rhymes like \"part\" or \"start\" that didn't quite capture the feeling she wanted to convey.\n\nWhen Sarah started using the RhymeFinder plugin in Dify:\n\n1. She entered \"heart\" into the word field\n2. Selected \"full\" for the match type\n3. Set the syllable filter to \"2 syllables\" to find more interesting options\n4. Specified 20 results to get a good variety\n\nWithin seconds, RhymeFinder presented her with two-syllable options like \"depart,\" \"impart,\" and \"restart,\" along with song examples showing how other artists had used these rhymes effectively.\n\nInspired by these options, Sarah completed her chorus with a powerful, unexpected rhyme that elevated her song from good to unforgettable. The plugin saved her hours of creative struggle and helped her discover rhyming possibilities she wouldn't have thought of on her own.\n\n## 3. Parameter Information\n\n### Input Parameters\n\n| Parameter | Type | Description | Required | Default |\n|-----------|------|-------------|----------|--------|\n| `word` | string | The English word to find rhymes for | Yes | - |\n| `match_type` | select | Type of rhyme match (\"full\" or \"partial\") | No | \"full\" |\n| `syllable_filter` | select | Filter results by syllable count | No | \"all\" |\n| `result_count` | number | Number of rhyming words to generate | No | 10 |\n| `model` | model-selector | Language model to use for generating rhymes | No | Claude 3.7 Sonnet |\n\n### Syllable Filter Options\n\n- `all`: Return rhyming words with any syllable count\n- `1`: Return only single-syllable rhyming words\n- `2`: Return only two-syllable rhyming words\n- `3`: Return only three-syllable rhyming words\n- `4`: Return only four-syllable rhyming words\n\n### Result Count\n\n- Minimum: 5 results\n- Maximum: 500 results\n- Default: 10 results\n\n### Output Format\n\nResults are returned in a structured format, grouped by syllable count. For each rhyming word, the following information is provided:\n\n- The rhyming word itself\n- Number of syllables in the word\n- A song example where this rhyming word is used (in the format \"Song Title - Artist\")\n\n## Contact Us\n\nIf you have any questions or suggestions about RhymeFinder, please feel free to contact us via email.\n\n**Email:** whiteayty@gmail.com\n\n**Follow me on Spotify:** [My Homepage 🎵](https://open.spotify.com/artist/4TlxM4kvsQLuMcNymLmBu8?si=THXVa-7HSJSR_x7PKFD78A)\n\n### Email Format\n\nWhen contacting us, please use the following format for your email subject:\n\n**[Question Type] - [Brief Description]**\n\nFor example:\n- **[Bug Report] - Error when filtering by syllable count**\n- **[Feature Request] - Add support for Spanish rhymes**\n- **[General Question] - How to customize output format**",
        "label": {
          "en_US": "rhymefinder",
          "ja_JP": "rhymefinder",
          "pt_BR": "rhymefinder",
          "zh_Hans": "rhymefinder"
        },
        "latest_package_identifier": "whyteawhy/rhymefinder:0.0.1@90b3d26c26d4e2a4d6b432c50ed30b99952a29643686859a17c5de3d56e43248",
        "latest_version": "0.0.1",
        "model": {},
        "name": "rhymefinder",
        "org": "whyteawhy",
        "plugin_id": "whyteawhy/rhymefinder",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/rhymefinder.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": true,
              "rerank": true,
              "speech2text": true,
              "text_embedding": true,
              "tts": true
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "whyteawhy",
            "description": {
              "en_US": "RhymeFinder is a powerful tool designed to assist songwriters, poets, and language enthusiasts in discovering perfect rhymes for English words.",
              "pt_BR": "RhymeFinder is a powerful tool designed to assist songwriters, poets, and language enthusiasts in discovering perfect rhymes for English words.",
              "zh_Hans": "RhymeFinder is a powerful tool designed to assist songwriters, poets, and language enthusiasts in discovering perfect rhymes for English words."
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "rhymefinder",
              "pt_BR": "rhymefinder",
              "zh_Hans": "rhymefinder"
            },
            "name": "rhymefinder",
            "tags": null
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool for finding rhyming words with syllable counts and song examples for a given English word.",
                  "pt_BR": "A tool for finding rhyming words with syllable counts and song examples for a given English word.",
                  "zh_Hans": "一个查询英文押韵词、音节数和歌曲示例的工具。"
                },
                "llm": "A tool for finding perfect rhymes for English words. Given an English word, it returns a list of rhyming words, their syllable counts, and song examples where they are used."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "whyteawhy",
                "label": {
                  "en_US": "RhymeFinder",
                  "pt_BR": "RhymeFinder",
                  "zh_Hans": "押韵词查询"
                },
                "name": "rhymefinder"
              },
              "output_schema": {
                "properties": {
                  "rhyming_words": {
                    "items": {
                      "properties": {
                        "song_example": {
                          "type": "string"
                        },
                        "syllables": {
                          "type": "integer"
                        },
                        "word": {
                          "type": "string"
                        }
                      },
                      "type": "object"
                    },
                    "type": "array"
                  }
                },
                "type": "object"
              },
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The English word to find rhymes for",
                    "pt_BR": "The English word to find rhymes for",
                    "zh_Hans": "需要查询押韵词的英文单词"
                  },
                  "label": {
                    "en_US": "English Word",
                    "pt_BR": "English Word",
                    "zh_Hans": "英文单词"
                  },
                  "llm_description": "The English word for which to find rhyming words. Must be a valid English word.",
                  "max": null,
                  "min": null,
                  "name": "word",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "full",
                  "form": "form",
                  "human_description": {
                    "en_US": "Choose between full rhyme (all syllables) or partial rhyme (last syllables)",
                    "pt_BR": "Choose between full rhyme (all syllables) or partial rhyme (last syllables)",
                    "zh_Hans": "选择完全押韵（所有音节）或部分押韵（最后几个音节）"
                  },
                  "label": {
                    "en_US": "Rhyme Type",
                    "pt_BR": "Rhyme Type",
                    "zh_Hans": "押韵类型"
                  },
                  "llm_description": "Determines if the tool should return words that fully rhyme with the input word (matching all syllables) or partially rhyme (matching only the last syllables).",
                  "max": null,
                  "min": null,
                  "name": "match_type",
                  "options": [
                    {
                      "label": {
                        "en_US": "Full Rhyme",
                        "pt_BR": "Full Rhyme",
                        "zh_Hans": "完全押韵"
                      },
                      "value": "full"
                    },
                    {
                      "label": {
                        "en_US": "Partial Rhyme",
                        "pt_BR": "Partial Rhyme",
                        "zh_Hans": "部分押韵"
                      },
                      "value": "partial"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": "all",
                  "form": "form",
                  "human_description": {
                    "en_US": "Filter results by syllable count",
                    "pt_BR": "Filter results by syllable count",
                    "zh_Hans": "按音节数筛选结果"
                  },
                  "label": {
                    "en_US": "Syllable Filter",
                    "pt_BR": "Syllable Filter",
                    "zh_Hans": "音节筛选"
                  },
                  "llm_description": "Filter the rhyming words by syllable count. Select 'All Syllables' to get words with various syllable counts, or select a specific number to get only words with that syllable count.",
                  "max": null,
                  "min": null,
                  "name": "syllable_filter",
                  "options": [
                    {
                      "label": {
                        "en_US": "All Syllables",
                        "pt_BR": "All Syllables",
                        "zh_Hans": "所有音节"
                      },
                      "value": "all"
                    },
                    {
                      "label": {
                        "en_US": "1 Syllable",
                        "pt_BR": "1 Syllable",
                        "zh_Hans": "1个音节"
                      },
                      "value": "1"
                    },
                    {
                      "label": {
                        "en_US": "2 Syllables",
                        "pt_BR": "2 Syllables",
                        "zh_Hans": "2个音节"
                      },
                      "value": "2"
                    },
                    {
                      "label": {
                        "en_US": "3 Syllables",
                        "pt_BR": "3 Syllables",
                        "zh_Hans": "3个音节"
                      },
                      "value": "3"
                    },
                    {
                      "label": {
                        "en_US": "4 Syllables",
                        "pt_BR": "4 Syllables",
                        "zh_Hans": "4个音节"
                      },
                      "value": "4"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                },
                {
                  "auto_generate": null,
                  "default": 10,
                  "form": "form",
                  "human_description": {
                    "en_US": "Number of rhyming words to generate (5-500)",
                    "pt_BR": "Number of rhyming words to generate (5-500)",
                    "zh_Hans": "要生成的押韵词数量（5-500）"
                  },
                  "label": {
                    "en_US": "Number of Results",
                    "pt_BR": "Number of Results",
                    "zh_Hans": "结果数量"
                  },
                  "llm_description": "The number of rhyming words to generate. Default is 10, minimum is 5, maximum is 500.",
                  "max": 500,
                  "min": 5,
                  "name": "result_count",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "form",
                  "human_description": {
                    "en_US": "Select the language model to use for generating rhymes",
                    "pt_BR": "Selecione o modelo de linguagem para gerar rimas",
                    "zh_Hans": "选择用于生成押韵词的语言模型"
                  },
                  "label": {
                    "en_US": "Language Model",
                    "pt_BR": "Modelo de Linguagem",
                    "zh_Hans": "语言模型"
                  },
                  "llm_description": "The language model to use for generating rhyming words.",
                  "max": null,
                  "min": null,
                  "name": "model",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": "llm",
                  "template": null,
                  "type": "model-selector"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-15T18:38:05Z",
        "version_updated_at": "2025-04-15T18:38:05Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Compatible Dify App's API with Huawei MetaStudio third-party llm api",
          "zh_Hans": "提供将 Dify 应用的API转为华为 MetaStudio 第三方 LLM 兼容的API"
        },
        "category": "extension",
        "created_at": "2025-04-13T16:54:09Z",
        "endpoint": {
          "endpoints": [
            {
              "hidden": false,
              "method": "POST",
              "path": "/metastudio_dify_app/chat"
            }
          ],
          "settings": [
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Base URL",
                "zh_Hans": "Base URL"
              },
              "name": "base_url",
              "options": null,
              "placeholder": {
                "en_US": "Please input your base URL",
                "zh_Hans": "请输入你的基础访问地址"
              },
              "required": true,
              "scope": null,
              "type": "text-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "API key",
                "zh_Hans": "API key"
              },
              "name": "api_key",
              "options": null,
              "placeholder": {
                "en_US": "Please input your API key",
                "zh_Hans": "请输入你的 API key"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "App",
                "zh_Hans": "App"
              },
              "name": "app_id",
              "options": null,
              "placeholder": {
                "en_US": "Please select an app",
                "zh_Hans": "请选择一个应用"
              },
              "required": true,
              "scope": "chat",
              "type": "app-selector",
              "url": null
            },
            {
              "default": null,
              "help": null,
              "label": {
                "en_US": "Memory Mode",
                "zh_Hans": "记忆模式"
              },
              "name": "memory_mode",
              "options": [
                {
                  "label": {
                    "en_US": "Last User Message",
                    "zh_Hans": "使用最后一条用户消息"
                  },
                  "value": "last_user_message"
                }
              ],
              "placeholder": {
                "en_US": "Please select a memory mode, it will decide how the Endpoint manage the context",
                "zh_Hans": "请选择一个上下文模式，它将决定该 Endpoint 使用哪种方式管理上下文"
              },
              "required": true,
              "scope": null,
              "type": "select",
              "url": null
            }
          ]
        },
        "icon": "zix2002/packages/metastudio_dify_app/_assets/icon.svg",
        "index_id": "zix2002___metastudio_dify_app",
        "install_count": 39,
        "introduction": "## MetaStudio Compatible Dify App\n\n**Author:** zix2002<zix2002@gmail.com>\n**Version:** 0.0.2\n**Type:** extension\n\n### Description\n\nThis plugin makes the Dify App API compatible with Huawei MetaStudio's [Intelligent Interaction](https://support.huaweicloud.com/api-metastudio/metastudio_02_0031.html) and [Virtual Avatar LiveStreaming](https://support.huaweicloud.com/usermanual-metastudio/metastudio_05_0137.html) third-party LLM API\n\n\n\n### Configure the plugin\n\n- Click the plugin, click `+` to add `API Endpoint`\n- Input the `Endpoint Name`, for example `/meta-studio/chat`\n- Input the `BASE URL`, your `dify` public access base url, for example `http://localhost:1438`, `https://dify.yourdomain.com`\n- Input the `API Key`, your `dify` api key, for example `sk-xxxxxx`\n- Select the `App` and `Memory Mode`\n- Click `Save`\n\nIf the `SERVICE OK`, the configuration is successful\n\n### Use the plugin\n\nCopy the public access url, for example `http://localhost:1438/e/1m4lpn4s7i3tb523/metastudio_dify_app/chat`,\nwhere `1m4lpn4s7i3tb523` is the `App ID` of `MetaStudio`\n\nIn the `MetaStudio` `Intelligent Interaction Digital Human` page or `Virtual Avatar LiveStreaming` page, you need to configure the following 3 parameters\n\n- `APPID`: `1m4lpn4s7i3tb523`\n- `APPKey`: `sk-xxxxxx`\n- `Third-party LLM address`: `http://localhost:1438/e/1m4lpn4s7i3tb523/metastudio_dify_app/chat`\n\n\n### Notice\n\n1. If you want to install the plugin locally, please modify the `/docker/.env` file, set `FORCE_VERIFYING_SIGNATURE` to `false`\n\n```env\nFORCE_VERIFYING_SIGNATURE=false\n```\n\nThen restart the `dify` container, refresh the page, and then reinstall the plugin\n\n```bash\ndocker compose down\ndocker compose up -d\n```\n\n2. If your extension APP is `Agent mode`, you can only use `stream` mode\nPlease open `Stream response` in the `MetaStudio` `Interactive Digital Human` configuration page\n\n\n",
        "label": {
          "en_US": "MetaStudio Compatible Dify App",
          "zh_Hans": "MetaStudio 兼容 Dify App"
        },
        "latest_package_identifier": "zix2002/metastudio_dify_app:0.0.2@3b2a0a83c01ff24bcf9dcc29b8d3c1ee3839d6b864501421aab3e5c8e8acad29",
        "latest_version": "0.0.2",
        "model": {},
        "name": "metastudio_dify_app",
        "org": "zix2002",
        "plugin_id": "zix2002/metastudio_dify_app",
        "plugins": {
          "agent_strategies": null,
          "endpoints": [
            "group/metastudio_dify_app.yaml"
          ],
          "models": null,
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 1048576,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-13T16:54:16Z",
        "version_updated_at": "2025-04-13T16:54:16Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "Linear integration for Dify. Create, update, search issues, add comments, search users and teams, and get your profile information from Linear directly from your Dify applications.",
          "ja_JP": "DifyのためのLinear統合。Difyアプリケーションから直接、Linearの課題の作成、更新、検索、コメントの追加、ユーザーとチームの検索、および自分のプロフィール情報の取得を行います。",
          "pt_BR": "Integração do Linear para Dify. Crie, atualize, pesquise problemas, adicione comentários, pesquise usuários e equipes e obtenha informações do seu perfil do Linear diretamente de seus aplicativos Dify.",
          "zh_Hans": "Linear 与 Dify 的集成。直接从 Dify 应用程序创建、更新、搜索问题，添加评论，搜索用户和团队，并获取您在 Linear 中的个人资料信息。"
        },
        "category": "tool",
        "created_at": "2025-04-21T06:41:36Z",
        "endpoint": {},
        "icon": "langgenius/packages/linear/_assets/icon.svg",
        "index_id": "langgenius___linear",
        "install_count": 37,
        "introduction": "# Linear Plugin for Dify\n\nThis plugin integrates Linear's project management capabilities with Dify, allowing you to create, update, search, and manage Linear issues, users, and teams directly from your Dify applications.\n\n## Features\n\n- **Create Issues**: Create new Linear issues with title, description, team, priority, and status.\n- **Update Issues**: Modify existing issues by updating their title, description, priority, status, assignee, or labels.\n- **Search Issues**: Find issues based on various criteria such as text, team, status, assignee, labels, and priority.\n- **Get User Issues**: Retrieve issues assigned to a specific user.\n- **Add Comments**: Add comments to existing Linear issues with support for markdown.\n- **Get Users**: Search for users by name or email to find their details (including ID/UUID).\n- **Get Teams**: Search for teams by name to find their details (including ID).\n- **Get My Profile**: Retrieve the profile information of the currently authenticated user.\n\n## Installation\n\n1. Install the plugin through Dify's Plugin Marketplace.\n2. Configure the plugin with your Linear Personal API key.\n\n## Authentication\n\nYou'll need a **Linear Personal API key** to use this plugin:\n\n1. Log in to your Linear account at [linear.app](https://linear.app)\n2. Go to your account settings (click your profile picture in the bottom left)\n3. Navigate to **Settings -> Account -> Security & access** (or visit [https://linear.app/settings/account/security](https://linear.app/settings/account/security) directly).\n4. Under the **Personal API keys** section, click **Create Key**.\n5. Give your key a descriptive label (e.g., \\\"Dify Integration\\\").\n6. Copy the generated key immediately (it won't be shown again).\n7. Paste the key into the **Linear Personal API Key** field in the plugin configuration section in Dify when adding the Linear plugin.\n\n**Important**: Your API key grants access to your Linear account according to its permissions. Keep it secure and never share it publicly.\n\n## Usage\n\nThe plugin provides the following tools that can be used in your Dify applications:\n\n### Create Linear Issue\n\nCreates a new issue in Linear with specified title, description, team, priority, and status.\n\nRequired parameters:\n- `title`: Title of the issue to create\n- `teamId`: ID of the team this issue belongs to\n\nOptional parameters:\n- `description`: Detailed description of the issue (Markdown supported)\n- `priority`: Priority level (0-4, where 0 is no priority and 1 is urgent)\n- `status`: Status of the issue (e.g., \"Todo\", \"In Progress\", \"Done\")\n\n### Update Linear Issue\n\nUpdates an existing issue in Linear.\n\nRequired parameters:\n- `id`: ID of the issue to update\n\nOptional parameters:\n- `title`: New title for the issue\n- `description`: New description for the issue\n- `priority`: New priority for the issue (0-4)\n- `status`: New workflow State ID for the issue\n- `assigneeId`: New assignee ID (use empty string \\\"\\\" or \\\"null\\\" to unassign)\n- `labels`: List of Label IDs to set for the issue (providing an empty list `[]` may clear existing labels, check API behavior)\n\n### Search Linear Issues\n\nSearches for issues in Linear using various criteria.\n\nOptional parameters:\n- `query`: Text to search in issue titles and descriptions\n- `teamId`: ID of the team to filter issues by\n- `status`: Filter issues by status name (e.g., \\\"In Progress\\\")\n- `assigneeId`: UUID of the user assigned to the issues\n- `labels`: Comma-separated list of label names to filter issues by\n- `priority`: Filter issues by priority level (1-4)\n- `limit`: Maximum number of issues to return (default: 10)\n- `includeArchived`: Whether to include archived issues in results\n\n### Get User Issues\n\nRetrieves issues assigned to a specific user.\n\nRequired parameter:\n- `userId`: UUID of the user whose issues to retrieve.\n\nOptional parameters:\n- `teamId`: Filter issues by a specific team ID.\n- `state`: Filter issues by a specific state name (e.g., \\\"Todo\\\").\n- `limit`: Maximum number of issues to return (default: 10, max: 50)\n\n### Add Comment to Issue\n\nAdds a comment to an existing Linear issue.\n\nRequired parameters:\n- `issueId`: ID of the issue to add a comment to\n- `body`: The text content of the comment (Markdown supported)\n\nOptional parameters:\n- `createAsUser`: Custom name to display for the comment\n- `displayIconUrl`: URL for the avatar icon to display with the comment\n\n### Get Linear Users\n\nSearches for users in Linear by name (partial match) or email (exact match) to retrieve their details.\n\nOptional parameters:\n- `name`: Partial name to search for (checks both name and display name, case-insensitive).\n- `email`: Exact email address to search for.\n- `limit`: Maximum number of users to return (default: 10, max: 50).\n\n*Note: You must provide either `name` or `email`.*\n\n### Get Linear Teams\n\nSearches for teams in Linear by name (partial match, case-insensitive).\n\nOptional parameters:\n- `name`: Partial name of the team to search for. If omitted, retrieves all accessible teams (up to limit).\n- `limit`: Maximum number of teams to return (default: 10, max: 50).\n\n### Get My Linear Profile\n\nRetrieves the profile information (ID, name, email) of the currently authenticated Linear user (based on the API key used).\n\nNo parameters required.\n\n## License\n\nThis plugin is licensed under the [MIT License](LICENSE).\n\n\n\n",
        "label": {
          "en_US": "Linear",
          "ja_JP": "Linear",
          "pt_BR": "Linear",
          "zh_Hans": "Linear"
        },
        "latest_package_identifier": "langgenius/linear:0.0.1@8046622d3ad7fd3c24a756ab58203750ac4caf1a0400f0d0d2563ed3ad9797f4",
        "latest_version": "0.0.1",
        "model": {},
        "name": "linear",
        "org": "langgenius",
        "plugin_id": "langgenius/linear",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/linear.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "app": {
              "enabled": true
            },
            "endpoint": {
              "enabled": true
            },
            "model": {
              "enabled": true,
              "llm": true,
              "moderation": false,
              "rerank": false,
              "speech2text": false,
              "text_embedding": false,
              "tts": false
            },
            "storage": {
              "enabled": true,
              "size": 1048576
            },
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [
          {
            "name": "productivity"
          },
          {
            "name": "business"
          }
        ],
        "tool": {
          "credentials_schema": [
            {
              "default": null,
              "help": {
                "en_US": "Found in Settings > Account > Security & access > Personal API keys",
                "ja_JP": "設定 > アカウント > セキュリティとアクセス > 個人用 API キー にあります",
                "pt_BR": "Encontrado em Configurações > Conta > Segurança e acesso > Chaves API pessoais",
                "zh_Hans": "可以在 设置 > 帐户 > 安全和访问 > 个人 API 密钥 中找到"
              },
              "label": {
                "en_US": "Linear Personal API Key",
                "ja_JP": "Linear 個人用 API キー",
                "pt_BR": "Chave API Pessoal do Linear",
                "zh_Hans": "Linear 个人 API 密钥"
              },
              "name": "linear_api_key",
              "options": null,
              "placeholder": {
                "en_US": "Enter your Linear Personal API key",
                "ja_JP": "Linear 個人用 API キーを入力してください",
                "pt_BR": "Digite sua chave API pessoal do Linear",
                "zh_Hans": "输入您的 Linear 个人 API 密钥"
              },
              "required": true,
              "scope": null,
              "type": "secret-input",
              "url": "https://linear.app/settings/account/security"
            }
          ],
          "identity": {
            "author": "langgenius",
            "description": {
              "en_US": "Linear is a project management tool for modern software teams.",
              "ja_JP": "Linearは、現代のソフトウェアチームのためのプロジェクト管理ツールです。",
              "pt_BR": "Linear é uma ferramenta de gerenciamento de projetos para equipes de software modernas.",
              "zh_Hans": "Linear 是现代软件团队的项目管理工具。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "Linear",
              "ja_JP": "Linear",
              "pt_BR": "Linear",
              "zh_Hans": "Linear"
            },
            "name": "linear",
            "tags": [
              "productivity",
              "business"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "Create a new issue in Linear with specified title, description, team, priority, and status.",
                  "ja_JP": "指定されたタイトル、説明、チーム、優先度、ステータスを持つ新しい課題を Linear に作成します。",
                  "pt_BR": "Criar um novo problema no Linear com título, descrição, equipe, prioridade e status especificados.",
                  "zh_Hans": "在 Linear 中创建一个具有指定标题、描述、团队、优先级和状态的新问题。"
                },
                "llm": "Creates a new Linear issue with specified details. Required fields are title and teamId, with optional description, priority (0-4, where 0 is no priority and 1 is urgent), and status."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Create Linear Issue",
                  "ja_JP": "Linear 課題を作成",
                  "pt_BR": "Criar problema no Linear",
                  "zh_Hans": "创建 Linear 问题"
                },
                "name": "linear_create_issue"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Title of the issue to create",
                    "ja_JP": "作成する課題のタイトル",
                    "pt_BR": "Título do problema a ser criado",
                    "zh_Hans": "要创建的问题的标题"
                  },
                  "label": {
                    "en_US": "Title",
                    "ja_JP": "タイトル",
                    "pt_BR": "Título",
                    "zh_Hans": "标题"
                  },
                  "llm_description": "Title of the issue to create in Linear",
                  "max": null,
                  "min": null,
                  "name": "title",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "ID of the team this issue belongs to",
                    "ja_JP": "この課題が所属するチームのID",
                    "pt_BR": "ID da equipe a qual este problema pertence",
                    "zh_Hans": "此问题所属的团队的 ID"
                  },
                  "label": {
                    "en_US": "Team ID",
                    "ja_JP": "チームID",
                    "pt_BR": "ID da Equipe",
                    "zh_Hans": "团队 ID"
                  },
                  "llm_description": "The unique identifier of the team in Linear where this issue should be created",
                  "max": null,
                  "min": null,
                  "name": "teamId",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Detailed description of the issue (Markdown supported)",
                    "ja_JP": "課題の詳細な説明（Markdown対応）",
                    "pt_BR": "Descrição detalhada do problema (Markdown suportado)",
                    "zh_Hans": "问题的详细描述（支持 Markdown）"
                  },
                  "label": {
                    "en_US": "Description",
                    "ja_JP": "説明",
                    "pt_BR": "Descrição",
                    "zh_Hans": "描述"
                  },
                  "llm_description": "A detailed description of the issue, supporting Markdown formatting",
                  "max": null,
                  "min": null,
                  "name": "description",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Priority of the issue (0-4, where 0 is no priority and 1 is urgent)",
                    "ja_JP": "課題の優先度（0-4、0は優先度なし、1は緊急）",
                    "pt_BR": "Prioridade do problema (0-4, onde 0 é sem prioridade e 1 é urgente)",
                    "zh_Hans": "问题的优先级（0-4，其中 0 表示无优先级，1 表示紧急）"
                  },
                  "label": {
                    "en_US": "Priority",
                    "ja_JP": "優先度",
                    "pt_BR": "Prioridade",
                    "zh_Hans": "优先级"
                  },
                  "llm_description": "The priority level of the issue (0=No priority, 1=Urgent, 2=High, 3=Normal, 4=Low)",
                  "max": null,
                  "min": null,
                  "name": "priority",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Status of the issue (e.g., \"Todo\", \"In Progress\", \"Done\")",
                    "ja_JP": "課題のステータス（例：「未着手」、「進行中」、「完了」）",
                    "pt_BR": "Status do problema (ex: \"A fazer\", \"Em andamento\", \"Concluído\")",
                    "zh_Hans": "问题的状态（例如，\"待办\"，\"进行中\"，\"已完成\"）"
                  },
                  "label": {
                    "en_US": "Status",
                    "ja_JP": "ステータス",
                    "pt_BR": "Status",
                    "zh_Hans": "状态"
                  },
                  "llm_description": "The workflow state ID of the issue",
                  "max": null,
                  "min": null,
                  "name": "status",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Update an existing issue in Linear with new title, description, priority, or status.",
                  "ja_JP": "新しいタイトル、説明、優先度、またはステータスで Linear の既存の課題を更新します。",
                  "pt_BR": "Atualizar um problema existente no Linear com novo título, descrição, prioridade ou status.",
                  "zh_Hans": "使用新的标题、描述、优先级或状态更新 Linear 中的现有问题。"
                },
                "llm": "Updates an existing Linear issue's properties. Requires the issue ID and accepts any combination of updatable fields including title, description, priority, or status."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Update Linear Issue",
                  "ja_JP": "Linear 課題を更新",
                  "pt_BR": "Atualizar problema no Linear",
                  "zh_Hans": "更新 Linear 问题"
                },
                "name": "linear_update_issue"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "ID of the issue to update",
                    "ja_JP": "更新する課題のID",
                    "pt_BR": "ID do problema a ser atualizado",
                    "zh_Hans": "要更新的问题的 ID"
                  },
                  "label": {
                    "en_US": "Issue ID",
                    "ja_JP": "課題ID",
                    "pt_BR": "ID do Problema",
                    "zh_Hans": "问题 ID"
                  },
                  "llm_description": "The unique identifier of the issue to update",
                  "max": null,
                  "min": null,
                  "name": "id",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "New title for the issue",
                    "ja_JP": "課題の新しいタイトル",
                    "pt_BR": "Novo título para o problema",
                    "zh_Hans": "问题的新标题"
                  },
                  "label": {
                    "en_US": "New Title",
                    "ja_JP": "新しいタイトル",
                    "pt_BR": "Novo Título",
                    "zh_Hans": "新标题"
                  },
                  "llm_description": "New title for the issue (leave empty to keep current title)",
                  "max": null,
                  "min": null,
                  "name": "title",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "New description for the issue (Markdown supported)",
                    "ja_JP": "課題の新しい説明（Markdown対応）",
                    "pt_BR": "Nova descrição para o problema (Markdown suportado)",
                    "zh_Hans": "问题的新描述（支持 Markdown）"
                  },
                  "label": {
                    "en_US": "New Description",
                    "ja_JP": "新しい説明",
                    "pt_BR": "Nova Descrição",
                    "zh_Hans": "新描述"
                  },
                  "llm_description": "New description for the issue, supporting Markdown formatting (leave empty to keep current description)",
                  "max": null,
                  "min": null,
                  "name": "description",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "New priority for the issue (0-4, where 0 is no priority and 1 is urgent)",
                    "ja_JP": "課題の新しい優先度（0-4、0は優先度なし、1は緊急）",
                    "pt_BR": "Nova prioridade para o problema (0-4, onde 0 é sem prioridade e 1 é urgente)",
                    "zh_Hans": "问题的新优先级（0-4，其中 0 表示无优先级，1 表示紧急）"
                  },
                  "label": {
                    "en_US": "New Priority",
                    "ja_JP": "新しい優先度",
                    "pt_BR": "Nova Prioridade",
                    "zh_Hans": "新优先级"
                  },
                  "llm_description": "New priority level of the issue (0=No priority, 1=Urgent, 2=High, 3=Normal, 4=Low)",
                  "max": null,
                  "min": null,
                  "name": "priority",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "New status for the issue (e.g., \"Todo\", \"In Progress\", \"Done\")",
                    "ja_JP": "課題の新しいステータス（例：「未着手」、「進行中」、「完了」）",
                    "pt_BR": "Novo status para o problema (ex: \"A fazer\", \"Em andamento\", \"Concluído\")",
                    "zh_Hans": "问题的新状态（例如，\"待办\"，\"进行中\"，\"已完成\"）"
                  },
                  "label": {
                    "en_US": "New Status",
                    "ja_JP": "新しいステータス",
                    "pt_BR": "Novo Status",
                    "zh_Hans": "新状态"
                  },
                  "llm_description": "New workflow state ID of the issue",
                  "max": null,
                  "min": null,
                  "name": "status",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Search for issues in Linear using various criteria such as text, team, status, assignee, labels, and priority.",
                  "ja_JP": "テキスト、チーム、ステータス、担当者、ラベル、優先度などのさまざまな条件を使用して Linear で課題を検索します。",
                  "pt_BR": "Pesquise problemas no Linear usando vários critérios como texto, equipe, status, responsável, etiquetas e prioridade.",
                  "zh_Hans": "使用各种条件在 Linear 中搜索问题，如文本、团队、状态、负责人、标签和优先级。"
                },
                "llm": "Searches Linear issues using flexible criteria. Supports filtering by any combination of title/description text, team, status, assignee, labels, priority (1=urgent, 2=high, 3=normal, 4=low), and estimate."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Search Linear Issues",
                  "ja_JP": "Linear 課題を検索",
                  "pt_BR": "Pesquisar problemas no Linear",
                  "zh_Hans": "搜索 Linear 问题"
                },
                "name": "linear_search_issues"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Text to search in issue titles and descriptions",
                    "ja_JP": "課題のタイトルと説明で検索するテキスト",
                    "pt_BR": "Texto para pesquisar em títulos e descrições de problemas",
                    "zh_Hans": "在问题标题和描述中搜索的文本"
                  },
                  "label": {
                    "en_US": "Search Text",
                    "ja_JP": "検索テキスト",
                    "pt_BR": "Texto de Pesquisa",
                    "zh_Hans": "搜索文本"
                  },
                  "llm_description": "Optional text to search in title and description of issues",
                  "max": null,
                  "min": null,
                  "name": "query",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "ID of the team to filter issues by",
                    "ja_JP": "課題をフィルタリングするチームのID",
                    "pt_BR": "ID da equipe para filtrar problemas",
                    "zh_Hans": "用于筛选问题的团队 ID"
                  },
                  "label": {
                    "en_US": "Team ID",
                    "ja_JP": "チームID",
                    "pt_BR": "ID da Equipe",
                    "zh_Hans": "团队 ID"
                  },
                  "llm_description": "Filter issues by team ID",
                  "max": null,
                  "min": null,
                  "name": "teamId",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Filter issues by status name (e.g., \"Todo\", \"In Progress\", \"Done\")",
                    "ja_JP": "ステータス名で課題をフィルタリング（例：「未着手」、「進行中」、「完了」）",
                    "pt_BR": "Filtrar problemas por nome de status (ex: \"A fazer\", \"Em andamento\", \"Concluído\")",
                    "zh_Hans": "按状态名称筛选问题（例如，\"待办\"，\"进行中\"，\"已完成\"）"
                  },
                  "label": {
                    "en_US": "Status",
                    "ja_JP": "ステータス",
                    "pt_BR": "Status",
                    "zh_Hans": "状态"
                  },
                  "llm_description": "Filter by status name (e.g., 'In Progress', 'Done')",
                  "max": null,
                  "min": null,
                  "name": "status",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "ID of the user assigned to the issues",
                    "ja_JP": "課題に割り当てられたユーザーのID",
                    "pt_BR": "ID do usuário atribuído aos problemas",
                    "zh_Hans": "分配给问题的用户的 ID"
                  },
                  "label": {
                    "en_US": "Assignee ID",
                    "ja_JP": "担当者ID",
                    "pt_BR": "ID do Responsável",
                    "zh_Hans": "负责人 ID"
                  },
                  "llm_description": "Filter by assignee's user ID",
                  "max": null,
                  "min": null,
                  "name": "assigneeId",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Filter issues by label names (comma-separated list)",
                    "ja_JP": "ラベル名で課題をフィルタリング（カンマ区切りリスト）",
                    "pt_BR": "Filtrar problemas por nomes de etiquetas (lista separada por vírgulas)",
                    "zh_Hans": "按标签名称筛选问题（逗号分隔的列表）"
                  },
                  "label": {
                    "en_US": "Labels",
                    "ja_JP": "ラベル",
                    "pt_BR": "Etiquetas",
                    "zh_Hans": "标签"
                  },
                  "llm_description": "Filter by label names (comma-separated list of label names)",
                  "max": null,
                  "min": null,
                  "name": "labels",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Filter issues by priority (0-4, where 0 is no priority and 1 is urgent)",
                    "ja_JP": "優先度で課題をフィルタリング（0-4、0は優先度なし、1は緊急）",
                    "pt_BR": "Filtrar problemas por prioridade (0-4, onde 0 é sem prioridade e 1 é urgente)",
                    "zh_Hans": "按优先级筛选问题（0-4，其中 0 表示无优先级，1 表示紧急）"
                  },
                  "label": {
                    "en_US": "Priority",
                    "ja_JP": "優先度",
                    "pt_BR": "Prioridade",
                    "zh_Hans": "优先级"
                  },
                  "llm_description": "Filter by priority (1=urgent, 2=high, 3=normal, 4=low)",
                  "max": null,
                  "min": null,
                  "name": "priority",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": 10,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Maximum number of issues to return (default: 10)",
                    "ja_JP": "返す課題の最大数（デフォルト：10）",
                    "pt_BR": "Número máximo de problemas a retornar (padrão: 10)",
                    "zh_Hans": "最多返回的问题数量（默认：10）"
                  },
                  "label": {
                    "en_US": "Result Limit",
                    "ja_JP": "結果制限",
                    "pt_BR": "Limite de Resultados",
                    "zh_Hans": "结果限制"
                  },
                  "llm_description": "Max results to return (default: 10)",
                  "max": null,
                  "min": null,
                  "name": "limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                },
                {
                  "auto_generate": null,
                  "default": false,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Include archived issues in search results",
                    "ja_JP": "検索結果にアーカイブされた課題を含める",
                    "pt_BR": "Incluir problemas arquivados nos resultados da pesquisa",
                    "zh_Hans": "在搜索结果中包含已归档的问题"
                  },
                  "label": {
                    "en_US": "Include Archived",
                    "ja_JP": "アーカイブを含む",
                    "pt_BR": "Incluir Arquivados",
                    "zh_Hans": "包含已归档"
                  },
                  "llm_description": "Include archived issues in results (default: false)",
                  "max": null,
                  "min": null,
                  "name": "includeArchived",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Retrieve issues assigned to a specific user in Linear or the current authenticated user.",
                  "ja_JP": "Linearの特定のユーザーまたは現在認証されているユーザーに割り当てられている課題を取得します。",
                  "pt_BR": "Recuperar problemas atribuídos a um usuário específico no Linear ou ao usuário autenticado atual.",
                  "zh_Hans": "检索分配给 Linear 中特定用户或当前认证用户的问题。"
                },
                "llm": "Retrieves issues assigned to a specific user or the authenticated user if no userId is provided. Returns issues sorted by last updated, including priority, status, and other metadata."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Get User Issues",
                  "ja_JP": "ユーザーの課題を取得",
                  "pt_BR": "Obter Problemas do Usuário",
                  "zh_Hans": "获取用户问题"
                },
                "name": "linear_get_user_issues"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "UUID of the user whose issues to retrieve (e.g., '123e4567-e89b-12d3-a456-426614174000'). Required.",
                    "ja_JP": "課題を取得するユーザーのUUID（例：'123e4567-e89b-12d3-a456-426614174000'）。必須。",
                    "pt_BR": "UUID do usuário cujos problemas serão recuperados (ex: '123e4567-e89b-12d3-a456-426614174000'). Obrigatório.",
                    "zh_Hans": "要检索其问题的用户的 UUID（例如，'123e4567-e89b-12d3-a456-426614174000'）。必填。"
                  },
                  "label": {
                    "en_US": "User ID",
                    "ja_JP": "ユーザーID",
                    "pt_BR": "ID do Usuário",
                    "zh_Hans": "用户 ID"
                  },
                  "llm_description": "Required user UUID (Universally Unique Identifier) to retrieve issues for. Must be in standard UUID format.",
                  "max": null,
                  "min": null,
                  "name": "userId",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Include archived issues in results",
                    "ja_JP": "結果にアーカイブされた課題を含める",
                    "pt_BR": "Incluir problemas arquivados nos resultados",
                    "zh_Hans": "在结果中包含已归档的问题"
                  },
                  "label": {
                    "en_US": "Include Archived",
                    "ja_JP": "アーカイブを含む",
                    "pt_BR": "Incluir Arquivados",
                    "zh_Hans": "包含已归档"
                  },
                  "llm_description": "Include archived issues in results",
                  "max": null,
                  "min": null,
                  "name": "includeArchived",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "boolean"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Maximum number of issues to return (default: 50)",
                    "ja_JP": "返す課題の最大数（デフォルト：50）",
                    "pt_BR": "Número máximo de problemas a retornar (padrão: 50)",
                    "zh_Hans": "最多返回的问题数量（默认：50）"
                  },
                  "label": {
                    "en_US": "Result Limit",
                    "ja_JP": "結果制限",
                    "pt_BR": "Limite de Resultados",
                    "zh_Hans": "结果限制"
                  },
                  "llm_description": "Maximum number of issues to return (default: 50)",
                  "max": null,
                  "min": null,
                  "name": "limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Add a comment to an existing Linear issue.",
                  "ja_JP": "既存の Linear 課題にコメントを追加します。",
                  "pt_BR": "Adicionar um comentário a um problema existente no Linear.",
                  "zh_Hans": "向现有的 Linear 问题添加评论。"
                },
                "llm": "Adds a comment to an existing Linear issue. Supports markdown formatting in the comment body. Can optionally specify a custom user name and avatar for the comment."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Add Comment to Issue",
                  "ja_JP": "課題にコメントを追加",
                  "pt_BR": "Adicionar Comentário ao Problema",
                  "zh_Hans": "添加评论到问题"
                },
                "name": "linear_add_comment"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "ID of the issue to add a comment to",
                    "ja_JP": "コメントを追加する課題のID",
                    "pt_BR": "ID do problema ao qual adicionar um comentário",
                    "zh_Hans": "要添加评论的问题的 ID"
                  },
                  "label": {
                    "en_US": "Issue ID",
                    "ja_JP": "課題ID",
                    "pt_BR": "ID do Problema",
                    "zh_Hans": "问题 ID"
                  },
                  "llm_description": "ID of the issue to comment on",
                  "max": null,
                  "min": null,
                  "name": "issueId",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The text content of the comment (Markdown supported)",
                    "ja_JP": "コメントのテキスト内容（Markdown対応）",
                    "pt_BR": "O conteúdo de texto do comentário (Markdown suportado)",
                    "zh_Hans": "评论的文本内容（支持 Markdown）"
                  },
                  "label": {
                    "en_US": "Comment Body",
                    "ja_JP": "コメント本文",
                    "pt_BR": "Corpo do Comentário",
                    "zh_Hans": "评论内容"
                  },
                  "llm_description": "Comment text in markdown format",
                  "max": null,
                  "min": null,
                  "name": "body",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Custom name to display for the comment",
                    "ja_JP": "コメントに表示するカスタム名",
                    "pt_BR": "Nome personalizado para exibir para o comentário",
                    "zh_Hans": "评论显示的自定义名称"
                  },
                  "label": {
                    "en_US": "Display Name",
                    "ja_JP": "表示名",
                    "pt_BR": "Nome de Exibição",
                    "zh_Hans": "显示名称"
                  },
                  "llm_description": "Optional custom username to show for the comment",
                  "max": null,
                  "min": null,
                  "name": "createAsUser",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "URL for the avatar icon to display with the comment",
                    "ja_JP": "コメントと一緒に表示するアバターアイコンのURL",
                    "pt_BR": "URL para o ícone de avatar a ser exibido com o comentário",
                    "zh_Hans": "与评论一起显示的头像图标的 URL"
                  },
                  "label": {
                    "en_US": "Avatar URL",
                    "ja_JP": "アバターURL",
                    "pt_BR": "URL do Avatar",
                    "zh_Hans": "头像 URL"
                  },
                  "llm_description": "Optional avatar URL for the comment",
                  "max": null,
                  "min": null,
                  "name": "displayIconUrl",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Search for users in Linear by name or email to retrieve their details, including user ID (UUID).",
                  "ja_JP": "名前またはメールアドレスで Linear のユーザーを検索し、ユーザーID（UUID）を含む詳細を取得します。",
                  "pt_BR": "Pesquise usuários no Linear por nome ou e-mail para recuperar seus detalhes, incluindo ID de usuário (UUID).",
                  "zh_Hans": "通过姓名或电子邮件在 Linear 中搜索用户，以检索其详细信息，包括用户 ID (UUID)。"
                },
                "llm": "Searches for Linear users based on name (partial match) or email (exact match). Returns a list of matching users including their ID (UUID), name, email, display name, and active status. Useful for finding a user's UUID needed for other tools."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Get Linear Users",
                  "ja_JP": "Linear ユーザーを取得",
                  "pt_BR": "Obter Usuários do Linear",
                  "zh_Hans": "获取 Linear 用户"
                },
                "name": "linear_get_users"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Partial name to search for (case-insensitive).",
                    "ja_JP": "検索する部分的な名前（大文字と小文字を区別しない）。",
                    "pt_BR": "Nome parcial para pesquisar (sem distinção entre maiúsculas e minúsculas).",
                    "zh_Hans": "要搜索的部分名称（不区分大小写）。"
                  },
                  "label": {
                    "en_US": "Name",
                    "ja_JP": "名前",
                    "pt_BR": "Nome",
                    "zh_Hans": "名称"
                  },
                  "llm_description": "Optional. Partial name to search for (case-insensitive). Use this OR email.",
                  "max": null,
                  "min": null,
                  "name": "name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Exact email address to search for.",
                    "ja_JP": "検索する正確なメールアドレス。",
                    "pt_BR": "Endereço de e-mail exato para pesquisar.",
                    "zh_Hans": "要搜索的确切电子邮件地址。"
                  },
                  "label": {
                    "en_US": "Email",
                    "ja_JP": "メールアドレス",
                    "pt_BR": "E-mail",
                    "zh_Hans": "电子邮件"
                  },
                  "llm_description": "Optional. Exact email address to search for. Use this OR name.",
                  "max": null,
                  "min": null,
                  "name": "email",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 10,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Maximum number of users to return (default: 10, max: 50).",
                    "ja_JP": "返すユーザーの最大数（デフォルト：10、最大：50）。",
                    "pt_BR": "Número máximo de usuários a retornar (padrão: 10, máx: 50).",
                    "zh_Hans": "最多返回的用户数量（默认：10，最大：50）。"
                  },
                  "label": {
                    "en_US": "Result Limit",
                    "ja_JP": "結果制限",
                    "pt_BR": "Limite de Resultados",
                    "zh_Hans": "结果限制"
                  },
                  "llm_description": "Max results to return (default: 10, max: 50).",
                  "max": null,
                  "min": null,
                  "name": "limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Search for teams in Linear by name to retrieve their details, including team ID.",
                  "ja_JP": "名前で Linear のチームを検索し、チームIDを含む詳細を取得します。",
                  "pt_BR": "Pesquise times no Linear por nome para recuperar seus detalhes, incluindo ID do time.",
                  "zh_Hans": "通过名称在 Linear 中搜索团队，以检索其详细信息，包括团队 ID。"
                },
                "llm": "Searches for Linear teams based on name (partial match, case-insensitive). Returns a list of matching teams including their ID, name, key, and description. Useful for finding a team's ID needed for creating issues."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Get Linear Teams",
                  "ja_JP": "Linear チームを取得",
                  "pt_BR": "Obter Times do Linear",
                  "zh_Hans": "获取 Linear 团队"
                },
                "name": "linear_get_teams"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Optional partial name of the team to search for (case-insensitive).",
                    "ja_JP": "検索するチームの部分的な名前（オプション、大文字と小文字を区別しない）。",
                    "pt_BR": "Nome parcial opcional do time para pesquisar (sem distinção entre maiúsculas e minúsculas).",
                    "zh_Hans": "要搜索的可选部分团队名称（不区分大小写）。"
                  },
                  "label": {
                    "en_US": "Name",
                    "ja_JP": "チーム名",
                    "pt_BR": "Nome do Time",
                    "zh_Hans": "团队名称"
                  },
                  "llm_description": "Optional. Partial name to search for (case-insensitive). If omitted, returns all accessible teams (up to the limit).",
                  "max": null,
                  "min": null,
                  "name": "name",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": 10,
                  "form": "llm",
                  "human_description": {
                    "en_US": "Maximum number of teams to return (default: 10, max: 50).",
                    "ja_JP": "返すチームの最大数（デフォルト：10、最大：50）。",
                    "pt_BR": "Número máximo de times a retornar (padrão: 10, máx: 50).",
                    "zh_Hans": "最多返回的团队数量（默认：10，最大：50）。"
                  },
                  "label": {
                    "en_US": "Result Limit",
                    "ja_JP": "結果制限",
                    "pt_BR": "Limite de Resultados",
                    "zh_Hans": "结果限制"
                  },
                  "llm_description": "Max results to return (default: 10, max: 50).",
                  "max": null,
                  "min": null,
                  "name": "limit",
                  "options": null,
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "number"
                }
              ]
            },
            {
              "description": {
                "human": {
                  "en_US": "Retrieves the profile information (ID, name, email) of the currently authenticated Linear user.",
                  "ja_JP": "現在認証されている Linear ユーザーのプロフィール情報（ID、名前、メールアドレス）を取得します。",
                  "pt_BR": "Recupera as informações do perfil (ID, nome, e-mail) do usuário Linear atualmente autenticado.",
                  "zh_Hans": "检索当前认证的 Linear 用户的个人资料信息（ID、姓名、电子邮件）。"
                },
                "llm": "Fetches the profile details (ID, name, email) for the user associated with the current Linear API key. Does not require any parameters."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "langgenius",
                "label": {
                  "en_US": "Get My Linear Profile",
                  "ja_JP": "私の Linear プロフィールを取得",
                  "pt_BR": "Obter Meu Perfil do Linear",
                  "zh_Hans": "获取我的 Linear 个人资料"
                },
                "name": "linear_get_my_profile"
              },
              "output_schema": null,
              "parameters": []
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-04-21T06:41:42Z",
        "version_updated_at": "2025-04-21T06:41:42Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "APRO AI Oracle API. We provide a wide range of oracle data, including market prices and news, and use distributed consensus to ensure data reliability and immutability.",
          "ja_JP": "APRO AIオラクルAPI。私たちは、市場価格やニュースを含む幅広いオラクルデータを提供し、分散型コンセンサスを使用してデータの信頼性と不変性を確保します。",
          "pt_BR": "APRO AI Oracle API. Fornecemos uma ampla gama de dados de oráculo, incluindo preços de mercado e notícias, e utilizamos consenso distribuído para garantir a confiabilidade e imutabilidade dos dados.",
          "zh_Hans": "APRO AI Oracle API。我们提供广泛的预言机数据，包括市场价格和新闻，并使用分布式共识确保数据的可靠性和不可变性。"
        },
        "category": "tool",
        "created_at": "2025-03-31T07:13:05Z",
        "endpoint": {},
        "icon": "apro/packages/apro_ai_oracle/_assets/icon.svg",
        "index_id": "apro___apro_ai_oracle",
        "install_count": 36,
        "introduction": "# APRO AI Oracle\n\n## Overview\n\nThe APRO AI Oracle tool is a real-time API that provide a wide range of oracle data, including market prices and news, and use distributed consensus to ensure data reliability and immutability.\n\n## Configuration\n\n### 1. Get APRO AI Oracle tools from Plugin Marketplace\n\nThe APRO AI Oracle tools could be found at the Plugin Marketplace, please install it first.\n\n### 2. Use the tool\n\nYou can use the APRO AI Oracle tool in the application any type\n\n\n#### Chatflow / Workflow applications\n\nBoth Chatflow and Workflow applications support adding a APRO AI Oracle tool node.\n\n#### Agent applications\n\nAdd the APRO AI Oracle tool in the Agent application, then enter online search instructions to call this tool.\n\n\n## Issues\n\nPlease report any issues to the [GitHub repository](https://github.com/APRO-com/dify-plugin-apro-ai-oracle/issues/new/choose).\n",
        "label": {
          "en_US": "APRO AI oracle",
          "ja_JP": "APRO AI oracle",
          "pt_BR": "APRO AI oracle",
          "zh_Hans": "APRO AI oracle"
        },
        "latest_package_identifier": "apro/apro_ai_oracle:0.0.2@bd1f9e59dafba2160a98335c43a3bc7fa111aa6c806b573524c02724f6dc4654",
        "latest_version": "0.0.2",
        "model": {},
        "name": "apro_ai_oracle",
        "org": "apro",
        "plugin_id": "apro/apro_ai_oracle",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": null,
          "tools": [
            "provider/apro_ai_oracle.yaml"
          ]
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "tool": {
              "enabled": true
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {
          "credentials_schema": [],
          "identity": {
            "author": "apro",
            "description": {
              "en_US": "APRO AI Oracle API. We provide a wide range of oracle data, including market prices and news, and use distributed consensus to ensure data reliability and immutability.",
              "pt_BR": "APRO AI Oracle API. Fornecemos uma ampla gama de dados de oráculo, incluindo preços de mercado e notícias, e utilizamos consenso distribuído para garantir a confiabilidade e imutabilidade dos dados.",
              "zh_Hans": "APRO AI Oracle API。我们提供广泛的预言机数据，包括市场价格和新闻，并使用分布式共识确保数据的可靠性和不可变性。"
            },
            "icon": "icon.svg",
            "label": {
              "en_US": "APRO AI oracle",
              "pt_BR": "APRO AI oracle",
              "zh_Hans": "APRO AI oracle"
            },
            "name": "apro_ai_oracle",
            "tags": [
              "finance",
              "utilities",
              "news"
            ]
          },
          "tools": [
            {
              "description": {
                "human": {
                  "en_US": "A tool that retrieves the price of a specific currency in a given quotation currency. The input should be the supported currency and the quotation currency.",
                  "pt_BR": "A tool that retrieves the price of a specific currency in a given quotation currency. The input should be the supported currency and the quotation currency.",
                  "zh_Hans": "一个获取特定货币在指定报价货币中的价格的工具。输入应该是支持的货币和报价货币"
                },
                "llm": "A tool that retrieves the price of a specific currency in a given quotation currency. The input should be the supported currency and the quotation currency."
              },
              "has_runtime_parameters": false,
              "identity": {
                "author": "apro",
                "label": {
                  "en_US": "Price of currency",
                  "pt_BR": "Price of currency",
                  "zh_Hans": "货币价格"
                },
                "name": "currency_price"
              },
              "output_schema": null,
              "parameters": [
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The user specifies the currency information to be queried.",
                    "pt_BR": "The user specifies the currency information to be queried.",
                    "zh_Hans": "用户制定需要查询的货币信息， 例如 btc"
                  },
                  "label": {
                    "en_US": "Currency information (name, symbol, or keyword)",
                    "pt_BR": "Currency information (name, symbol, or keyword)",
                    "zh_Hans": "查询货币信息（全名，货币符号 或者 关键字）"
                  },
                  "llm_description": "The user specifies the currency information to be queried.",
                  "max": null,
                  "min": null,
                  "name": "name",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": null,
                  "form": "llm",
                  "human_description": {
                    "en_US": "The user specifies the quotation currency information to be queried.",
                    "pt_BR": "The user specifies the quotation currency information to be queried.",
                    "zh_Hans": "用户制定需要查询的报价货币信息"
                  },
                  "label": {
                    "en_US": "Quotation currency (name, symbol, or keyword) (Example usd)",
                    "pt_BR": "Quotation currency (name, symbol, or keyword) (Example usd)",
                    "zh_Hans": "报价货币（名称、符号或关键词）（例如 USD）"
                  },
                  "llm_description": "The user specifies the quotation currency information to be queried.",
                  "max": null,
                  "min": null,
                  "name": "quotation",
                  "options": null,
                  "precision": null,
                  "required": true,
                  "scope": null,
                  "template": null,
                  "type": "string"
                },
                {
                  "auto_generate": null,
                  "default": "median",
                  "form": "form",
                  "human_description": {
                    "en_US": "The user specifies the aggregation method for querying the quotation.",
                    "pt_BR": "The user specifies the aggregation method for querying the quotation.",
                    "zh_Hans": "用户制定需要查询的报价的聚合方法"
                  },
                  "label": {
                    "en_US": "Aggregation method (median or average) (Default median)",
                    "pt_BR": "Aggregation method (median or average) (Default median)",
                    "zh_Hans": "聚合方法（中位数或平均值）（默认值：中位数）"
                  },
                  "llm_description": "The user specifies the aggregation method for querying the quotation.",
                  "max": null,
                  "min": null,
                  "name": "type",
                  "options": [
                    {
                      "label": {
                        "en_US": "median",
                        "zh_Hans": "中位数"
                      },
                      "value": "median"
                    },
                    {
                      "label": {
                        "en_US": "average",
                        "zh_Hans": "平均数"
                      },
                      "value": "average"
                    }
                  ],
                  "precision": null,
                  "required": false,
                  "scope": null,
                  "template": null,
                  "type": "select"
                }
              ]
            }
          ]
        },
        "type": "plugin",
        "updated_at": "2025-03-31T07:13:11Z",
        "version_updated_at": "2025-03-31T07:13:11Z"
      },
      {
        "agent_strategy": {},
        "badges": [],
        "brief": {
          "en_US": "lindormai",
          "ja_JP": "lindormai",
          "pt_BR": "lindormai",
          "zh_Hans": "lindormai"
        },
        "category": "model",
        "created_at": "2025-04-15T12:48:27Z",
        "endpoint": {},
        "icon": "jiangzhijie/packages/lindormai/_assets/icon_s_en.png",
        "index_id": "jiangzhijie___lindormai",
        "install_count": 26,
        "introduction": "## NOTE\nThis directory contains the code for Dify version 1.0.0 or later.\n\n* lindormai/ : source code of lindormai plugin\n* lindormai.difypkg : lindormai plugin package, you can use this file to install the lindormai plugin in lindorm.",
        "label": {
          "en_US": "lindormai",
          "ja_JP": "lindormai",
          "pt_BR": "lindormai",
          "zh_Hans": "lindormai"
        },
        "latest_package_identifier": "jiangzhijie/lindormai:0.0.1@2b780fe3db00d63f37ba1f9397471f922dbdfd8af89931fb76e905801c6dace2",
        "latest_version": "0.0.1",
        "model": {
          "background": "#FAF5FF",
          "configurate_methods": [
            "customizable-model"
          ],
          "description": {
            "en_US": "lindormai",
            "ja_JP": "lindormai",
            "pt_BR": "lindormai",
            "zh_Hans": "lindormai"
          },
          "help": {
            "title": {
              "en_US": "How to deploy your model in Lindorm AI Engine",
              "zh_Hans": "如何在Lindorm AI引擎部署模型"
            },
            "url": {
              "en_US": "https://help.aliyun.com/document_detail/2393245.html?spm=a2c4g.11186623.help-menu-172543.d_2_7.4b0f1513fp0y82&scm=20140722.H_2393245._.OR_help-T_cn#DAS#zh-V_1"
            }
          },
          "icon_large": {
            "en_US": "icon_l_en.png"
          },
          "icon_small": {
            "en_US": "icon_s_en.png"
          },
          "label": {
            "en_US": "LindormAI"
          },
          "model_credential_schema": {
            "credential_form_schemas": [
              {
                "default": null,
                "label": {
                  "en_US": "Lindorm AI Engine URL",
                  "zh_Hans": "Lindorm AI Engine URL"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter the URL of you LindormAI, e.g. http://ld-xxxxxxxxxxxxx-proxy-ai-pub.lindorm.aliyuncs.com:9002",
                  "zh_Hans": "在此输入Lindorm的AI连接地址，如 http://ld-xxxxxxxxxxxxx-proxy-ai-pub.lindorm.aliyuncs.com:9002"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "lindormai_endpoint"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Username",
                  "zh_Hans": "lindorm 用户名"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter your lindorm username",
                  "zh_Hans": "在此输入您的用户名"
                },
                "required": true,
                "show_on": [],
                "type": "text-input",
                "variable": "lindormai_username"
              },
              {
                "default": null,
                "label": {
                  "en_US": "Password",
                  "zh_Hans": "密码"
                },
                "max_length": 0,
                "options": [],
                "placeholder": {
                  "en_US": "Enter the password",
                  "zh_Hans": "在此输入您的密码"
                },
                "required": true,
                "show_on": [],
                "type": "secret-input",
                "variable": "lindormai_password"
              }
            ],
            "model": {
              "label": {
                "en_US": "Model Name",
                "zh_Hans": "模型名称"
              },
              "placeholder": {
                "en_US": "Enter your deployed model name",
                "zh_Hans": "输入部署的模型名称"
              }
            }
          },
          "models": [],
          "provider": "lindormai",
          "provider_credential_schema": null,
          "supported_model_types": [
            "text-embedding",
            "rerank"
          ]
        },
        "name": "lindormai",
        "org": "jiangzhijie",
        "plugin_id": "jiangzhijie/lindormai",
        "plugins": {
          "agent_strategies": null,
          "endpoints": null,
          "models": [
            "provider/lindormai.yaml"
          ],
          "tools": null
        },
        "privacy_options": "",
        "privacy_policy": "PRIVACY.md",
        "repository": "",
        "resource": {
          "memory": 268435456,
          "permission": {
            "model": {
              "enabled": true,
              "llm": false,
              "moderation": false,
              "rerank": true,
              "speech2text": false,
              "text_embedding": true,
              "tts": false
            }
          }
        },
        "status": "active",
        "tags": [],
        "tool": {},
        "type": "plugin",
        "updated_at": "2025-04-15T12:48:36Z",
        "version_updated_at": "2025-04-15T12:48:36Z"
      }
    ],
    "total": 274
  },
  "msg": "ok"
}